chore: 从 git 跟踪中移除日志文件、onu.md 和 __pycache__

- 移除 logs/ 目录下的日志文件
- 移除 onu.md 生成文件
- 移除所有 __pycache__/ 目录
- 更新 .gitignore 防止再次提交

.env.example

@@ -0,0 +1,30 @@
+# 应用
+DEBUG=false
+LOG_LEVEL=INFO
+
+# 数据库
+DATABASE_URL=postgresql+asyncpg://gx-gp-notify:password@10.10.10.14:5432/gx-gp-notify
+
+# 爬虫
+CRAWLER_BASE_URL=https://zfcg.gxzf.gov.cn
+CRAWLER_KEYWORDS=["大化"]
+CRAWLER_MAX_PAGES=10
+CRAWLER_TIMEOUT=30
+
+# 企业微信
+WECHAT_ENABLED=true
+WECHAT_CORP_ID=ww69e8e44636f47780
+WECHAT_AGENT_ID=1000007
+WECHAT_SECRET=
+WECHAT_TOKEN=
+WECHAT_ENCODING_AES_KEY=
+WECHAT_PORT=18001
+WECHAT_HOST=0.0.0.0
+
+# 定时任务
+SCHEDULER_ENABLED=true
+SCHEDULER_CRON=0 8,14,18 * * *
+
+# Markdown
+MARKDOWN_ENABLED=true
+MARKDOWN_OUTPUT_FILE=onu.md

.gitignore

@@ -0,0 +1,13 @@
+.env
+logs/
+*.log
+__pycache__/
+*.pyc
+.venv/
+.ruff_cache/
+.pytest_cache/
+*.egg-info/
+dist/
+config.yaml
+gx_gp_monitor/config/config.yaml
+onu.md

alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# this is typically a path given in POSIX (e.g. forward slashes)
+# format, relative to the token %(here)s which refers to the location of this
+# ini file
+script_location = %(here)s/alembic
+
+# template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
+# Uncomment the line below if you want the files to be prepended with date and time
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be installed by adding
+# `alembic[tz]` to the pip requirements.
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

alembic/env.py

@@ -0,0 +1,34 @@
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+from app.models.announcement import Base
+
+config = context.config
+
+target_metadata = Base.metadata
+
+
+def run_migrations_offline():
+    from app.config import settings
+    url = settings.database_url
+    context.configure(url=url, target_metadata=target_metadata, literal_binds=True)
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    from app.config import settings
+    connectable = engine_from_config(
+        {"sqlalchemy.url": settings.database_url},
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

alembic/versions/567cd83d63c2_create_announcements_table.py

@@ -0,0 +1,194 @@
+"""create_announcements_table
+
+Revision ID: 567cd83d63c2
+Revises: 
+Create Date: 2026-05-09 13:33:26.593143
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = '567cd83d63c2'
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('auto_announcements')
+    op.drop_table('announcement_sources')
+    op.drop_index(op.f('idx_dahuagov_content_hash'), table_name='dahuagov_announcements')
+    op.drop_index(op.f('idx_dahuagov_created_at'), table_name='dahuagov_announcements')
+    op.drop_index(op.f('idx_dahuagov_publish_date'), table_name='dahuagov_announcements')
+    op.drop_table('dahuagov_announcements')
+    op.drop_index(op.f('idx_crawl_results_crawled_at'), table_name='crawl_results')
+    op.drop_table('crawl_results')
+    op.drop_table('manual_announcements')
+    op.add_column('announcements', sa.Column('is_sent', sa.Boolean(), nullable=False))
+    op.alter_column('announcements', 'purchase_name',
+               existing_type=sa.VARCHAR(length=200),
+               nullable=False)
+    op.alter_column('announcements', 'content_url',
+               existing_type=sa.TEXT(),
+               nullable=False)
+    op.alter_column('announcements', 'content_hash',
+               existing_type=sa.VARCHAR(length=32),
+               type_=sa.String(length=64),
+               nullable=False)
+    op.alter_column('announcements', 'crawl_mode',
+               existing_type=sa.VARCHAR(length=20),
+               nullable=False,
+               existing_server_default=sa.text("'auto'::character varying"))
+    op.alter_column('announcements', 'is_new',
+               existing_type=sa.BOOLEAN(),
+               nullable=False,
+               existing_server_default=sa.text('true'))
+    op.alter_column('announcements', 'keyword_matched',
+               existing_type=sa.BOOLEAN(),
+               nullable=False,
+               existing_server_default=sa.text('false'))
+    op.alter_column('announcements', 'created_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=False,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.alter_column('announcements', 'updated_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=False,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.drop_index(op.f('idx_announcements_content_hash'), table_name='announcements')
+    op.drop_index(op.f('idx_announcements_created_at'), table_name='announcements')
+    op.drop_index(op.f('idx_announcements_publish_date'), table_name='announcements')
+    op.drop_index(op.f('idx_announcements_source_code'), table_name='announcements')
+    op.drop_column('announcements', 'date_filtered')
+    op.drop_column('announcements', 'is_today')
+    op.drop_column('announcements', 'crawled_at')
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('announcements', sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True))
+    op.add_column('announcements', sa.Column('is_today', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True))
+    op.add_column('announcements', sa.Column('date_filtered', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True))
+    op.create_index(op.f('idx_announcements_source_code'), 'announcements', ['source_code'], unique=False)
+    op.create_index(op.f('idx_announcements_publish_date'), 'announcements', [sa.literal_column('publish_date DESC')], unique=False)
+    op.create_index(op.f('idx_announcements_created_at'), 'announcements', [sa.literal_column('created_at DESC')], unique=False)
+    op.create_index(op.f('idx_announcements_content_hash'), 'announcements', ['content_hash'], unique=False)
+    op.alter_column('announcements', 'updated_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=True,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.alter_column('announcements', 'created_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=True,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.alter_column('announcements', 'keyword_matched',
+               existing_type=sa.BOOLEAN(),
+               nullable=True,
+               existing_server_default=sa.text('false'))
+    op.alter_column('announcements', 'is_new',
+               existing_type=sa.BOOLEAN(),
+               nullable=True,
+               existing_server_default=sa.text('true'))
+    op.alter_column('announcements', 'crawl_mode',
+               existing_type=sa.VARCHAR(length=20),
+               nullable=True,
+               existing_server_default=sa.text("'auto'::character varying"))
+    op.alter_column('announcements', 'content_hash',
+               existing_type=sa.String(length=64),
+               type_=sa.VARCHAR(length=32),
+               nullable=True)
+    op.alter_column('announcements', 'content_url',
+               existing_type=sa.TEXT(),
+               nullable=True)
+    op.alter_column('announcements', 'purchase_name',
+               existing_type=sa.VARCHAR(length=200),
+               nullable=True)
+    op.drop_column('announcements', 'is_sent')
+    op.create_table('manual_announcements',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('title', sa.VARCHAR(length=500), autoincrement=False, nullable=False),
+    sa.Column('publish_date', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+    sa.Column('purchase_name', sa.VARCHAR(length=200), autoincrement=False, nullable=True),
+    sa.Column('content_url', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('source_code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('source_name', sa.VARCHAR(length=100), autoincrement=False, nullable=False),
+    sa.Column('announcement_type', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('content_hash', sa.VARCHAR(length=32), autoincrement=False, nullable=True),
+    sa.Column('keyword_matched', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.Column('date_filtered', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_new', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_today', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.PrimaryKeyConstraint('id', name=op.f('manual_announcements_pkey'))
+    )
+    op.create_table('crawl_results',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('source_code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('status', sa.VARCHAR(length=20), autoincrement=False, nullable=False),
+    sa.Column('total_count', sa.INTEGER(), server_default=sa.text('0'), autoincrement=False, nullable=True),
+    sa.Column('new_count', sa.INTEGER(), server_default=sa.text('0'), autoincrement=False, nullable=True),
+    sa.Column('error_message', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('duration', sa.DOUBLE_PRECISION(precision=53), server_default=sa.text('0.0'), autoincrement=False, nullable=True),
+    sa.ForeignKeyConstraint(['source_code'], ['announcement_sources.code'], name=op.f('crawl_results_source_code_fkey')),
+    sa.PrimaryKeyConstraint('id', name=op.f('crawl_results_pkey'))
+    )
+    op.create_index(op.f('idx_crawl_results_crawled_at'), 'crawl_results', [sa.literal_column('crawled_at DESC')], unique=False)
+    op.create_table('dahuagov_announcements',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('title', sa.VARCHAR(length=500), autoincrement=False, nullable=False),
+    sa.Column('publish_date', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+    sa.Column('purchase_name', sa.VARCHAR(length=200), autoincrement=False, nullable=True),
+    sa.Column('content_url', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('source_code', sa.VARCHAR(length=50), server_default=sa.text("'dahuagov'::character varying"), autoincrement=False, nullable=False),
+    sa.Column('source_name', sa.VARCHAR(length=100), server_default=sa.text("'大化县政府网采购公告'::character varying"), autoincrement=False, nullable=False),
+    sa.Column('announcement_type', sa.VARCHAR(length=50), server_default=sa.text("'purchase'::character varying"), autoincrement=False, nullable=False),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('content_hash', sa.VARCHAR(length=32), autoincrement=False, nullable=True),
+    sa.Column('is_new', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.PrimaryKeyConstraint('id', name=op.f('dahuagov_announcements_pkey')),
+    sa.UniqueConstraint('content_hash', name=op.f('dahuagov_announcements_content_hash_key'), postgresql_include=[], postgresql_nulls_not_distinct=False)
+    )
+    op.create_index(op.f('idx_dahuagov_publish_date'), 'dahuagov_announcements', [sa.literal_column('publish_date DESC')], unique=False)
+    op.create_index(op.f('idx_dahuagov_created_at'), 'dahuagov_announcements', [sa.literal_column('created_at DESC')], unique=False)
+    op.create_index(op.f('idx_dahuagov_content_hash'), 'dahuagov_announcements', ['content_hash'], unique=False)
+    op.create_table('announcement_sources',
+    sa.Column('code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('category_id', sa.INTEGER(), autoincrement=False, nullable=False),
+    sa.Column('name', sa.VARCHAR(length=100), autoincrement=False, nullable=False),
+    sa.Column('type', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.PrimaryKeyConstraint('code', name=op.f('announcement_sources_pkey'))
+    )
+    op.create_table('auto_announcements',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('title', sa.VARCHAR(length=500), autoincrement=False, nullable=False),
+    sa.Column('publish_date', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+    sa.Column('purchase_name', sa.VARCHAR(length=200), autoincrement=False, nullable=True),
+    sa.Column('content_url', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('source_code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('source_name', sa.VARCHAR(length=100), autoincrement=False, nullable=False),
+    sa.Column('announcement_type', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('content_hash', sa.VARCHAR(length=32), autoincrement=False, nullable=True),
+    sa.Column('keyword_matched', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.Column('date_filtered', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_new', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_today', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.PrimaryKeyConstraint('id', name=op.f('auto_announcements_pkey')),
+    sa.UniqueConstraint('content_hash', name=op.f('auto_announcements_content_hash_key'), postgresql_include=[], postgresql_nulls_not_distinct=False)
+    )
+    # ### end Alembic commands ###

app/api/announcements.py

@@ -0,0 +1,108 @@
+from datetime import datetime
+
+from fastapi import APIRouter, Depends, HTTPException, Query
+from sqlalchemy import func, select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.api.deps import get_db
+from app.models.announcement import Announcement
+from app.models.schemas import AnnouncementListResponse, AnnouncementResponse
+
+router = APIRouter()
+
+
+@router.get("/announcements", response_model=AnnouncementListResponse)
+async def list_announcements(
+    page: int = Query(1, ge=1),
+    page_size: int = Query(20, ge=1, le=100),
+    source_code: str | None = None,
+    keyword: str | None = None,
+    start_date: str | None = None,
+    end_date: str | None = None,
+    crawl_mode: str | None = None,
+    db: AsyncSession = Depends(get_db),
+):
+    conditions = []
+    if source_code:
+        conditions.append(Announcement.source_code == source_code)
+    if crawl_mode:
+        conditions.append(Announcement.crawl_mode == crawl_mode)
+    if start_date:
+        conditions.append(Announcement.publish_date >= start_date)
+    if end_date:
+        conditions.append(Announcement.publish_date <= end_date)
+    if keyword:
+        conditions.append(
+            Announcement.title.ilike(f"%{keyword}%")
+        )
+
+    base_query = select(Announcement)
+    if conditions:
+        base_query = base_query.where(*conditions)
+
+    count_query = select(func.count()).select_from(base_query.subquery())
+    total_result = await db.execute(count_query)
+    total = total_result.scalar() or 0
+
+    items_query = base_query.order_by(Announcement.publish_date.desc()) \
+        .offset((page - 1) * page_size).limit(page_size)
+    items_result = await db.execute(items_query)
+    items = items_result.scalars().all()
+
+    return AnnouncementListResponse(
+        total=total,
+        page=page,
+        page_size=page_size,
+        items=[AnnouncementResponse.model_validate(item) for item in items],
+    )
+
+
+@router.get("/announcements/{announcement_id}", response_model=AnnouncementResponse)
+async def get_announcement(announcement_id: int, db: AsyncSession = Depends(get_db)):
+    result = await db.execute(
+        select(Announcement).where(Announcement.id == announcement_id)
+    )
+    item = result.scalar_one_or_none()
+    if item is None:
+        raise HTTPException(status_code=404, detail="公告不存在")
+    return AnnouncementResponse.model_validate(item)
+
+
+@router.get("/announcements/today", response_model=AnnouncementListResponse)
+async def get_today_announcements(db: AsyncSession = Depends(get_db)):
+    today = datetime.now().date()
+    result = await db.execute(
+        select(Announcement).where(
+            func.date(Announcement.publish_date) == today
+        ).order_by(Announcement.publish_date.desc())
+    )
+    items = result.scalars().all()
+    return AnnouncementListResponse(
+        total=len(items), page=1, page_size=len(items),
+        items=[AnnouncementResponse.model_validate(item) for item in items],
+    )
+
+
+@router.get("/announcements/stats")
+async def get_stats(db: AsyncSession = Depends(get_db)):
+    total = await db.execute(select(func.count()).select_from(Announcement))
+    today_count = await db.execute(
+        select(func.count()).where(
+            func.date(Announcement.publish_date) == func.current_date()
+        ).select_from(Announcement)
+    )
+    new_count = await db.execute(
+        select(func.count()).where(Announcement.is_new == True)  # noqa: E712
+        .select_from(Announcement)
+    )
+    unsent = await db.execute(
+        select(func.count()).where(
+            Announcement.is_sent == False, Announcement.is_new == True  # noqa: E712
+        ).select_from(Announcement)
+    )
+    return {
+        "total": total.scalar() or 0,
+        "today": today_count.scalar() or 0,
+        "new": new_count.scalar() or 0,
+        "unsent": unsent.scalar() or 0,
+    }

app/api/crawl.py

@@ -0,0 +1,46 @@
+from fastapi import APIRouter
+
+from app.api.deps import get_crawl_service
+from app.models.schemas import CrawlTriggerRequest
+
+router = APIRouter()
+
+
+@router.post("/crawl/trigger")
+async def trigger_crawl(request: CrawlTriggerRequest):
+    service = get_crawl_service()
+    names = service.get_spider_names()
+
+    all_results = []
+    for name in names:
+        results = await service.run_spider(name)
+        all_results.extend(results)
+
+    return {
+        "spiders_run": names,
+        "total_announcements": sum(r.total_count for r in all_results),
+        "errors": [r.error_message for r in all_results if not r.success],
+    }
+
+
+@router.get("/crawl/status")
+async def crawl_status():
+    service = get_crawl_service()
+    return {
+        "spiders": service.get_spider_names(),
+        "running": False,
+    }
+
+
+@router.get("/crawl/sources")
+async def crawl_sources():
+    import json
+
+    from app.config import settings
+    sources = json.loads(settings.announcement_sources)
+    return {
+        "sources": [
+            {"code": code, "name": info["name"], "type": info["type"]}
+            for code, info in sources.items()
+        ]
+    }

app/api/deps.py

@@ -0,0 +1,23 @@
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.crawler.dahuagov_spider import DahuagovSpider
+from app.crawler.gxgp_spider import GXGPSpider
+from app.services.crawl_service import CrawlService
+
+
+async def get_db() -> AsyncSession:
+    from app.main import async_session  # 延迟导入避免循环引用
+    async with async_session() as session:
+        yield session
+
+
+_crawl_service: CrawlService | None = None
+
+
+def get_crawl_service() -> CrawlService:
+    global _crawl_service
+    if _crawl_service is None:
+        _crawl_service = CrawlService()
+        _crawl_service.register(GXGPSpider())
+        _crawl_service.register(DahuagovSpider())
+    return _crawl_service

app/api/router.py

@@ -0,0 +1,10 @@
+from fastapi import APIRouter
+
+from app.api import announcements, crawl, wechat
+from app.api import scheduler as scheduler_module
+
+api_router = APIRouter(prefix="/api/v1")
+api_router.include_router(announcements.router, tags=["announcements"])
+api_router.include_router(crawl.router, tags=["crawl"])
+api_router.include_router(wechat.router, tags=["wechat"])
+api_router.include_router(scheduler_module.router)

app/api/scheduler.py

@@ -0,0 +1,30 @@
+from fastapi import APIRouter
+
+from app.models.schemas import JobResponse
+from app.scheduler.jobs import scheduler
+
+router = APIRouter(prefix="/scheduler", tags=["scheduler"])
+
+
+@router.get("/jobs")
+async def list_jobs():
+    jobs = []
+    for job in scheduler.get_jobs():
+        jobs.append(JobResponse(
+            id=job.id,
+            name=job.name,
+            next_run_time=str(job.next_run_time) if job.next_run_time else None,
+        ))
+    return {"jobs": jobs}
+
+
+@router.post("/pause/{job_id}")
+async def pause_job(job_id: str):
+    scheduler.pause_job(job_id)
+    return {"status": "paused", "job_id": job_id}
+
+
+@router.post("/resume/{job_id}")
+async def resume_job(job_id: str):
+    scheduler.resume_job(job_id)
+    return {"status": "resumed", "job_id": job_id}

app/api/wechat.py

@@ -0,0 +1,68 @@
+from fastapi import APIRouter, Request, Response
+
+from app.wechat.handler import WeChatMessageHandler
+
+router = APIRouter()
+
+_handler: WeChatMessageHandler | None = None
+
+
+def get_handler() -> WeChatMessageHandler:
+    global _handler
+    if _handler is None:
+        _handler = WeChatMessageHandler()
+    return _handler
+
+
+@router.get("/wechat/callback")
+async def wechat_verify(request: Request):
+    handler = get_handler()
+    params = request.query_params
+    echostr = handler.verify_url(
+        params.get("msg_signature", ""),
+        params.get("timestamp", ""),
+        params.get("nonce", ""),
+        params.get("echostr", ""),
+    )
+    if echostr:
+        return Response(content=echostr, media_type="text/plain")
+    return Response(content="verification failed", status_code=403)
+
+
+@router.post("/wechat/callback")
+async def wechat_callback(request: Request):
+    handler = get_handler()
+    params = request.query_params
+    post_data = await request.body()
+    post_text = post_data.decode("utf-8")
+
+    xml_tree = handler.decrypt_message(
+        post_text,
+        params.get("msg_signature", ""),
+        params.get("timestamp", ""),
+        params.get("nonce", ""),
+    )
+    if xml_tree is None:
+        return Response(content="decrypt failed", status_code=403)
+
+    msg_type = xml_tree.find("MsgType")
+    msg_type = msg_type.text if msg_type is not None else "unknown"
+
+    if msg_type == "event":
+        event = xml_tree.find("Event")
+        event_key = xml_tree.find("EventKey")
+        from_user = xml_tree.find("FromUserName")
+        handler.handle_event(
+            event.text if event is not None else "",
+            event_key.text if event_key is not None else None,
+            from_user.text if from_user is not None else "",
+        )
+    elif msg_type == "text":
+        content = xml_tree.find("Content")
+        from_user = xml_tree.find("FromUserName")
+        handler.handle_text(
+            content.text if content is not None else "",
+            from_user.text if from_user is not None else "",
+        )
+
+    return Response(content="success")

app/config.py

@@ -0,0 +1,44 @@
+
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+
+class Settings(BaseSettings):
+    model_config = SettingsConfigDict(env_file=".env", env_file_encoding="utf-8")
+
+    # 应用
+    debug: bool = False
+    log_level: str = "INFO"
+
+    # 数据库
+    database_url: str = "postgresql+asyncpg://gx-gp-notify:password@localhost:5432/gx-gp-notify"
+
+    # 爬虫
+    crawler_base_url: str = "https://zfcg.gxzf.gov.cn"
+    crawler_keywords: list[str] = ["大化"]
+    crawler_max_pages: int = 10
+    crawler_timeout: int = 30
+    crawler_page_size: int = 100
+
+    # 企业微信
+    wechat_enabled: bool = True
+    wechat_corp_id: str = ""
+    wechat_agent_id: str = ""
+    wechat_secret: str = ""
+    wechat_token: str = ""
+    wechat_encoding_aes_key: str = ""
+    wechat_port: int = 18001
+    wechat_host: str = "0.0.0.0"
+
+    # 定时任务
+    scheduler_enabled: bool = True
+    scheduler_cron: str = "0 8,14,18 * * *"
+
+    # Markdown
+    markdown_enabled: bool = True
+    markdown_output_file: str = "onu.md"
+
+    # 公告来源（JSON 字符串，从环境变量读取）
+    announcement_sources: str = '{"ZcyAnnouncement1":{"category_id":66485,"name":"采购公告","type":"purchase"},"ZcyAnnouncement2":{"category_id":66485,"name":"结果公告","type":"result"},"ZcyAnnouncement3":{"category_id":66485,"name":"合同公告","type":"contract"},"ZcyAnnouncement4":{"category_id":66485,"name":"更正公告","type":"correction"},"ZcyAnnouncement5":{"category_id":66485,"name":"招标文件预公示","type":"pre_announcement"},"ZcyAnnouncement6":{"category_id":66485,"name":"单一来源公示","type":"single_source"},"ZcyAnnouncement7":{"category_id":66485,"name":"电子卖场公示","type":"electronic_market"},"ZcyAnnouncement10":{"category_id":66485,"name":"履约验收公示","type":"acceptance"},"ZcyAnnouncement11":{"category_id":66485,"name":"工程类公告","type":"engineering"},"ZcyAnnouncement20":{"category_id":66485,"name":"框架协议征集公告","type":"framework_agreement"},"ZcyAnnouncement21":{"category_id":66485,"name":"框架协议入围结果公告","type":"framework_result"},"ZcyAnnouncement23":{"category_id":66485,"name":"框架协议成交结果汇总公告","type":"framework_summary"},"61-266648":{"category_id":66485,"name":"采购意向公开","type":"intention"}}'  # noqa: E501
+
+
+settings = Settings()

app/crawler/base.py

@@ -0,0 +1,56 @@
+import hashlib
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from datetime import datetime
+
+
+@dataclass
+class CrawlResult:
+    source_code: str
+    source_name: str
+    total_count: int = 0
+    new_count: int = 0
+    announcements: list = field(default_factory=list)
+    error_message: str | None = None
+    crawled_at: datetime = field(default_factory=datetime.now)
+    duration: float = 0.0
+
+    @property
+    def success(self) -> bool:
+        return self.error_message is None
+
+
+@dataclass
+class PipelineConfig:
+    filter_enabled: bool = True
+    keywords: list[str] = field(default_factory=list)
+    dedup_enabled: bool = True
+    notify_mode: str = "filtered"
+    mark_sent: bool = False
+
+
+@dataclass
+class PipelineResult:
+    stored: int = 0
+    filtered: int = 0
+    notified: int = 0
+    markdown_generated: bool = False
+
+
+class BaseSpider(ABC):
+    name: str
+    source_code: str
+    source_name: str
+
+    @abstractmethod
+    async def crawl(self) -> CrawlResult:
+        ...
+
+    def get_pipeline_config(self) -> PipelineConfig:
+        return PipelineConfig()
+
+    @staticmethod
+    def generate_content_hash(title: str, publish_date: str, purchase_name: str,
+                              content_url: str, source_code: str) -> str:
+        content = f"{title}|{publish_date}|{purchase_name}|{content_url}|{source_code}"
+        return hashlib.sha256(content.encode("utf-8")).hexdigest()

app/crawler/dahuagov_spider.py

@@ -0,0 +1,74 @@
+import asyncio
+import random
+from datetime import datetime
+
+import httpx
+
+from app.config import settings
+from app.crawler.base import BaseSpider, CrawlResult, PipelineConfig
+from app.crawler.parsers import parse_dahuagov_html
+
+
+class DahuagovSpider(BaseSpider):
+    name = "dahuagov"
+    source_code = "dahuagov"
+    source_name = "大化县政府网采购公告"
+
+    BASE_URL = "http://www.gxdh.gov.cn"
+    ANNOUNCEMENT_PATH = "/xxgk/zdlyxxgk/ggzypzly/zfcgly/cggg/"
+
+    def get_pipeline_config(self) -> PipelineConfig:
+        return PipelineConfig(
+            filter_enabled=False,
+            keywords=[],
+            dedup_enabled=True,
+            notify_mode="all",
+            mark_sent=True,
+        )
+
+    async def crawl(self) -> CrawlResult:
+        start_time = datetime.now()
+        url = self.BASE_URL + self.ANNOUNCEMENT_PATH
+
+        async with httpx.AsyncClient(timeout=settings.crawler_timeout) as client:
+            await self._delay()
+            try:
+                headers = {
+                    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+                    "Accept": "text/html,application/xhtml+xml",
+                    "Accept-Language": "zh-CN,zh;q=0.9",
+                    "Referer": self.BASE_URL,
+                }
+                response = await client.get(url, headers=headers)
+                if response.status_code != 200:
+                    return CrawlResult(
+                        source_code=self.source_code,
+                        source_name=self.source_name,
+                        error_message=f"HTTP {response.status_code}",
+                        crawled_at=start_time,
+                    )
+                html = response.text
+            except Exception as e:
+                return CrawlResult(
+                    source_code=self.source_code,
+                    source_name=self.source_name,
+                    error_message=str(e),
+                    crawled_at=start_time,
+                )
+
+        announcements = parse_dahuagov_html(html, start_time)
+        duration = (datetime.now() - start_time).total_seconds()
+
+        return CrawlResult(
+            source_code=self.source_code,
+            source_name=self.source_name,
+            total_count=len(announcements),
+            new_count=len(announcements),
+            announcements=announcements,
+            crawled_at=start_time,
+            duration=duration,
+        )
+
+    async def _delay(self):
+        delay = random.uniform(1.0, 3.0)
+        await asyncio.sleep(delay)

app/crawler/gxgp_spider.py

@@ -0,0 +1,118 @@
+import json
+import random
+import time
+from datetime import datetime
+
+import httpx
+
+from app.config import settings
+from app.crawler.base import BaseSpider, CrawlResult, PipelineConfig
+from app.crawler.parsers import extract_pagination, parse_gxgp_api_response
+
+
+class GXGPSpider(BaseSpider):
+    name = "gxgp"
+    source_code = "gxgp"
+    source_name = "广西政府采购网"
+
+    def __init__(self):
+        self.base_url = settings.crawler_base_url
+        self.announcement_api = f"{self.base_url}/portal/category"
+
+    def get_pipeline_config(self) -> PipelineConfig:
+        return PipelineConfig(
+            filter_enabled=True,
+            keywords=list(settings.crawler_keywords),
+            dedup_enabled=True,
+            notify_mode="filtered",
+            mark_sent=False,
+        )
+
+    async def crawl(self, sources: list[str] | None = None,
+                    max_pages: int | None = None) -> CrawlResult:
+        if max_pages is None:
+            max_pages = settings.crawler_max_pages
+        if sources is None:
+            source_map = json.loads(settings.announcement_sources)
+            sources = list(source_map.keys())
+
+        start_time = datetime.now()
+        all_announcements = []
+        error_messages = []
+
+        async with httpx.AsyncClient(timeout=settings.crawler_timeout) as client:
+            for source_code in sources:
+                source_info = json.loads(settings.announcement_sources).get(source_code)
+                if not source_info:
+                    continue
+
+                category_id = source_info["category_id"]
+                source_name = source_info["name"]
+
+                for page_no in range(1, max_pages + 1):
+                    if page_no > 1:
+                        await self._delay()
+
+                    try:
+                        data = await self._fetch_page(
+                            client, source_code, category_id, page_no
+                        )
+                        if data is None:
+                            break
+
+                        records = parse_gxgp_api_response(
+                            data, source_code, source_name,
+                            start_time, category_id
+                        )
+                        if not records:
+                            break
+
+                        all_announcements.extend(records)
+
+                        pagination = extract_pagination(data)
+                        if not pagination["has_next"]:
+                            break
+                    except Exception as e:
+                        error_messages.append(f"{source_code} page {page_no}: {e}")
+                        break
+
+        duration = (datetime.now() - start_time).total_seconds()
+        return CrawlResult(
+            source_code=self.source_code,
+            source_name=self.source_name,
+            total_count=len(all_announcements),
+            new_count=len(all_announcements),
+            announcements=all_announcements,
+            error_message="; ".join(error_messages) if error_messages else None,
+            crawled_at=start_time,
+            duration=duration,
+        )
+
+    async def _fetch_page(self, client: httpx.AsyncClient, source_code: str,
+                          category_id: int, page_no: int) -> dict | None:
+        payload = {
+            "keyword": "",
+            "publishDateBegin": "",
+            "publishDateEnd": "",
+            "pageNo": page_no,
+            "pageSize": settings.crawler_page_size,
+            "categoryCode": source_code,
+            "_t": int(time.time() * 1000),
+        }
+        headers = {
+            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36",
+            "Content-Type": "application/json;charset=UTF-8",
+            "Origin": self.base_url,
+            "Referer": f"{self.base_url}/site/category?parentId={category_id}&childrenCode={source_code}",  # noqa: E501
+        }
+        response = await client.post(
+            self.announcement_api, json=payload, headers=headers
+        )
+        if response.status_code != 200:
+            return None
+        return response.json()
+
+    async def _delay(self):
+        import asyncio
+        delay = random.uniform(1.0, 3.0)
+        await asyncio.sleep(delay)

app/crawler/parsers.py

@@ -0,0 +1,139 @@
+import hashlib
+from datetime import datetime
+from typing import Any
+from urllib.parse import urljoin
+
+from bs4 import BeautifulSoup
+
+
+def parse_gxgp_api_response(
+    response_data: dict[str, Any],
+    source_code: str,
+    source_name: str,
+    crawled_at: datetime,
+    category_id: int,
+) -> list[dict[str, Any]]:
+    if not response_data.get("success"):
+        return []
+    data = response_data.get("result", {}).get("data", {})
+    records = data.get("data", [])
+    if not records:
+        return []
+
+    results = []
+    for record in records:
+        title = str(record.get("title", "")).strip()
+        if not title:
+            continue
+
+        timestamp = record.get("publishDate")
+        if not timestamp:
+            continue
+        try:
+            publish_date = datetime.fromtimestamp(int(timestamp) / 1000)
+        except (ValueError, TypeError):
+            continue
+
+        purchase_name = str(record.get("purchaseName", "")).strip()
+        article_id = record.get("articleId")
+        if not article_id:
+            continue
+
+        content_url = (
+            f"https://zfcg.gxzf.gov.cn/site/detail?"
+            f"parentId={category_id}&articleId={article_id}"
+        )
+
+        announce = {
+            "title": title,
+            "publish_date": publish_date,
+            "purchase_name": purchase_name,
+            "content_url": content_url,
+            "source_code": source_code,
+            "source_name": source_name,
+            "announcement_type": "purchase",
+            "crawl_mode": "auto",
+            "is_new": True,
+            "is_today": publish_date.date() == datetime.now().date(),
+        }
+        announce["content_hash"] = _generate_hash(announce)
+        results.append(announce)
+
+    return results
+
+
+def extract_pagination(response_data: dict[str, Any]) -> dict[str, Any]:
+    data = response_data.get("result", {}).get("data", {})
+    return {
+        "total": data.get("total", 0),
+        "page_no": data.get("pageNo", 1),
+        "page_size": data.get("pageSize", 100),
+        "pages": data.get("pages", 0),
+        "empty": data.get("empty", True),
+        "has_next": data.get("hasNext", False),
+        "has_previous": data.get("hasPrevious", False),
+    }
+
+
+def parse_dahuagov_html(html: str, crawled_at: datetime) -> list[dict[str, Any]]:
+    soup = BeautifulSoup(html, "html.parser")
+    lists = soup.find_all("ul", class_="more-list")
+    if not lists:
+        return []
+
+    results = []
+    base_url = "http://www.gxdh.gov.cn"
+    base_path = "/xxgk/zdlyxxgk/ggzypzly/zfcgly/cggg/"
+
+    for ul in lists:
+        for li in ul.find_all("li"):
+            date_span = li.find("span")
+            if not date_span:
+                continue
+            date_text = date_span.get_text(strip=True)
+            try:
+                publish_date = datetime.strptime(date_text, "%Y-%m-%d")
+            except ValueError:
+                continue
+
+            link_tag = li.find("a")
+            if not link_tag:
+                continue
+            title = link_tag.get("title", "") or link_tag.get_text(strip=True)
+            href = link_tag.get("href", "")
+            if not title or not href:
+                continue
+
+            if href.startswith("./") or href.startswith("../"):
+                content_url = urljoin(base_url + base_path, href)
+            elif href.startswith("/"):
+                content_url = base_url + href
+            elif href.startswith("http"):
+                content_url = href
+            else:
+                content_url = urljoin(base_url + base_path, href)
+
+            announce = {
+                "title": title,
+                "publish_date": publish_date,
+                "purchase_name": "大化瑶族自治县",
+                "content_url": content_url,
+                "source_code": "dahuagov",
+                "source_name": "大化县政府网采购公告",
+                "announcement_type": "purchase",
+                "crawl_mode": "auto",
+                "is_new": True,
+                "is_today": publish_date.date() == datetime.now().date(),
+            }
+            announce["content_hash"] = _generate_hash(announce)
+            results.append(announce)
+
+    return results
+
+
+def _generate_hash(ann: dict[str, Any]) -> str:
+    content = (
+        f"{ann['title']}|{ann['publish_date'].strftime('%Y-%m-%d')}"
+        f"|{ann['purchase_name']}|{ann['content_url']}|{ann['source_code']}"
+    )
+    return hashlib.sha256(content.encode("utf-8")).hexdigest()

app/main.py

@@ -0,0 +1,45 @@
+import logging
+from contextlib import asynccontextmanager
+
+from fastapi import FastAPI
+from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker, create_async_engine
+
+from app.api.router import api_router
+from app.config import settings
+
+engine = create_async_engine(settings.database_url, echo=settings.debug)
+async_session = async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
+
+
+async def get_db() -> AsyncSession:
+    async with async_session() as session:
+        yield session
+
+
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    logging.basicConfig(
+        level=getattr(logging, settings.log_level),
+        format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
+    )
+    from app.scheduler.jobs import shutdown_scheduler, start_scheduler
+    start_scheduler()
+    yield
+    shutdown_scheduler()
+    await engine.dispose()
+
+
+app = FastAPI(
+    title="广西政府采购网公告监控系统",
+    version="2.0.0",
+    lifespan=lifespan,
+    docs_url="/docs" if settings.debug else None,
+    redoc_url=None,
+)
+
+app.include_router(api_router)
+
+
+@app.get("/health")
+async def health():
+    return {"status": "ok"}

app/models/announcement.py

@@ -0,0 +1,42 @@
+import hashlib
+from datetime import datetime
+
+from sqlalchemy import Boolean, DateTime, Integer, String, Text, func
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
+
+
+class Base(DeclarativeBase):
+    pass
+
+
+class Announcement(Base):
+    __tablename__ = "announcements"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
+    title: Mapped[str] = mapped_column(String(500), nullable=False)
+    publish_date: Mapped[datetime] = mapped_column(DateTime, nullable=False)
+    purchase_name: Mapped[str] = mapped_column(String(200), default="")
+    content_url: Mapped[str] = mapped_column(Text, default="")
+    source_code: Mapped[str] = mapped_column(String(50), nullable=False)
+    source_name: Mapped[str] = mapped_column(String(100), nullable=False)
+    announcement_type: Mapped[str] = mapped_column(String(50), default="purchase")
+    content_hash: Mapped[str] = mapped_column(String(64), unique=True, nullable=False)
+    crawl_mode: Mapped[str] = mapped_column(String(20), default="auto")
+    is_new: Mapped[bool] = mapped_column(Boolean, default=True)
+    is_sent: Mapped[bool] = mapped_column(Boolean, default=False)
+    keyword_matched: Mapped[bool] = mapped_column(Boolean, default=False)
+    created_at: Mapped[datetime] = mapped_column(DateTime, server_default=func.now())
+    updated_at: Mapped[datetime] = mapped_column(DateTime, server_default=func.now(), onupdate=func.now())  # noqa: E501
+
+    @staticmethod
+    def generate_hash(title: str, publish_date: str, purchase_name: str,
+                      content_url: str, source_code: str) -> str:
+        content = f"{title}|{publish_date}|{purchase_name}|{content_url}|{source_code}"
+        return hashlib.sha256(content.encode("utf-8")).hexdigest()
+
+    @staticmethod
+    def source_map() -> dict:
+        import json
+
+        from app.config import settings
+        return json.loads(settings.announcement_sources)

app/models/schemas.py

@@ -0,0 +1,56 @@
+from datetime import datetime
+
+from pydantic import BaseModel
+
+
+class AnnouncementResponse(BaseModel):
+    id: int
+    title: str
+    publish_date: datetime
+    purchase_name: str
+    content_url: str
+    source_code: str
+    source_name: str
+    announcement_type: str
+    crawl_mode: str
+    is_new: bool
+    is_sent: bool
+    keyword_matched: bool
+    created_at: datetime
+
+    model_config = {"from_attributes": True}
+
+
+class AnnouncementListResponse(BaseModel):
+    total: int
+    page: int
+    page_size: int
+    items: list[AnnouncementResponse]
+
+
+class CrawlTriggerRequest(BaseModel):
+    keywords: list[str] | None = None
+    sources: list[str] | None = None
+    manual: bool = False
+
+
+class CrawlStatusResponse(BaseModel):
+    running: bool
+    last_crawl_time: datetime | None = None
+    total_sources: int
+
+
+class SourceInfo(BaseModel):
+    code: str
+    name: str
+    type: str
+
+
+class SourcesResponse(BaseModel):
+    sources: list[SourceInfo]
+
+
+class JobResponse(BaseModel):
+    id: str
+    name: str
+    next_run_time: str | None = None

app/scheduler/jobs.py

@@ -0,0 +1,48 @@
+import logging
+
+from apscheduler.schedulers.asyncio import AsyncIOScheduler
+
+from app.api.deps import get_crawl_service
+from app.config import settings
+
+logger = logging.getLogger(__name__)
+scheduler = AsyncIOScheduler()
+
+
+async def scheduled_crawl():
+    logger.info("开始定时爬取任务")
+    service = get_crawl_service()
+    names = service.get_spider_names()
+    for name in names:
+        try:
+            results = await service.run_spider(name)
+            for r in results:
+                if not r.success:
+                    logger.error(f"Spider {name} 失败: {r.error_message}")
+                else:
+                    logger.info(f"Spider {name} 完成: {r.total_count} 条")
+        except Exception as e:
+            logger.error(f"Spider {name} 异常: {e}")
+    logger.info("定时爬取任务完成")
+
+
+def start_scheduler():
+    if not settings.scheduler_enabled:
+        return
+    scheduler.add_job(
+        scheduled_crawl,
+        "cron",
+        hour="8,14,18",
+        minute="0",
+        id="scheduled_crawl",
+        name="定时爬取",
+        timezone="Asia/Shanghai",
+    )
+    scheduler.start()
+    logger.info("APScheduler 已启动 (8:00, 14:00, 18:00)")
+
+
+def shutdown_scheduler():
+    if scheduler.running:
+        scheduler.shutdown(wait=False)
+        logger.info("APScheduler 已停止")

app/services/crawl_service.py

@@ -0,0 +1,36 @@
+
+from app.crawler.base import BaseSpider, CrawlResult
+
+
+class CrawlService:
+    def __init__(self):
+        self.spiders: dict[str, BaseSpider] = {}
+
+    def register(self, spider: BaseSpider):
+        self.spiders[spider.name] = spider
+
+    async def run_all(self) -> list[CrawlResult]:
+        results = []
+        for name, spider in self.spiders.items():
+            result = await spider.crawl()
+            results.append(result)
+        return results
+
+    async def run_spider(self, name: str, **kwargs) -> list[CrawlResult]:
+        spider = self.spiders.get(name)
+        if spider is None:
+            return [CrawlResult(
+                source_code=name, source_name=name,
+                error_message=f"Spider not found: {name}"
+            )]
+        result = await spider.crawl(**kwargs)
+        return [result]
+
+    def get_spider_names(self) -> list[str]:
+        return list(self.spiders.keys())
+
+    def get_pipeline_config(self, name: str):
+        spider = self.spiders.get(name)
+        if spider:
+            return spider.get_pipeline_config()
+        return None

app/services/filter_service.py

@@ -0,0 +1,53 @@
+from datetime import date
+from typing import Any
+
+
+def filter_by_keywords(announcements: list[dict[str, Any]],
+                       keywords: list[str]) -> list[dict[str, Any]]:
+    if not keywords:
+        return announcements
+
+    filtered = []
+    for ann in announcements:
+        search_text = f"{ann.get('title', '')} {ann.get('purchase_name', '')}"
+        if any(kw in search_text for kw in keywords):
+            ann["keyword_matched"] = True
+            filtered.append(ann)
+
+    return filtered
+
+
+def filter_by_date(announcements: list[dict[str, Any]],
+                   start_date: date | None = None,
+                   end_date: date | None = None) -> list[dict[str, Any]]:
+    if not start_date and not end_date:
+        return announcements
+
+    filtered = []
+    for ann in announcements:
+        pub_date = ann.get("publish_date")
+        if not pub_date:
+            continue
+        if not isinstance(pub_date, date):
+            pub_date = pub_date.date() if hasattr(pub_date, "date") else None
+        if pub_date is None:
+            continue
+
+        if start_date and pub_date < start_date:
+            continue
+        if end_date and pub_date > end_date:
+            continue
+        filtered.append(ann)
+
+    return filtered
+
+
+def dedup_by_hash(announcements: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    seen = set()
+    result = []
+    for ann in announcements:
+        h = ann.get("content_hash")
+        if h and h not in seen:
+            seen.add(h)
+            result.append(ann)
+    return result

app/services/notification_service.py

@@ -0,0 +1,46 @@
+from typing import Any
+
+from app.config import settings
+from app.wechat.client import WeChatClient
+
+
+class NotificationService:
+    def __init__(self):
+        self.client = WeChatClient()
+
+    async def send(self, announcements: list[dict[str, Any]]) -> int:
+        if not settings.wechat_enabled:
+            return 0
+        if not announcements:
+            return 0
+
+        sent = 0
+        for ann in announcements:
+            try:
+                title = ann.get("title", "")
+                if len(title) > 128:
+                    title = title[:125] + "..."
+
+                purchase_name = ann.get("purchase_name", "")
+                if len(purchase_name) > 25:
+                    purchase_name = purchase_name[:22] + "..."
+
+                pub_date = ann.get("publish_date")
+                time_str = pub_date.strftime("%Y-%m-%d %H:%M") if pub_date else "时间未知"
+
+                source_name = ann.get("source_name", "")
+
+                description = (
+                    f'<div style="font-size: 14px; margin-top: 8px;">'
+                    f'{source_name} | {purchase_name} | {time_str}'
+                    f'</div>'
+                )
+
+                url = ann.get("content_url", "")
+
+                if await self.client.send_textcard(title, description, url):
+                    sent += 1
+            except Exception:
+                continue
+
+        return sent

app/services/pipeline.py

@@ -0,0 +1,105 @@
+from typing import Any
+
+from app.crawler.base import PipelineConfig, PipelineResult
+from app.services.filter_service import dedup_by_hash
+
+
+class PostCrawlPipeline:
+    def __init__(self, db_session, notification_service):
+        self.db = db_session
+        self.notify = notification_service
+
+    async def process(self, announcements: list[dict[str, Any]],
+                      config: PipelineConfig) -> PipelineResult:
+        result = PipelineResult()
+
+        if not announcements:
+            return result
+
+        # 1. Dedup
+        if config.dedup_enabled:
+            announcements = dedup_by_hash(announcements)
+
+        # 2. Store to database
+        stored = await self._save_to_db(announcements)
+        result.stored = stored
+
+        to_notify = announcements
+
+        # 3. Filter
+        if config.filter_enabled and config.keywords:
+            before = len(to_notify)
+            to_notify = [a for a in to_notify
+                         if self._match_keywords(a, config.keywords)]
+            result.filtered = before - len(to_notify)
+
+        # 4. Notify
+        if config.notify_mode == "all":
+            result.notified = await self._send_notifications(to_notify)
+        elif config.notify_mode == "filtered":
+            if config.filter_enabled and config.keywords:
+                result.notified = await self._send_notifications(to_notify)
+            elif not config.filter_enabled:
+                result.notified = await self._send_notifications(to_notify)
+
+        # 5. Mark sent
+        if config.mark_sent and result.notified > 0:
+            await self._mark_sent(to_notify)
+
+        return result
+
+    async def _save_to_db(self, announcements: list[dict[str, Any]]) -> int:
+        from sqlalchemy.dialects.postgresql import insert
+
+        from app.models.announcement import Announcement
+
+        if not announcements:
+            return 0
+
+        values = [{
+            "title": a["title"],
+            "publish_date": a["publish_date"],
+            "purchase_name": a.get("purchase_name", ""),
+            "content_url": a.get("content_url", ""),
+            "source_code": a["source_code"],
+            "source_name": a["source_name"],
+            "announcement_type": a.get("announcement_type", "purchase"),
+            "content_hash": a["content_hash"],
+            "crawl_mode": a.get("crawl_mode", "auto"),
+            "is_new": a.get("is_new", True),
+            "is_sent": False,
+            "keyword_matched": a.get("keyword_matched", False),
+        } for a in announcements]
+
+        stmt = insert(Announcement).values(values)
+        stmt = stmt.on_conflict_do_nothing(index_elements=["content_hash"])
+
+        result_proxy = await self.db.execute(stmt)
+        await self.db.commit()
+        return result_proxy.rowcount if result_proxy.rowcount >= 0 else len(values)
+
+    async def _send_notifications(self, announcements: list[dict[str, Any]]) -> int:
+        return await self.notify.send(announcements)
+
+    async def _mark_sent(self, announcements: list[dict[str, Any]]) -> int:
+        from sqlalchemy import update
+
+        from app.models.announcement import Announcement
+
+        hashes = [a["content_hash"] for a in announcements if a.get("content_hash")]
+        if not hashes:
+            return 0
+
+        stmt = (
+            update(Announcement)
+            .where(Announcement.content_hash.in_(hashes))
+            .values(is_sent=True)
+        )
+        result = await self.db.execute(stmt)
+        await self.db.commit()
+        return result.rowcount
+
+    @staticmethod
+    def _match_keywords(announcement: dict[str, Any], keywords: list[str]) -> bool:
+        text = f"{announcement.get('title', '')} {announcement.get('purchase_name', '')}"
+        return any(kw in text for kw in keywords)

app/wechat/client.py

@@ -0,0 +1,76 @@
+import time
+
+import httpx
+
+from app.config import settings
+
+
+class WeChatClient:
+    def __init__(self):
+        self._access_token: str | None = None
+        self._token_expires_at: float = 0
+
+    async def _get_access_token(self) -> str | None:
+        now = time.time()
+        if self._access_token and now < self._token_expires_at:
+            return self._access_token
+
+        url = "https://qyapi.weixin.qq.com/cgi-bin/gettoken"
+        params = {
+            "corpid": settings.wechat_corp_id,
+            "corpsecret": settings.wechat_secret,
+        }
+        async with httpx.AsyncClient(timeout=30) as client:
+            response = await client.get(url, params=params)
+            data = response.json()
+            if data.get("errcode") == 0:
+                self._access_token = data["access_token"]
+                self._token_expires_at = now + data.get("expires_in", 7200) - 300
+                return self._access_token
+        return None
+
+    async def send_text(self, content: str, to_user: str = "@all") -> bool:
+        return await self._send_message("text", {"content": content}, to_user)
+
+    async def send_markdown(self, content: str, to_user: str = "@all") -> bool:
+        return await self._send_message("markdown", {"content": content}, to_user)
+
+    async def send_textcard(
+        self,
+        title: str,
+        description: str,
+        url: str,
+        to_user: str = "@all",
+        btn_txt: str = "查看详情",
+    ) -> bool:
+        return await self._send_message(
+            "textcard",
+            {
+                "title": title,
+                "description": description,
+                "url": url,
+                "btntxt": btn_txt,
+            },
+            to_user,
+        )
+
+    async def _send_message(
+        self, msgtype: str, msg_data: dict, to_user: str = "@all"
+    ) -> bool:
+        token = await self._get_access_token()
+        if not token:
+            return False
+
+        url = "https://qyapi.weixin.qq.com/cgi-bin/message/send"
+        params = {"access_token": token}
+        body = {
+            "touser": to_user,
+            "msgtype": msgtype,
+            "agentid": int(settings.wechat_agent_id),
+            msgtype: msg_data,
+        }
+
+        async with httpx.AsyncClient(timeout=30) as client:
+            response = await client.post(url, params=params, json=body)
+            data = response.json()
+            return data.get("errcode") == 0

app/wechat/crypto.py

@@ -0,0 +1,283 @@
+#!/usr/bin/env python
+
+""" 对企业微信发送给企业后台的消息加解密示例代码.
+@copyright: Copyright (c) 1998-2014 Tencent Inc.
+
+"""
+# ------------------------------------------------------------------------
+import base64
+import hashlib
+import logging
+import random
+import socket
+import struct
+import time
+import xml.etree.ElementTree as ET
+
+from Crypto.Cipher import AES
+
+try:
+    import ierror
+except ImportError:
+    from . import ierror
+
+
+"""
+关于Crypto.Cipher模块，ImportError: No module named 'Crypto'解决方案
+请到官方网站 https://www.dlitz.net/software/pycrypto/ 下载pycrypto。
+下载后，按照README中的“Installation”小节的提示进行pycrypto安装。
+"""
+
+
+class FormatError(Exception):
+    pass
+
+
+def throw_exception(message, exception_class=FormatError):
+    """my define raise exception function"""
+    raise exception_class(message)
+
+
+class SHA1:
+    """计算企业微信的消息签名接口"""
+
+    def getSHA1(self, token, timestamp, nonce, encrypt):
+        """用SHA1算法生成安全签名
+        @param token:  票据
+        @param timestamp: 时间戳
+        @param encrypt: 密文
+        @param nonce: 随机字符串
+        @return: 安全签名
+        """
+        try:
+            sortlist = [token, timestamp, nonce, encrypt]
+            sortlist.sort()
+            sha = hashlib.sha1()
+            sha.update("".join(sortlist).encode())
+            return ierror.WXBizMsgCrypt_OK, sha.hexdigest()
+        except Exception as e:
+            logger = logging.getLogger()
+            logger.error(e)
+            return ierror.WXBizMsgCrypt_ComputeSignature_Error, None
+
+
+class XMLParse:
+    """提供提取消息格式中的密文及生成回复消息格式的接口"""
+
+    # xml消息模板
+    AES_TEXT_RESPONSE_TEMPLATE = """<xml>
+<Encrypt><![CDATA[%(msg_encrypt)s]]></Encrypt>
+<MsgSignature><![CDATA[%(msg_signaturet)s]]></MsgSignature>
+<TimeStamp>%(timestamp)s</TimeStamp>
+<Nonce><![CDATA[%(nonce)s]]></Nonce>
+</xml>"""
+
+    def extract(self, xmltext):
+        """提取出xml数据包中的加密消息
+        @param xmltext: 待提取的xml字符串
+        @return: 提取出的加密消息字符串
+        """
+        try:
+            xml_tree = ET.fromstring(xmltext)
+            encrypt = xml_tree.find("Encrypt")
+            return ierror.WXBizMsgCrypt_OK, encrypt.text
+        except Exception as e:
+            logger = logging.getLogger()
+            logger.error(e)
+            return ierror.WXBizMsgCrypt_ParseXml_Error, None
+
+    def generate(self, encrypt, signature, timestamp, nonce):
+        """生成xml消息
+        @param encrypt: 加密后的消息密文
+        @param signature: 安全签名
+        @param timestamp: 时间戳
+        @param nonce: 随机字符串
+        @return: 生成的xml字符串
+        """
+        resp_dict = {
+            'msg_encrypt': encrypt,
+            'msg_signaturet': signature,
+            'timestamp': timestamp,
+            'nonce': nonce,
+        }
+        resp_xml = self.AES_TEXT_RESPONSE_TEMPLATE % resp_dict
+        return resp_xml
+
+
+class PKCS7Encoder:
+    """提供基于PKCS7算法的加解密接口"""
+
+    block_size = 32
+
+    def encode(self, text):
+        """ 对需要加密的明文进行填充补位
+        @param text: 需要进行填充补位操作的明文
+        @return: 补齐明文字符串
+        """
+        text_length = len(text)
+        # 计算需要填充的位数
+        amount_to_pad = self.block_size - (text_length % self.block_size)
+        if amount_to_pad == 0:
+            amount_to_pad = self.block_size
+        # 获得补位所用的字符
+        pad = chr(amount_to_pad)
+        return text + (pad * amount_to_pad).encode()
+
+    def decode(self, decrypted):
+        """删除解密后明文的补位字符
+        @param decrypted: 解密后的明文
+        @return: 删除补位字符后的明文
+        """
+        pad = ord(decrypted[-1])
+        if pad < 1 or pad > 32:
+            pad = 0
+        return decrypted[:-pad]
+
+
+class Prpcrypt:
+    """提供接收和推送给企业微信消息的加解密接口"""
+
+    def __init__(self, key):
+
+        # self.key = base64.b64decode(key+"=")
+        self.key = key
+        # 设置加解密模式为AES的CBC模式
+        self.mode = AES.MODE_CBC
+
+    def encrypt(self, text, receiveid):
+        """对明文进行加密
+        @param text: 需要加密的明文
+        @return: 加密得到的字符串
+        """
+        # 16位随机字符串添加到明文开头
+        text = text.encode()
+        text = self.get_random_str() + struct.pack("I", socket.htonl(len(text))) + text + receiveid.encode()  # noqa: E501
+
+        # 使用自定义的填充方式对明文进行补位填充
+        pkcs7 = PKCS7Encoder()
+        text = pkcs7.encode(text)
+        # 加密
+        cryptor = AES.new(self.key, self.mode, self.key[:16])
+        try:
+            ciphertext = cryptor.encrypt(text)
+            # 使用BASE64对加密后的字符串进行编码
+            return ierror.WXBizMsgCrypt_OK, base64.b64encode(ciphertext)
+        except Exception as e:
+            logger = logging.getLogger()
+            logger.error(e)
+            return ierror.WXBizMsgCrypt_EncryptAES_Error, None
+
+    def decrypt(self, text, receiveid):
+        """对解密后的明文进行补位删除
+        @param text: 密文
+        @return: 删除填充补位后的明文
+        """
+        try:
+            cryptor = AES.new(self.key, self.mode, self.key[:16])
+            # 使用BASE64对密文进行解码，然后AES-CBC解密
+            plain_text = cryptor.decrypt(base64.b64decode(text))
+        except Exception as e:
+            logger = logging.getLogger()
+            logger.error(e)
+            return ierror.WXBizMsgCrypt_DecryptAES_Error, None
+        try:
+            pad = plain_text[-1]
+            # 去掉补位字符串
+            # pkcs7 = PKCS7Encoder()
+            # plain_text = pkcs7.encode(plain_text)
+            # 去除16位随机字符串
+            content = plain_text[16:-pad]
+            xml_len = socket.ntohl(struct.unpack("I", content[: 4])[0])
+            xml_content = content[4: xml_len + 4]
+            from_receiveid = content[xml_len + 4:]
+        except Exception as e:
+            logger = logging.getLogger()
+            logger.error(e)
+            return ierror.WXBizMsgCrypt_IllegalBuffer, None
+
+        if from_receiveid.decode('utf8') != receiveid:
+            return ierror.WXBizMsgCrypt_ValidateCorpid_Error, None
+        return 0, xml_content
+
+    def get_random_str(self):
+        """ 随机生成16位字符串
+        @return: 16位字符串
+        """
+        return str(random.randint(1000000000000000, 9999999999999999)).encode()
+
+
+class WXBizMsgCrypt:
+    # 构造函数
+    def __init__(self, sToken, sEncodingAESKey, sReceiveId):
+        try:
+            self.key = base64.b64decode(sEncodingAESKey + "=")
+            assert len(self.key) == 32
+        except Exception:
+            throw_exception("[error]: EncodingAESKey unvalid !", FormatError)
+            # return ierror.WXBizMsgCrypt_IllegalAesKey,None
+        self.m_sToken = sToken
+        self.m_sReceiveId = sReceiveId
+
+        # 验证URL
+        # @param sMsgSignature: 签名串，对应URL参数的msg_signature
+        # @param sTimeStamp: 时间戳，对应URL参数的timestamp
+        # @param sNonce: 随机串，对应URL参数的nonce
+        # @param sEchoStr: 随机串，对应URL参数的echostr
+        # @param sReplyEchoStr: 解密之后的echostr，当return返回0时有效
+        # @return：成功0，失败返回对应的错误码
+
+    def VerifyURL(self, sMsgSignature, sTimeStamp, sNonce, sEchoStr):
+        sha1 = SHA1()
+        ret, signature = sha1.getSHA1(self.m_sToken, sTimeStamp, sNonce, sEchoStr)
+        if ret != 0:
+            return ret, None
+        if not signature == sMsgSignature:
+            return ierror.WXBizMsgCrypt_ValidateSignature_Error, None
+        pc = Prpcrypt(self.key)
+        ret, sReplyEchoStr = pc.decrypt(sEchoStr, self.m_sReceiveId)
+        return ret, sReplyEchoStr
+
+    def EncryptMsg(self, sReplyMsg, sNonce, timestamp=None):
+        # 将企业回复用户的消息加密打包
+        # @param sReplyMsg: 企业号待回复用户的消息，xml格式的字符串
+        # @param sTimeStamp: 时间戳，可以自己生成，也可以用URL参数的timestamp,如为None则自动用当前时间  # noqa: E501
+        # @param sNonce: 随机串，可以自己生成，也可以用URL参数的nonce  # noqa: E501
+        # sEncryptMsg: 加密后的可以直接回复用户的密文，包括msg_signature, timestamp, nonce, encrypt的xml格式的字符串,  # noqa: E501
+        # return：成功0，sEncryptMsg,失败返回对应的错误码None
+        pc = Prpcrypt(self.key)
+        ret, encrypt = pc.encrypt(sReplyMsg, self.m_sReceiveId)
+        encrypt = encrypt.decode('utf8')
+        if ret != 0:
+            return ret, None
+        if timestamp is None:
+            timestamp = str(int(time.time()))
+        # 生成安全签名
+        sha1 = SHA1()
+        ret, signature = sha1.getSHA1(self.m_sToken, timestamp, sNonce, encrypt)
+        if ret != 0:
+            return ret, None
+        xmlParse = XMLParse()
+        return ret, xmlParse.generate(encrypt, signature, timestamp, sNonce)
+
+    def DecryptMsg(self, sPostData, sMsgSignature, sTimeStamp, sNonce):
+        # 检验消息的真实性，并且获取解密后的明文
+        # @param sMsgSignature: 签名串，对应URL参数的msg_signature
+        # @param sTimeStamp: 时间戳，对应URL参数的timestamp
+        # @param sNonce: 随机串，对应URL参数的nonce
+        # @param sPostData: 密文，对应POST请求的数据
+        #  xml_content: 解密后的原文，当return返回0时有效
+        # @return: 成功0，失败返回对应的错误码
+        # 验证安全签名
+        xmlParse = XMLParse()
+        ret, encrypt = xmlParse.extract(sPostData)
+        if ret != 0:
+            return ret, None
+        sha1 = SHA1()
+        ret, signature = sha1.getSHA1(self.m_sToken, sTimeStamp, sNonce, encrypt)
+        if ret != 0:
+            return ret, None
+        if not signature == sMsgSignature:
+            return ierror.WXBizMsgCrypt_ValidateSignature_Error, None
+        pc = Prpcrypt(self.key)
+        ret, xml_content = pc.decrypt(encrypt, self.m_sReceiveId)
+        return ret, xml_content

app/wechat/handler.py

@@ -0,0 +1,57 @@
+import xml.etree.ElementTree as ET
+
+from app.config import settings
+from app.wechat.crypto import WXBizMsgCrypt
+
+
+class WeChatMessageHandler:
+    def __init__(self):
+        self.wxcpt = WXBizMsgCrypt(
+            sToken=settings.wechat_token,
+            sEncodingAESKey=settings.wechat_encoding_aes_key,
+            sReceiveId=settings.wechat_corp_id,
+        )
+
+    def verify_url(
+        self, msg_signature: str, timestamp: str, nonce: str, echostr: str
+    ) -> str | None:
+        ret, sEchoStr = self.wxcpt.VerifyURL(
+            msg_signature, timestamp, nonce, echostr
+        )
+        if ret == 0:
+            return (
+                sEchoStr.decode("utf-8")
+                if isinstance(sEchoStr, bytes)
+                else sEchoStr
+            )
+        return None
+
+    def decrypt_message(
+        self,
+        post_data: str,
+        msg_signature: str,
+        timestamp: str,
+        nonce: str,
+    ) -> ET.Element | None:
+        ret, xml_content = self.wxcpt.DecryptMsg(
+            post_data, msg_signature, timestamp, nonce
+        )
+        if ret != 0:
+            return None
+        return ET.fromstring(xml_content)
+
+    def encrypt_response(
+        self, response_xml: str, nonce: str, timestamp: str
+    ) -> str | None:
+        ret, encrypted = self.wxcpt.EncryptMsg(response_xml, nonce, timestamp)
+        if ret == 0:
+            return encrypted
+        return None
+
+    def handle_event(
+        self, event: str, event_key: str | None, from_user: str
+    ) -> str | None:
+        return None
+
+    def handle_text(self, content: str, from_user: str) -> str | None:
+        return None

app/wechat/ierror.py

@@ -0,0 +1,19 @@
+#!/usr/bin/env python
+#########################################################################
+# Author: jonyqin
+# Created Time: Thu 11 Sep 2014 01:53:58 PM CST
+# File Name: ierror.py
+# Description:定义错误码含义
+#########################################################################
+WXBizMsgCrypt_OK = 0
+WXBizMsgCrypt_ValidateSignature_Error = -40001
+WXBizMsgCrypt_ParseXml_Error = -40002
+WXBizMsgCrypt_ComputeSignature_Error = -40003
+WXBizMsgCrypt_IllegalAesKey = -40004
+WXBizMsgCrypt_ValidateCorpid_Error = -40005
+WXBizMsgCrypt_EncryptAES_Error = -40006
+WXBizMsgCrypt_DecryptAES_Error = -40007
+WXBizMsgCrypt_IllegalBuffer = -40008
+WXBizMsgCrypt_EncodeBase64_Error = -40009
+WXBizMsgCrypt_DecodeBase64_Error = -40010
+WXBizMsgCrypt_GenReturnXml_Error = -40011

docker/Dockerfile

@@ -0,0 +1,16 @@
+FROM python:3.12-slim
+
+WORKDIR /app
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    libpq-dev && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY pyproject.toml .
+RUN pip install --no-cache-dir -e ".[dev]"
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

docker/docker-compose.yml

@@ -0,0 +1,12 @@
+services:
+  app:
+    build:
+      context: ..
+      dockerfile: docker/Dockerfile
+    ports:
+      - "8000:8000"
+    env_file:
+      - ../.env
+    volumes:
+      - ../logs:/app/logs
+    restart: unless-stopped

docs/superpowers/specs/2026-05-09-fastapi-docker-migration-design.md

@@ -0,0 +1,516 @@
+# FastAPI + Docker 迁移设计文档
+
+**日期**: 2026-05-09
+**版本**: 1.0
+**状态**: 设计阶段
+
+---
+
+## 1. 背景与目标
+
+将现有的广西政府采购网公告监控系统从 Flask CLI 架构迁移到 FastAPI + Docker 部署方案，同时提升代码质量、安全性和可维护性。
+
+### 核心目标
+
+- FastAPI 替代 Flask 回调服务器 + argparse CLI，统一为一个 Web 应用
+- Docker 单容器部署，连接现有 PostgreSQL
+- SQLAlchemy ORM 替代原始 psycopg2 操作
+- APScheduler 内置定时任务
+- 环境变量管理配置，敏感信息不提交 git
+- 异步改造（httpx + asyncpg）
+
+---
+
+## 2. 新项目结构
+
+```
+gx-gp-notify/
+├── app/
+│   ├── __init__.py
+│   ├── main.py                  # FastAPI 应用入口 + lifespan
+│   ├── config.py                # Pydantic Settings (环境变量驱动)
+│   ├── api/
+│   │   ├── __init__.py
+│   │   ├── router.py            # 统一路由注册
+│   │   ├── deps.py              # 依赖注入 (get_db, get_scheduler)
+│   │   ├── announcements.py     # 公告 CRUD 端点
+│   │   ├── crawl.py             # 爬取触发端点
+│   │   └── wechat.py            # 企业微信回调端点
+│   ├── models/
+│   │   ├── __init__.py
+│   │   ├── announcement.py      # SQLAlchemy 模型
+│   │   └── schemas.py           # Pydantic 请求/响应模型
+│   ├── crawler/
+│   │   ├── __init__.py
+│   │   ├── base.py              # Spider 抽象基类 + Pipeline 配置
+│   │   ├── gxgp_spider.py       # 广西政府采购网爬虫 (API 模式)
+│   │   ├── dahuagov_spider.py   # 大化县政府网爬虫 (HTML 模式)
+│   │   └── parsers.py           # 数据解析器
+│   ├── services/
+│   │   ├── __init__.py
+│   │   ├── crawl_service.py     # 爬取编排器 (注册/调用所有 Spider)
+│   │   ├── pipeline.py          # 统一后处理管道 (存储→筛选→推送)
+│   │   ├── filter_service.py    # 筛选逻辑
+│   │   └── notification_service.py  # 通知服务
+│   ├── wechat/
+│   │   ├── __init__.py
+│   │   ├── handler.py           # 消息处理器
+│   │   ├── menu.py              # 菜单管理
+│   │   ├── crypto.py            # WXBizMsgCrypt 加解密
+│   │   └── client.py            # 企业微信 API 客户端
+│   └── scheduler/
+│       ├── __init__.py
+│       └── jobs.py              # APScheduler 定时任务
+├── tests/
+│   ├── __init__.py
+│   ├── conftest.py              # pytest fixtures
+│   ├── test_crawler/            # 爬虫解析器测试
+│   ├── test_api/                # API 端点测试
+│   └── test_services/           # 业务逻辑测试
+├── alembic/                     # 数据库迁移
+│   └── versions/
+├── docker/
+│   ├── Dockerfile
+│   └── docker-compose.yml
+├── pyproject.toml               # 项目元数据 + 依赖 + 工具配置
+├── .env.example                 # 环境变量模板
+├── .gitignore
+└── logs/                        # 日志目录 (gitignore)
+```
+
+---
+
+## 3. 爬虫模块化设计
+
+### 3.1 设计动机
+
+系统爬取两个不同来源的公告：广西政府采购网（API 模式，13 种公告类型）和大化县政府网（HTML 解析，单一来源）。两个爬虫的后处理流程不同：
+
+| 对比 | 广西政府采购网 | 大化县政府网 |
+|------|---------------|-------------|
+| 爬取方式 | POST JSON API | GET HTML + BeautifulSoup |
+| 反爬机制 | 敏感词检查 | 无 |
+| 分页 | 多页轮询 | 单页 |
+| 筛选策略 | 关键词 + 日期 + 去重 | 不过滤 |
+| 推送策略 | 只推送关键词匹配的 | 全部推送 |
+| 已发送标记 | is_new 标记 | is_new → mark_sent |
+
+为避免两个爬虫各自维护一套存储/筛选/推送逻辑，采用 **Spider 接口 + Pipeline 策略模式** 分离关注点。
+
+### 3.2 架构
+
+```
+┌─────────────────────────────────────────────────┐
+│              CrawlOrchestrator                   │
+│    (注册所有 Spider，统一调度爬取)                 │
+└─────────────────────┬───────────────────────────┘
+                      │
+        ┌─────────────┼─────────────┐
+        │             │             │
+┌───────▼──────┐ ┌────▼──────┐ ┌────▼──────────┐
+│ GXGPSpider   │ │ Dahuagov  │ │ (FutureSpider) │
+│ (API 模式)    │ │ Spider    │ │                │
+│ 13 sources   │ │ (HTML模式) │ │                │
+└───────┬──────┘ └────┬──────┘ └────┬───────────┘
+        │             │             │
+        └─────────────┼─────────────┘
+                      │  List[Announcement]
+                      │
+┌─────────────────────▼───────────────────────────┐
+│              PostCrawlPipeline                   │
+│                                                  │
+│  每个 Spider 声明 PipelineConfig:                 │
+│   - filter_enabled: 是否启用关键词筛选            │
+│   - keywords: 筛选关键词列表                      │
+│   - dedup_enabled: 是否去重                      │
+│   - notify_mode: "filtered" | "all"             │
+│   - mark_sent: 推送后是否标记已发送               │
+│                                                  │
+│  统一处理流程:                                    │
+│  存储 → 去重 → 筛选(可选) → 推送(可选) → 标记(可选) │
+└──────────────────────────────────────────────────┘
+```
+
+### 3.3 Spider 基类
+
+```python
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from typing import List
+
+@dataclass
+class PipelineConfig:
+    """Spider 后处理策略配置"""
+    filter_enabled: bool = True
+    keywords: List[str] = None
+    dedup_enabled: bool = True
+    notify_mode: str = "filtered"  # "filtered" | "all"
+    mark_sent: bool = False
+
+
+class BaseSpider(ABC):
+    """爬虫基类 — 只负责爬取+解析，不管后续如何处理"""
+
+    name: str                            # spider 名称
+    source_code: str                     # 来源代码
+    source_name: str                     # 来源名称
+
+    @abstractmethod
+    async def crawl(self) -> CrawlResult:
+        """执行爬取，返回包含 Announcement 列表的 CrawlResult"""
+        ...
+
+    def get_pipeline_config(self) -> PipelineConfig:
+        """返回后处理策略（子类可覆盖）"""
+        return PipelineConfig()
+```
+
+### 3.4 两个 Spider 的 PipelineConfig
+
+```python
+# GXGPSpider — 关键词筛选模式
+PipelineConfig(
+    filter_enabled=True,
+    keywords=["大化"],          # 从配置读取
+    dedup_enabled=True,
+    notify_mode="filtered",     # 只推送匹配关键词的
+    mark_sent=False,            # 用 is_new 标记，不单独 mark_sent
+)
+
+# DahuagovSpider — 全量推送模式
+PipelineConfig(
+    filter_enabled=False,
+    keywords=[],
+    dedup_enabled=True,
+    notify_mode="all",          # 全部推送
+    mark_sent=True,             # 推送后标记已发送
+)
+```
+
+### 3.5 统一后处理管道
+
+```python
+class PostCrawlPipeline:
+    """统一后处理管道 — 所有 Spider 共用"""
+
+    async def process(self, announcements: List[Announcement],
+                     config: PipelineConfig) -> PipelineResult:
+        # 1. 统一存入 announcements 表 (按 source_code 区分)
+        # 2. 去重 (基于 content_hash)
+        # 3. 根据 config.filter_enabled 决定是否筛选
+        # 4. 根据 config.notify_mode 决定推送策略
+        #    - "all": 推送全部新公告
+        #    - "filtered": 只推送匹配关键词的
+        # 5. 根据 config.mark_sent 标记已发送
+        # 6. 生成 Markdown (可选)
+        ...
+```
+
+### 3.6 优势
+
+- **新增爬虫源**只需实现 `BaseSpider.crawl()` + 声明 `PipelineConfig`，推送/存储逻辑零改动
+- **推送逻辑单一入口**，修改一处对所有源生效
+- 每个 Spider 文件只关注"怎么爬"和"怎么解析"，不再包含存储/筛选/推送代码
+- `dahuagov_announcements` 独立表可合并到统一的 `announcements` 表，用 `source_code='dahuagov'` 区分
+
+---
+
+## 4. API 端点设计
+
+### 3.1 公告查询
+
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| `GET` | `/api/v1/announcements` | 查询公告列表（分页、来源筛选、日期筛选、关键词搜索） |
+| `GET` | `/api/v1/announcements/{id}` | 获取单条公告详情 |
+| `GET` | `/api/v1/announcements/today` | 获取今日公告 |
+| `GET` | `/api/v1/announcements/stats` | 获取公告统计信息 |
+
+### 3.2 爬取控制
+
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| `POST` | `/api/v1/crawl/trigger` | 手动触发一次爬取（支持关键词/来源参数） |
+| `GET` | `/api/v1/crawl/status` | 查看最近爬取状态 |
+| `GET` | `/api/v1/crawl/sources` | 获取已配置的公告来源列表 |
+
+### 3.3 定时任务
+
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| `GET` | `/api/v1/scheduler/jobs` | 查看活跃的定时任务 |
+| `POST` | `/api/v1/scheduler/pause/{job_id}` | 暂停某个定时任务 |
+| `POST` | `/api/v1/scheduler/resume/{job_id}` | 恢复某个定时任务 |
+
+### 3.4 企业微信
+
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| `GET` `POST` | `/api/v1/wechat/callback` | 企业微信回调入口（URL验证 + 消息接收） |
+
+### 3.5 系统
+
+| 方法 | 路径 | 说明 |
+|------|------|------|
+| `GET` | `/health` | 健康检查（包含数据库连通性） |
+
+### 3.6 通用特性
+
+- FastAPI 自动生成 Swagger UI (`/docs`) 和 ReDoc (`/redoc`)
+- 统一分页格式：`{ total, page, page_size, items }`
+- 统一错误响应：`{ detail: "error message" }`
+- 依赖注入：数据库 session、配置、调度器均通过 FastAPI `Depends()` 注入
+- CORS 默认关闭，通过 `CORS_ORIGINS` 环境变量可选开启
+
+---
+
+## 5. 数据模型
+
+### 5.1 公告表 (announcements)
+
+合并现有的 `announcements`、`auto_announcements`、`manual_announcements`、`dahuagov_announcements` 四张表为一张，通过 `source_code` 字段区分来源，通过 `PipelineConfig` 控制每个来源的推送策略。
+
+| 字段 | 类型 | 说明 |
+|------|------|------|
+| id | Integer | 主键 |
+| title | String(500) | 公告标题 |
+| publish_date | DateTime | 发布时间 |
+| purchase_name | String(200) | 发布单位 |
+| content_url | Text | 内容链接 |
+| source_code | String(50) | 来源代码（ZcyAnnouncement1 / dahuagov 等） |
+| source_name | String(100) | 来源名称 |
+| announcement_type | String(50) | 公告类型枚举值 |
+| content_hash | String(64) | SHA256 内容哈希，UNIQUE INDEX |
+| crawl_mode | String(20) | "auto" / "manual" |
+| is_new | Boolean | 是否新公告 |
+| is_sent | Boolean | 是否已推送 |
+| keyword_matched | Boolean | 是否匹配关键词 |
+| created_at | DateTime | 创建时间 |
+| updated_at | DateTime | 更新时间 |
+
+### 5.2 设计决策
+
+- **四表合一**：不再为不同来源或抓取模式创建独立表。`source_code` 区分来源（`ZcyAnnouncement1` ~ `dahuagov`），`crawl_mode` 区分自动/手动
+- **is_sent 字段**：替代原来大化县的 `is_new → mark_sent` 模式，同时为广西采购网的公告提供统一的已推送标记
+- **keyword_matched 字段**：在筛选阶段标记，持久化到数据库方便后续查询
+
+### 5.3 变更说明
+
+- `content_hash` 从 MD5 (32位) 改为 SHA256 (64位)
+- 去掉 `announcement_sources` 表，来源信息从环境变量配置动态读取
+- 去掉 `crawl_results` 表，爬取结果通过日志记录
+- 使用 Alembic 管理数据库迁移
+- 旧数据迁移：通过 Alembic migration 脚本将现有四张表的数据合并到新表
+
+---
+
+## 5. 配置管理
+
+### 5.1 pydantic-settings
+
+所有配置通过 `pydantic-settings` 的 `BaseSettings` 加载，来源优先级：环境变量 > `.env` 文件 > 默认值。
+
+### 5.2 环境变量
+
+```bash
+# 应用
+DEBUG=false
+LOG_LEVEL=INFO
+
+# 数据库（连接现有 PostgreSQL）
+DATABASE_URL=postgresql+asyncpg://gx-gp-notify:password@10.10.10.14:5432/gx-gp-notify
+
+# 爬虫
+CRAWLER_BASE_URL=https://zfcg.gxzf.gov.cn
+CRAWLER_KEYWORDS=["大化"]
+CRAWLER_MAX_PAGES=10
+CRAWLER_TIMEOUT=30
+
+# 企业微信
+WECHAT_ENABLED=true
+WECHAT_CORP_ID=ww69e8e44636f47780
+WECHAT_AGENT_ID=1000007
+WECHAT_SECRET=<secret>
+WECHAT_TOKEN=<token>
+WECHAT_ENCODING_AES_KEY=<aes_key>
+
+# 定时任务
+SCHEDULER_ENABLED=true
+SCHEDULER_CRON=0 8,14,18 * * *
+
+# Markdown 输出
+MARKDOWN_OUTPUT_FILE=onu.md
+```
+
+### 5.3 安全措施
+
+- `.env` 文件加入 `.gitignore`
+- `config.yaml` 中的敏感信息不再提交到仓库
+- 使用 SHA256 替代 MD5 做内容哈希
+- 建议清理 git 历史中的敏感信息
+
+---
+
+## 6. Docker 部署
+
+### 6.1 架构
+
+```
+docker-compose.yml
+┌─────────────────────────────┐
+│  app (FastAPI)              │
+│  - uvicorn 服务器           │
+│  - APScheduler (内置)       │
+│  - 端口 8000                │
+│  - 挂载: ./logs             │
+└──────────┬──────────────────┘
+           │ TCP 连接
+┌──────────▼──────────────────┐
+│  外部 PostgreSQL (现有)      │
+│  10.10.10.14:5432           │
+└─────────────────────────────┘
+```
+
+### 6.2 Dockerfile
+
+```dockerfile
+FROM python:3.12-slim
+WORKDIR /app
+COPY pyproject.toml .
+RUN pip install --no-cache-dir .
+COPY . .
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
+```
+
+### 6.3 docker-compose.yml
+
+```yaml
+services:
+  app:
+    build: .
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env
+    volumes:
+      - ./logs:/app/logs
+    restart: unless-stopped
+```
+
+### 6.4 启动步骤
+
+```bash
+cp .env.example .env        # 编辑 .env 填入真实配置
+docker compose up -d        # 启动服务
+docker compose logs -f app  # 查看日志
+```
+
+---
+
+## 7. 技术栈
+
+| 组件 | 当前 | 迁移后 |
+|------|------|--------|
+| Web 框架 | Flask (仅回调用) | FastAPI |
+| CLI | argparse | 不再需要，API 替代 |
+| 数据库驱动 | psycopg2 (同步) | asyncpg (异步) + SQLAlchemy 2.0 |
+| HTTP 客户端 | requests (同步) | httpx (异步) |
+| 定时任务 | schedule 库 | APScheduler |
+| 配置 | PyYAML + config.yaml | pydantic-settings + .env |
+| 加密 | pycryptodome + cryptography | 保留 |
+| 部署 | 裸机 + uWSGI | Docker + uvicorn |
+| 代码检查 | 无 | ruff |
+| 测试 | 无 | pytest + httpx |
+| 迁移 | 手动 CREATE TABLE | Alembic |
+
+---
+
+## 8. 额外改进
+
+### 8.1 异步改造
+
+- 爬虫网络请求：`httpx.AsyncClient` 替代 `requests`
+- 数据库：`asyncpg` + SQLAlchemy async engine
+- 通知发送：`httpx.AsyncClient`
+- API 端点使用 `async def`
+
+### 8.2 自动化测试
+
+- 爬虫解析器单元测试（Mock 网页响应，验证解析逻辑）
+- 筛选逻辑单元测试
+- API 端点集成测试（用 `httpx.AsyncClient` + 测试数据库）
+- pytest + pytest-asyncio + pytest-cov
+
+### 8.3 日志改进
+
+- 结构化日志（JSON 格式）
+- Docker 环境下输出到 stdout
+- 保留文件日志供宿主机查看（挂载 `./logs` 目录）
+
+### 8.4 错误处理
+
+- 统一异常处理中间件
+- 健康检查 `/health` 含数据库连通性验证
+- 关键操作结构化日志记录
+
+### 8.5 代码质量
+
+- `ruff` 替代 flake8 + black
+- `pyproject.toml` 统一管理依赖和工具配置
+- 全面 Type Hints
+
+### 8.6 .gitignore
+
+```gitignore
+.env
+logs/
+*.log
+__pycache__/
+*.pyc
+.venv/
+.ruff_cache/
+.pytest_cache/
+*.egg-info/
+```
+
+---
+
+## 9. 迁移策略
+
+### 分步执行
+
+1. 创建新项目结构骨架（FastAPI app + config）
+2. 数据库模型 + Alembic 迁移
+3. 迁移爬虫模块（异步改造）
+4. 迁移服务层（筛选、通知、Markdown）
+5. 迁移 WeChat 回调（Flask → FastAPI route）
+6. 添加 APScheduler 定时任务
+7. 编写测试
+8. Docker 化
+9. 清理旧文件
+
+### 向后兼容
+
+- 保留 `dahuagov_announcements` 表结构不变
+- 企业微信回调 URL 路径保持不变 (`/api/v1/wechat/callback`)
+- 数据库迁移使用 Alembic，不丢失现有数据
+
+---
+
+## 10. 未包含的内容
+
+- 不做多用户认证/授权（个人使用）
+- 不做 Celery 分布式任务（个人使用，APScheduler 足够）
+- 不做 Redis 缓存
+- 不做前端 UI
+
+---
+
+## 11. 风险与缓解
+
+| 风险 | 缓解 |
+|------|------|
+| 数据库迁移丢失数据 | Alembic 自动生成迁移脚本，先在测试环境验证 |
+| 异步爬虫被目标站限流 | 保留现有延迟/重试机制，httpx 支持同样的超时配置 |
+| 企业微信回调兼容性 | 回调路径不变，加解密逻辑完全复用现有代码 |
+| Docker 网络访问 10.10.10.14 | 确认 Docker 宿主机可访问该 IP，必要时用 `host.docker.internal` |

gx_gp_monitor/config/config.yaml

@@ -1,135 +0,0 @@
-# 广西政府采购网公告监控系统配置文件
-# 复制此文件为 config.yaml 并修改相应配置
-
-# 调试模式
-debug: false
-
-# 日志配置
-log_level: INFO
-log_file: logs/gx_gp_monitor.log
-log_max_size: 10485760  # 10MB
-log_backup_count: 5
-
-# 爬虫配置
-crawler:
-  base_url: "https://zfcg.gxzf.gov.cn"
-  timeout: 30                     # 请求超时时间（秒）
-  max_retries: 3                  # 最大重试次数
-  retry_delay: 1.0               # 重试初始延迟
-  max_retry_delay: 60.0          # 重试最大延迟
-  backoff_factor: 2.0            # 退避因子
-  user_agents:                    # User-Agent列表
-    - "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
-    - "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/17.0 Safari/605.1.15"
-    - "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
-  proxies: []                     # 代理列表
-  request_delay: 1.0             # 请求间延迟
-  request_delay_max: 3.0         # 请求间最大延迟
-  keyword: ["大化"]    # 关键词筛选（支持多个关键词）
-  start_date: ""                 # 开始日期 (YYYY-MM-DD)
-  end_date: ""                   # 结束日期 (YYYY-MM-DD)
-  max_pages: 10                  # 最大页数
-  page_size: 100                 # 每页大小
-
-# 数据库配置
-database:
-  enabled: true                   # 是否启用数据库存储
-  type: postgresql               # 数据库类型
-  host: "10.10.10.14"           # 数据库主机
-  port: 5432                     # 数据库端口
-  name: "gx-gp-notify"          # 数据库名称
-  user: "gx-gp-notify"          # 数据库用户名
-  password: "MA6RBX4F6Bd5DGmw"   # 数据库密码
-  pool_size: 5                   # 连接池大小
-  max_overflow: 10               # 最大连接数
-  pool_timeout: 30               # 连接超时时间
-  pool_recycle: 3600            # 连接回收时间（秒）
-  data_retention_days: 90        # 数据保留天数
-  auto_cleanup: true             # 是否自动清理过期数据
-
-# 企业微信通知配置
-wechat_app:
-  enabled: true                    # 是否启用企业微信通知
-  corp_id: "ww69e8e44636f47780"                      # 企业ID
-  agent_id: "1000007"                     # 应用ID
-  secret: "SmelCwKFoL0E9ATWFzr-w7gsfXBTN72lT1UqnNd0HpI"                       # 应用Secret
-  token: "DmvL98cAF6x9CFtQZwqD2emGL8S7HxA"                        # Token
-  encoding_aes_key: "yAc4OoSCP92YTefHXYfw27WeG9oF11W9d6nw6QYlU3D"             # 消息加密Key
-  port: 18001                      # 服务端口
-  host: "0.0.0.0"                 # 服务主机
-  debug: false                     # 调试模式
-  use_proxy: false                 # 是否使用代理API
-  proxy_api_url: "https://api.v6ole.top"  # 代理API地址
-
-# Markdown输出配置
-markdown:
-  enabled: true                    # 是否启用Markdown输出
-  output_file: "onu.md"           # 输出文件路径
-  max_entries: 1000               # 最大条目数
-  include_today_highlight: true   # 是否突出显示今日公告
-  template_file: "templates/announcement.md"  # 模板文件
-
-# 公告来源配置
-sources:
-  ZcyAnnouncement1:
-    category_id: 66485
-    name: "采购公告"
-    type: "purchase"
-  ZcyAnnouncement2:
-    category_id: 66485
-    name: "结果公告"
-    type: "result"
-  ZcyAnnouncement3:
-    category_id: 66485
-    name: "合同公告"
-    type: "contract"
-  ZcyAnnouncement4:
-    category_id: 66485
-    name: "更正公告"
-    type: "correction"
-  ZcyAnnouncement5:
-    category_id: 66485
-    name: "招标文件预公示"
-    type: "pre_announcement"
-  ZcyAnnouncement6:
-    category_id: 66485
-    name: "单一来源公示"
-    type: "single_source"
-  ZcyAnnouncement7:
-    category_id: 66485
-    name: "电子卖场公示"
-    type: "electronic_market"
-  ZcyAnnouncement10:
-    category_id: 66485
-    name: "履约验收公示"
-    type: "acceptance"
-  ZcyAnnouncement11:
-    category_id: 66485
-    name: "工程类公告"
-    type: "engineering"
-  ZcyAnnouncement20:
-    category_id: 66485
-    name: "框架协议征集公告"
-    type: "framework_agreement"
-  ZcyAnnouncement21:
-    category_id: 66485
-    name: "框架协议入围结果公告"
-    type: "framework_result"
-  ZcyAnnouncement23:
-    category_id: 66485
-    name: "框架协议成交结果汇总公告"
-    type: "framework_summary"
-  "61-266648":
-    category_id: 66485
-    name: "采购意向公开"
-    type: "intention"
-
-# 调度配置已移除 - 如需定时任务功能，请重新添加
-
-# 监控配置
-monitoring:
-  enabled: true                   # 是否启用监控
-  health_check_interval: 300      # 健康检查间隔（秒）
-  alert_on_failure: true          # 失败时是否告警
-  max_consecutive_failures: 3     # 最大连续失败次数
-  metrics_enabled: true           # 是否启用指标收集

logs/gx_gp_monitor.log.1

@@ -1,493 +0,0 @@
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 512
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: GwLOHlMWE3qBsHJ3DegXZk5RGOb0hEg2g9SbYIvxkhynxr/43t...
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: vlN4cpR79+nVcy2Cvf22D4nsbOxqtyYFlVO3nvPdIz2NLVZTCr...
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 052516f0e87dd3793a1035dccb0f3b3d9fd806de
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 060aff2e6666d1df9c957ebb61d214664c64e72f
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 052516f0e87dd3793a1035dccb0f3b3d9fd806de
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 060aff2e6666d1df9c957ebb61d214664c64e72f
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=text
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - INFO - 处理文本消息: content=河池分行大化瑶族自治县中医医院结算系
-统项目..., user=NongGuangGuo
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.message_handler - INFO - 处理文本消息: 河池分行大化瑶族自治县中医医院结算系
-统项目, user: NongGuangGuo
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 关键词搜索: ['河池分行大化瑶族自治县中医医院结算系', '统项目']
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=crawl_now, user=NongGuangGuo
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: crawl_now, user: NongGuangGuo
-2026-05-06 15:08:19 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 触发立即搜索
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - === 广西政府采购网公告监控系统启动 ===
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 版本: 1.0.0
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 配置文件: 默认配置
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - === 广西政府采购网公告监控系统启动 ===
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 版本: 1.0.0
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 配置文件: 默认配置
-2026-05-06 15:08:19 - gx_gp_monitor.core.database - INFO - 数据库连接池初始化成功
-2026-05-06 15:08:19 - gx_gp_monitor.core.database - INFO - 开始初始化数据库表结构
-2026-05-06 15:08:19 - gx_gp_monitor.core.database - INFO - 数据库表结构初始化完成
-2026-05-06 15:08:19 - gx_gp_monitor.storage.postgresql - INFO - 存储初始化完成
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 应用初始化完成
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: False)
-2026-05-06 15:08:19 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:08:19 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:08:19 - gx_gp_monitor.core.reliability - INFO - 健康检查通过
-2026-05-06 15:08:19 - gx_gp_monitor.core.database - INFO - 开始初始化数据库表结构
-2026-05-06 15:08:19 - gx_gp_monitor.core.database - INFO - 数据库表结构初始化完成
-2026-05-06 15:08:19 - gx_gp_monitor.storage.postgresql - INFO - 存储初始化完成
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 应用初始化完成
-2026-05-06 15:08:19 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: True)
-2026-05-06 15:08:20 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:08:20 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 采购公告 爬取完成，共获取 100 条公告，耗时 0.44秒
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 开始爬取 结果公告
-2026-05-06 15:08:20 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 结果公告 爬取完成，共获取 100 条公告，耗时 0.40秒
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 开始爬取 合同公告
-2026-05-06 15:08:21 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 合同公告 爬取完成，共获取 100 条公告，耗时 0.46秒
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 开始爬取 更正公告
-2026-05-06 15:08:21 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 更正公告 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 开始爬取 招标文件预公示
-2026-05-06 15:08:21 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 招标文件预公示 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 开始爬取 单一来源公示
-2026-05-06 15:08:22 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:22 - gx_gp_monitor - INFO - 单一来源公示 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:22 - gx_gp_monitor - INFO - 开始爬取 电子卖场公示
-2026-05-06 15:08:22 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:22 - gx_gp_monitor - INFO - 电子卖场公示 爬取完成，共获取 100 条公告，耗时 0.50秒
-2026-05-06 15:08:22 - gx_gp_monitor - INFO - 开始爬取 履约验收公示
-2026-05-06 15:08:22 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:22 - gx_gp_monitor - INFO - 履约验收公示 爬取完成，共获取 100 条公告，耗时 0.27秒
-2026-05-06 15:08:22 - gx_gp_monitor - INFO - 开始爬取 工程类公告
-2026-05-06 15:08:23 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:23 - gx_gp_monitor - INFO - 工程类公告 爬取完成，共获取 100 条公告，耗时 0.30秒
-2026-05-06 15:08:23 - gx_gp_monitor - INFO - 开始爬取 框架协议征集公告
-2026-05-06 15:08:23 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:23 - gx_gp_monitor - INFO - 框架协议征集公告 爬取完成，共获取 100 条公告，耗时 0.27秒
-2026-05-06 15:08:23 - gx_gp_monitor - INFO - 开始爬取 框架协议入围结果公告
-2026-05-06 15:08:23 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:23 - gx_gp_monitor - INFO - 框架协议入围结果公告 爬取完成，共获取 100 条公告，耗时 0.26秒
-2026-05-06 15:08:23 - gx_gp_monitor - INFO - 开始爬取 框架协议成交结果汇总公告
-2026-05-06 15:08:24 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:24 - gx_gp_monitor - INFO - 框架协议成交结果汇总公告 爬取完成，共获取 100 条公告，耗时 0.27秒
-2026-05-06 15:08:24 - gx_gp_monitor - INFO - 开始爬取 采购意向公开
-2026-05-06 15:08:24 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:24 - gx_gp_monitor - INFO - 采购意向公开 爬取完成，共获取 100 条公告，耗时 0.29秒
-2026-05-06 15:08:24 - gx_gp_monitor.crawler.spider - INFO - 爬取完成: 共处理 13 个来源，成功 13 个，失败 0 个，获取 1300 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.main - INFO - 搜索到 1300 条原始公告
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 开始按来源保存 1300 条公告，每个来源最多保留 100 条
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement1 保存了 1 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement2 保存了 1 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement3 保存了 1 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement4 保存了 1 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement5 保存了 1 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement6 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement7 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement10 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement11 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement20 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement21 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement23 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 来源 61-266648 保存了 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.storage.postgresql - INFO - 按来源保存完成，总计保存 5 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.main - INFO - 保存自动爬取公告完成：共保存 5 条，按来源统计: {'ZcyAnnouncement1': 1, 'ZcyAnnouncement2': 1, 'ZcyAnnouncement3': 1, 'ZcyAnnouncement4': 1, 'ZcyAnnouncement5': 1, 'ZcyAnnouncement6': 0, 'ZcyAnnouncement7': 0, 'ZcyAnnouncement10': 0, 'ZcyAnnouncement11': 0, 'ZcyAnnouncement20': 0, 'ZcyAnnouncement21': 0, 'ZcyAnnouncement23': 0, '61-266648': 0}
-2026-05-06 15:08:24 - gx_gp_monitor.main - INFO - 筛选出 1300 条新公告
-2026-05-06 15:08:24 - gx_gp_monitor.filters.filters - INFO - 来源筛选: 1300 -> 1300 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.filters.filters - INFO - 去重筛选: 移除了 1300 条重复公告
-2026-05-06 15:08:24 - gx_gp_monitor.filters.filters - INFO - 关键词筛选: 0 -> 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.filters.filters - INFO - 筛选完成: 总数 1300 -> 筛选后 0 (关键词: 0, 日期: 0, 去重: 1300, 来源: 0)
-2026-05-06 15:08:24 - gx_gp_monitor.main - INFO - 筛选后剩余 0 条公告
-2026-05-06 15:08:24 - gx_gp_monitor.storage.md_generator - INFO - Markdown文件已保存到: onu.md (共 0 条公告)
-2026-05-06 15:08:24 - gx_gp_monitor.main - INFO - 爬取任务完成: {'success': True, 'total_crawled': 1300, 'filtered': 0, 'saved': 0, 'markdown_generated': True, 'notification_sent': False, 'filter_stats': {'keyword_filtered': 1300, 'date_filtered': 0, 'duplicate_filtered': 1300, 'source_filtered': 0}}
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: /GWEdhQRyz77Ot0gML2ySdkbya+0yS/l2Zun0R3RRbsUsiZ/5/...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: a3f07c703a094e51e6f65f10e1207347ba52e516
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: a3f07c703a094e51e6f65f10e1207347ba52e516
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_search, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_search, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 触发关键词搜索菜单
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Zh2CaGZnzxNyfY2UAmovYgB312yS33AE9njwfsmdnR4Zdz6dpM...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 2b12a7b22e5b1ce6051b25e1239eb3f89e168f89
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 2b12a7b22e5b1ce6051b25e1239eb3f89e168f89
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: /GWEdhQRyz77Ot0gML2ySdkbya+0yS/l2Zun0R3RRbsUsiZ/5/...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: a3f07c703a094e51e6f65f10e1207347ba52e516
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: a3f07c703a094e51e6f65f10e1207347ba52e516
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_search, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_search, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 触发关键词搜索菜单
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: BShc5Ko31VKzOh2A5AV7Id4WWX6+b+i013Kb+j4gOeFD4QpMz/...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: bcacf78d1048a9a06df24a596f173cd483feff96
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: bcacf78d1048a9a06df24a596f173cd483feff96
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Zh2CaGZnzxNyfY2UAmovYgB312yS33AE9njwfsmdnR4Zdz6dpM...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 2b12a7b22e5b1ce6051b25e1239eb3f89e168f89
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 2b12a7b22e5b1ce6051b25e1239eb3f89e168f89
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Hj5eJcf9InnhKnkJxjUdwjrfJLtEGw9pSsTXEZUemhGwdaseGY...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: efc35b9b2fb9c388203fd0d92725e4c52e7971bd
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: efc35b9b2fb9c388203fd0d92725e4c52e7971bd
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: /GWEdhQRyz77Ot0gML2ySdkbya+0yS/l2Zun0R3RRbsUsiZ/5/...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: a3f07c703a094e51e6f65f10e1207347ba52e516
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: a3f07c703a094e51e6f65f10e1207347ba52e516
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_search, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_search, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 触发关键词搜索菜单
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: BShc5Ko31VKzOh2A5AV7Id4WWX6+b+i013Kb+j4gOeFD4QpMz/...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: bcacf78d1048a9a06df24a596f173cd483feff96
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: bcacf78d1048a9a06df24a596f173cd483feff96
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Zh2CaGZnzxNyfY2UAmovYgB312yS33AE9njwfsmdnR4Zdz6dpM...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 2b12a7b22e5b1ce6051b25e1239eb3f89e168f89
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 2b12a7b22e5b1ce6051b25e1239eb3f89e168f89
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Hj5eJcf9InnhKnkJxjUdwjrfJLtEGw9pSsTXEZUemhGwdaseGY...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: efc35b9b2fb9c388203fd0d92725e4c52e7971bd
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: efc35b9b2fb9c388203fd0d92725e4c52e7971bd
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: s2AORSQopkHXxA09QhYM2xaxUQiwXq6SbJmEVtAdVgBsKdaTyk...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 09b95c92d81b3fdf2e2ce2d39f26f3fabb702ca2
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 09b95c92d81b3fdf2e2ce2d39f26f3fabb702ca2
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=help_guide, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: help_guide, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 请求使用说明
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: BShc5Ko31VKzOh2A5AV7Id4WWX6+b+i013Kb+j4gOeFD4QpMz/...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: bcacf78d1048a9a06df24a596f173cd483feff96
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: bcacf78d1048a9a06df24a596f173cd483feff96
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: koSh3mf1jROPiRIjbk0r2Wxz6G45YqfC7e6FEMFpko9WHl2TaA...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: b1009660d3a9d1248e4f4ae0380f311e15a31b35
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: b1009660d3a9d1248e4f4ae0380f311e15a31b35
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Hj5eJcf9InnhKnkJxjUdwjrfJLtEGw9pSsTXEZUemhGwdaseGY...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: efc35b9b2fb9c388203fd0d92725e4c52e7971bd
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: efc35b9b2fb9c388203fd0d92725e4c52e7971bd
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: s2AORSQopkHXxA09QhYM2xaxUQiwXq6SbJmEVtAdVgBsKdaTyk...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 09b95c92d81b3fdf2e2ce2d39f26f3fabb702ca2
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 09b95c92d81b3fdf2e2ce2d39f26f3fabb702ca2
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=help_guide, user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: help_guide, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 请求使用说明
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Wf8nBEZm2h74BAUuJO4v23ZodRVoaehzIkrZmu5znNTFx6ZviG...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 1374c68c6060fedb594170f77ac661f74115216a
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 1374c68c6060fedb594170f77ac661f74115216a
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: gpwcqJRahQ4lkz8z+9dRmAKMTp6cZTj7TFaoc7dXjJ+gpiTKee...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 2f83d678f4cf2d420d13889341727e94da5f7e20
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 2f83d678f4cf2d420d13889341727e94da5f7e20
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=text
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.callback_server - INFO - 处理文本消息: content=你好..., user=WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 处理文本消息: 你好, user: WeiJueSen
-2026-05-06 15:08:24 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 关键词搜索: ['你好']
-2026-05-06 15:08:24 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: True)
-2026-05-06 15:08:24 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:08:24 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:08:25 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:25 - gx_gp_monitor - INFO - 采购公告 爬取完成，共获取 100 条公告，耗时 0.45秒
-2026-05-06 15:08:25 - gx_gp_monitor - INFO - 开始爬取 结果公告
-2026-05-06 15:08:25 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:25 - gx_gp_monitor - INFO - 结果公告 爬取完成，共获取 100 条公告，耗时 0.36秒
-2026-05-06 15:08:25 - gx_gp_monitor - INFO - 开始爬取 合同公告
-2026-05-06 15:08:26 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 合同公告 爬取完成，共获取 100 条公告，耗时 0.30秒
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 开始爬取 更正公告
-2026-05-06 15:08:26 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 更正公告 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 开始爬取 招标文件预公示
-2026-05-06 15:08:26 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 招标文件预公示 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 开始爬取 单一来源公示
-2026-05-06 15:08:26 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 单一来源公示 爬取完成，共获取 100 条公告，耗时 0.30秒
-2026-05-06 15:08:26 - gx_gp_monitor - INFO - 开始爬取 电子卖场公示
-2026-05-06 15:08:27 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:27 - gx_gp_monitor - INFO - 电子卖场公示 爬取完成，共获取 100 条公告，耗时 0.48秒
-2026-05-06 15:08:27 - gx_gp_monitor - INFO - 开始爬取 履约验收公示
-2026-05-06 15:08:27 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:27 - gx_gp_monitor - INFO - 履约验收公示 爬取完成，共获取 100 条公告，耗时 0.29秒
-2026-05-06 15:08:27 - gx_gp_monitor - INFO - 开始爬取 工程类公告
-2026-05-06 15:08:28 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:28 - gx_gp_monitor - INFO - 工程类公告 爬取完成，共获取 100 条公告，耗时 0.40秒
-2026-05-06 15:08:28 - gx_gp_monitor - INFO - 开始爬取 框架协议征集公告
-2026-05-06 15:08:28 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:28 - gx_gp_monitor - INFO - 框架协议征集公告 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:28 - gx_gp_monitor - INFO - 开始爬取 框架协议入围结果公告
-2026-05-06 15:08:28 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:28 - gx_gp_monitor - INFO - 框架协议入围结果公告 爬取完成，共获取 100 条公告，耗时 0.27秒
-2026-05-06 15:08:28 - gx_gp_monitor - INFO - 开始爬取 框架协议成交结果汇总公告
-2026-05-06 15:08:29 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:29 - gx_gp_monitor - INFO - 框架协议成交结果汇总公告 爬取完成，共获取 100 条公告，耗时 0.29秒
-2026-05-06 15:08:29 - gx_gp_monitor - INFO - 开始爬取 采购意向公开
-2026-05-06 15:08:29 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:29 - gx_gp_monitor - INFO - 采购意向公开 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:08:29 - gx_gp_monitor.crawler.spider - INFO - 爬取完成: 共处理 13 个来源，成功 13 个，失败 0 个，获取 1300 条公告
-2026-05-06 15:08:29 - gx_gp_monitor.main - INFO - 搜索到 1300 条原始公告
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 开始按来源保存 1300 条手动搜索公告到专用表，每个来源最多保留 100 条
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement1 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement2 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement3 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement4 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement5 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement6 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement7 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement10 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement11 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement20 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement21 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement23 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 来源 61-266648 保存了 1 条手动搜索公告
-2026-05-06 15:08:29 - gx_gp_monitor.storage.postgresql - INFO - 按来源保存手动搜索公告完成，总计保存 13 条公告
-2026-05-06 15:08:29 - gx_gp_monitor.main - INFO - 保存手动搜索公告完成：共保存 13 条，按来源统计: {'ZcyAnnouncement1': 1, 'ZcyAnnouncement2': 1, 'ZcyAnnouncement3': 1, 'ZcyAnnouncement4': 1, 'ZcyAnnouncement5': 1, 'ZcyAnnouncement6': 1, 'ZcyAnnouncement7': 1, 'ZcyAnnouncement10': 1, 'ZcyAnnouncement11': 1, 'ZcyAnnouncement20': 1, 'ZcyAnnouncement21': 1, 'ZcyAnnouncement23': 1, '61-266648': 1}
-2026-05-06 15:08:29 - gx_gp_monitor.filters.filters - INFO - 日期筛选: 1300 -> 352 条公告
-2026-05-06 15:08:29 - gx_gp_monitor.filters.filters - INFO - 关键词筛选: 352 -> 0 条公告
-2026-05-06 15:08:29 - gx_gp_monitor.filters.filters - INFO - 来源筛选: 0 -> 0 条公告
-2026-05-06 15:08:29 - gx_gp_monitor.main - INFO - 筛选后剩余 0 条公告
-2026-05-06 15:08:29 - gx_gp_monitor.main - INFO - 手动爬取模式：跳过筛选后公告的数据库保存
-2026-05-06 15:08:29 - gx_gp_monitor.main - INFO - 爬取任务完成: {'success': True, 'total_crawled': 1300, 'filtered': 0, 'saved': 0, 'markdown_generated': False, 'notification_sent': False, 'filter_stats': {'keyword_filtered': 352, 'date_filtered': 948, 'duplicate_filtered': 0, 'source_filtered': 0}, 'filtered_announcements': []}
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: rMwd7/7jivhj3K171JP9cTR0n/vSdK/XxP5FWC4NirBXOkApNN...
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: aff09303a74cb9b91b58bda7f544420d89e99342
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: aff09303a74cb9b91b58bda7f544420d89e99342
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:39 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: 9BiCuWCpV4Por0LpC3Q2d+iJL/AY9a8gv724JzeANrK2O/S/9L...
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 3b373232e89cde03fef86f3efae1d3848558428c
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 3b373232e89cde03fef86f3efae1d3848558428c
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:08:46 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:08:50 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:50 - gx_gp_monitor - INFO - 采购公告 爬取完成，共获取 100 条公告，耗时 30.48秒
-2026-05-06 15:08:50 - gx_gp_monitor - INFO - 开始爬取 结果公告
-2026-05-06 15:08:50 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:50 - gx_gp_monitor - INFO - 结果公告 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:50 - gx_gp_monitor - INFO - 开始爬取 合同公告
-2026-05-06 15:08:51 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:51 - gx_gp_monitor - INFO - 合同公告 爬取完成，共获取 100 条公告，耗时 0.29秒
-2026-05-06 15:08:51 - gx_gp_monitor - INFO - 开始爬取 更正公告
-2026-05-06 15:08:51 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:51 - gx_gp_monitor - INFO - 更正公告 爬取完成，共获取 100 条公告，耗时 0.34秒
-2026-05-06 15:08:51 - gx_gp_monitor - INFO - 开始爬取 招标文件预公示
-2026-05-06 15:08:51 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:51 - gx_gp_monitor - INFO - 招标文件预公示 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:51 - gx_gp_monitor - INFO - 开始爬取 单一来源公示
-2026-05-06 15:08:52 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:52 - gx_gp_monitor - INFO - 单一来源公示 爬取完成，共获取 100 条公告，耗时 0.28秒
-2026-05-06 15:08:52 - gx_gp_monitor - INFO - 开始爬取 电子卖场公示
-2026-05-06 15:08:52 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:52 - gx_gp_monitor - INFO - 电子卖场公示 爬取完成，共获取 100 条公告，耗时 0.46秒
-2026-05-06 15:08:52 - gx_gp_monitor - INFO - 开始爬取 履约验收公示
-2026-05-06 15:08:52 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:52 - gx_gp_monitor - INFO - 履约验收公示 爬取完成，共获取 100 条公告，耗时 0.40秒
-2026-05-06 15:08:52 - gx_gp_monitor - INFO - 开始爬取 工程类公告
-2026-05-06 15:08:53 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:53 - gx_gp_monitor - INFO - 工程类公告 爬取完成，共获取 100 条公告，耗时 0.30秒
-2026-05-06 15:08:53 - gx_gp_monitor - INFO - 开始爬取 框架协议征集公告
-2026-05-06 15:08:53 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:53 - gx_gp_monitor - INFO - 框架协议征集公告 爬取完成，共获取 100 条公告，耗时 0.26秒
-2026-05-06 15:08:53 - gx_gp_monitor - INFO - 开始爬取 框架协议入围结果公告
-2026-05-06 15:08:53 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:53 - gx_gp_monitor - INFO - 框架协议入围结果公告 爬取完成，共获取 100 条公告，耗时 0.28秒
-2026-05-06 15:08:53 - gx_gp_monitor - INFO - 开始爬取 框架协议成交结果汇总公告
-2026-05-06 15:08:54 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:54 - gx_gp_monitor - INFO - 框架协议成交结果汇总公告 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:08:54 - gx_gp_monitor - INFO - 开始爬取 采购意向公开
-2026-05-06 15:08:54 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:54 - gx_gp_monitor - INFO - 采购意向公开 爬取完成，共获取 100 条公告，耗时 0.30秒
-2026-05-06 15:08:54 - gx_gp_monitor.crawler.spider - INFO - 爬取完成: 共处理 13 个来源，成功 13 个，失败 0 个，获取 1300 条公告
-2026-05-06 15:08:54 - gx_gp_monitor.main - INFO - 搜索到 1300 条原始公告
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 开始按来源保存 1300 条手动搜索公告到专用表，每个来源最多保留 100 条
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement1 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement2 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement3 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement4 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement5 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement6 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement7 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement10 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement11 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement20 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement21 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement23 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.core.database - INFO - 批量保存公告到manual_announcements完成，影响行数: 1
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 来源 61-266648 保存了 1 条手动搜索公告
-2026-05-06 15:08:54 - gx_gp_monitor.storage.postgresql - INFO - 按来源保存手动搜索公告完成，总计保存 13 条公告
-2026-05-06 15:08:54 - gx_gp_monitor.main - INFO - 保存手动搜索公告完成：共保存 13 条，按来源统计: {'ZcyAnnouncement1': 1, 'ZcyAnnouncement2': 1, 'ZcyAnnouncement3': 1, 'ZcyAnnouncement4': 1, 'ZcyAnnouncement5': 1, 'ZcyAnnouncement6': 1, 'ZcyAnnouncement7': 1, 'ZcyAnnouncement10': 1, 'ZcyAnnouncement11': 1, 'ZcyAnnouncement20': 1, 'ZcyAnnouncement21': 1, 'ZcyAnnouncement23': 1, '61-266648': 1}
-2026-05-06 15:08:54 - gx_gp_monitor.filters.filters - INFO - 日期筛选: 1300 -> 352 条公告
-2026-05-06 15:08:54 - gx_gp_monitor.filters.filters - INFO - 关键词筛选: 352 -> 0 条公告
-2026-05-06 15:08:54 - gx_gp_monitor.filters.filters - INFO - 来源筛选: 0 -> 0 条公告
-2026-05-06 15:08:54 - gx_gp_monitor.main - INFO - 筛选后剩余 0 条公告
-2026-05-06 15:08:54 - gx_gp_monitor.main - INFO - 手动爬取模式：跳过筛选后公告的数据库保存
-2026-05-06 15:08:54 - gx_gp_monitor.main - INFO - 爬取任务完成: {'success': True, 'total_crawled': 1300, 'filtered': 0, 'saved': 0, 'markdown_generated': False, 'notification_sent': False, 'filter_stats': {'keyword_filtered': 352, 'date_filtered': 948, 'duplicate_filtered': 0, 'source_filtered': 0}, 'filtered_announcements': []}
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: thc6lzWswZ3ZylEM+A5xlLi2CKg5D6FMa1JFGzAuW6/IrfJMqq...
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 16e97f27eb0f7307ebb9b87c5a072b613b2c8a18
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 16e97f27eb0f7307ebb9b87c5a072b613b2c8a18
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=help_guide, user=NongGuangGuo
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: help_guide, user: NongGuangGuo
-2026-05-06 15:09:28 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求使用说明
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: 5ju3K87vTeR4WaPsI8IqATUO1g30XklsBfeGNDSzcH09aZgr3x...
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 5c49ef855bd9a5763992d62e734aef75666a4a2c
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 5c49ef855bd9a5763992d62e734aef75666a4a2c
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=today_stats, user=WeiJueSen
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: today_stats, user: WeiJueSen
-2026-05-06 15:09:33 - gx_gp_monitor.wechat.message_handler - INFO - 用户 WeiJueSen 请求今日统计
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 384
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: Cu+8S6elykWeq3afFdD/lbMtOni21mETVdpRjEn+AHtiYRlBYV...
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 21012d5bc0f6d7e71328b0ec2ccb62b938898f89
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 21012d5bc0f6d7e71328b0ec2ccb62b938898f89
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=subscribe, event_key=None, user=LuLiuCui
-2026-05-09 10:31:46 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: subscribe, key: None, user: LuLiuCui

logs/gx_gp_monitor.log.2

@@ -1,139 +0,0 @@
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: vlN4cpR79+nVcy2Cvf22D4nsbOxqtyYFlVO3nvPdIz2NLVZTCr...
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 060aff2e6666d1df9c957ebb61d214664c64e72f
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 060aff2e6666d1df9c957ebb61d214664c64e72f
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=crawl_now, user=NongGuangGuo
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: crawl_now, user: NongGuangGuo
-2026-05-06 15:07:43 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 触发立即搜索
-2026-05-06 15:07:43 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: False)
-2026-05-06 15:07:43 - gx_gp_monitor.core.reliability - INFO - 健康检查通过
-2026-05-06 15:07:43 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:07:43 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:07:44 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:44 - gx_gp_monitor - INFO - 采购公告 爬取完成，共获取 100 条公告，耗时 0.53秒
-2026-05-06 15:07:44 - gx_gp_monitor - INFO - 开始爬取 结果公告
-2026-05-06 15:07:44 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:44 - gx_gp_monitor - INFO - 结果公告 爬取完成，共获取 100 条公告，耗时 0.43秒
-2026-05-06 15:07:44 - gx_gp_monitor - INFO - 开始爬取 合同公告
-2026-05-06 15:07:45 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:45 - gx_gp_monitor - INFO - 合同公告 爬取完成，共获取 100 条公告，耗时 0.29秒
-2026-05-06 15:07:45 - gx_gp_monitor - INFO - 开始爬取 更正公告
-2026-05-06 15:07:45 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:45 - gx_gp_monitor - INFO - 更正公告 爬取完成，共获取 100 条公告，耗时 0.38秒
-2026-05-06 15:07:45 - gx_gp_monitor - INFO - 开始爬取 招标文件预公示
-2026-05-06 15:07:45 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:45 - gx_gp_monitor - INFO - 招标文件预公示 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:07:45 - gx_gp_monitor - INFO - 开始爬取 单一来源公示
-2026-05-06 15:07:46 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:46 - gx_gp_monitor - INFO - 单一来源公示 爬取完成，共获取 100 条公告，耗时 0.34秒
-2026-05-06 15:07:46 - gx_gp_monitor - INFO - 开始爬取 电子卖场公示
-2026-05-06 15:07:46 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:46 - gx_gp_monitor - INFO - 电子卖场公示 爬取完成，共获取 100 条公告，耗时 0.51秒
-2026-05-06 15:07:46 - gx_gp_monitor - INFO - 开始爬取 履约验收公示
-2026-05-06 15:07:47 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 履约验收公示 爬取完成，共获取 100 条公告，耗时 0.30秒
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 开始爬取 工程类公告
-2026-05-06 15:07:47 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 工程类公告 爬取完成，共获取 100 条公告，耗时 0.27秒
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 开始爬取 框架协议征集公告
-2026-05-06 15:07:47 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 框架协议征集公告 爬取完成，共获取 100 条公告，耗时 0.35秒
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 开始爬取 框架协议入围结果公告
-2026-05-06 15:07:47 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 框架协议入围结果公告 爬取完成，共获取 100 条公告，耗时 0.32秒
-2026-05-06 15:07:47 - gx_gp_monitor - INFO - 开始爬取 框架协议成交结果汇总公告
-2026-05-06 15:07:48 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:48 - gx_gp_monitor - INFO - 框架协议成交结果汇总公告 爬取完成，共获取 100 条公告，耗时 0.35秒
-2026-05-06 15:07:48 - gx_gp_monitor - INFO - 开始爬取 采购意向公开
-2026-05-06 15:07:48 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:07:48 - gx_gp_monitor - INFO - 采购意向公开 爬取完成，共获取 100 条公告，耗时 0.33秒
-2026-05-06 15:07:48 - gx_gp_monitor.crawler.spider - INFO - 爬取完成: 共处理 13 个来源，成功 13 个，失败 0 个，获取 1300 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.main - INFO - 搜索到 1300 条原始公告
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 开始按来源保存 1300 条公告，每个来源最多保留 100 条
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 数据库连接错误: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 批量保存公告失败: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement1 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 数据库连接错误: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 批量保存公告失败: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement2 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 数据库连接错误: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 批量保存公告失败: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement3 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 数据库连接错误: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 批量保存公告失败: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement4 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 数据库连接错误: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - ERROR - 批量保存公告失败: connection already closed
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement5 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement6 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement7 保存了 1 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement10 保存了 1 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement11 保存了 1 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement20 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement21 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 0 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 ZcyAnnouncement23 保存了 0 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.core.database - INFO - 批量保存公告完成，成功保存 1 条
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 来源 61-266648 保存了 1 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.storage.postgresql - INFO - 按来源保存完成，总计保存 4 条公告
-2026-05-06 15:07:48 - gx_gp_monitor.main - INFO - 保存自动爬取公告完成：共保存 4 条，按来源统计: {'ZcyAnnouncement1': 0, 'ZcyAnnouncement2': 0, 'ZcyAnnouncement3': 0, 'ZcyAnnouncement4': 0, 'ZcyAnnouncement5': 0, 'ZcyAnnouncement6': 0, 'ZcyAnnouncement7': 1, 'ZcyAnnouncement10': 1, 'ZcyAnnouncement11': 1, 'ZcyAnnouncement20': 0, 'ZcyAnnouncement21': 0, 'ZcyAnnouncement23': 0, '61-266648': 1}
-2026-05-06 15:07:48 - gx_gp_monitor.main - INFO - 筛选出 1300 条新公告
-2026-05-06 15:07:48 - gx_gp_monitor.filters.filters - INFO - 来源筛选: 1300 -> 1300 条公告
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 512
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: GwLOHlMWE3qBsHJ3DegXZk5RGOb0hEg2g9SbYIvxkhynxr/43t...
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 052516f0e87dd3793a1035dccb0f3b3d9fd806de
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 052516f0e87dd3793a1035dccb0f3b3d9fd806de
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=text
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.callback_server - INFO - 处理文本消息: content=河池分行大化瑶族自治县中医医院结算系
-统项目..., user=NongGuangGuo
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.message_handler - INFO - 处理文本消息: 河池分行大化瑶族自治县中医医院结算系
-统项目, user: NongGuangGuo
-2026-05-06 15:07:49 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 关键词搜索: ['河池分行大化瑶族自治县中医医院结算系', '统项目']
-2026-05-06 15:07:49 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: True)
-2026-05-06 15:07:49 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:07:49 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:07:49 - gx_gp_monitor.filters.filters - INFO - 去重筛选: 移除了 803 条重复公告
-2026-05-06 15:07:49 - gx_gp_monitor.filters.filters - INFO - 关键词筛选: 497 -> 0 条公告
-2026-05-06 15:07:49 - gx_gp_monitor.filters.filters - INFO - 筛选完成: 总数 1300 -> 筛选后 0 (关键词: 497, 日期: 0, 去重: 803, 来源: 0)
-2026-05-06 15:07:49 - gx_gp_monitor.main - INFO - 筛选后剩余 0 条公告
-2026-05-06 15:07:49 - gx_gp_monitor.storage.md_generator - INFO - Markdown文件已保存到: onu.md (共 0 条公告)
-2026-05-06 15:07:49 - gx_gp_monitor.main - INFO - 爬取任务完成: {'success': True, 'total_crawled': 1300, 'filtered': 0, 'saved': 0, 'markdown_generated': True, 'notification_sent': False, 'filter_stats': {'keyword_filtered': 1797, 'date_filtered': 0, 'duplicate_filtered': 803, 'source_filtered': 0}}
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: p4+cMpoxGV5kJJ2lLlM6u6/HHN4OJMSHH/wxWwSxKkZGGxajZn...
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: fc48810bdc9c0216f44d1adde162007b4cca0790
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: fc48810bdc9c0216f44d1adde162007b4cca0790
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=crawl_now, user=NongGuangGuo
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: crawl_now, user: NongGuangGuo
-2026-05-06 15:07:51 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 触发立即搜索
-2026-05-06 15:07:51 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: False)
-2026-05-06 15:07:51 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:07:51 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:08:20 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 采购公告 爬取完成，共获取 100 条公告，耗时 30.54秒
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 开始爬取 结果公告
-2026-05-06 15:08:20 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 结果公告 爬取完成，共获取 100 条公告，耗时 0.34秒
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 开始爬取 合同公告
-2026-05-06 15:08:20 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 合同公告 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:08:20 - gx_gp_monitor - INFO - 开始爬取 更正公告
-2026-05-06 15:08:21 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 更正公告 爬取完成，共获取 100 条公告，耗时 0.33秒
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 开始爬取 招标文件预公示
-2026-05-06 15:08:21 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 招标文件预公示 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:08:21 - gx_gp_monitor - INFO - 开始爬取 单一来源公示

logs/gx_gp_monitor.log.3

@@ -1,48 +0,0 @@
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: QMt5ylkt6tq8Vl8TdJuv5/WIdXPum6+KEhz/iY06ZJZ6cc6oAi...
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: d9502bdfb3f5fe20997c0668e5f7af42d6444726
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: d9502bdfb3f5fe20997c0668e5f7af42d6444726
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=keyword_manage, user=NongGuangGuo
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: keyword_manage, user: NongGuangGuo
-2026-05-06 15:07:40 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 请求关键词管理
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: p4+cMpoxGV5kJJ2lLlM6u6/HHN4OJMSHH/wxWwSxKkZGGxajZn...
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: fc48810bdc9c0216f44d1adde162007b4cca0790
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: fc48810bdc9c0216f44d1adde162007b4cca0790
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=crawl_now, user=NongGuangGuo
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: crawl_now, user: NongGuangGuo
-2026-05-06 15:07:46 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 触发立即搜索
-2026-05-06 15:07:46 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: False)
-2026-05-06 15:07:46 - gx_gp_monitor.core.reliability - INFO - 健康检查通过
-2026-05-06 15:07:46 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:07:46 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - ERROR - ✅ XML解析成功，提取的encrypt长度: 472
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - ERROR - 提取的encrypt前50字符: vlN4cpR79+nVcy2Cvf22D4nsbOxqtyYFlVO3nvPdIz2NLVZTCr...
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - ERROR - 计算的签名: 060aff2e6666d1df9c957ebb61d214664c64e72f
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - ERROR - 接收的签名: 060aff2e6666d1df9c957ebb61d214664c64e72f
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - ERROR - 签名匹配: True
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - ERROR - 尝试使用默认token计算签名...
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - INFO - 收到企业微信消息: 类型=event
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.callback_server - INFO - 处理事件消息: event=click, event_key=crawl_now, user=NongGuangGuo
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.message_handler - INFO - 处理事件: click, key: crawl_now, user: NongGuangGuo
-2026-05-06 15:07:48 - gx_gp_monitor.wechat.message_handler - INFO - 用户 NongGuangGuo 触发立即搜索
-2026-05-06 15:07:48 - gx_gp_monitor.main - INFO - 开始执行搜索任务 (手动搜索: False)
-2026-05-06 15:07:48 - gx_gp_monitor.crawler.spider - INFO - 开始爬取 13 个公告来源
-2026-05-06 15:07:48 - gx_gp_monitor - INFO - 开始爬取 采购公告
-2026-05-06 15:08:17 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:17 - gx_gp_monitor - INFO - 采购公告 爬取完成，共获取 100 条公告，耗时 30.47秒
-2026-05-06 15:08:17 - gx_gp_monitor - INFO - 开始爬取 结果公告
-2026-05-06 15:08:17 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:17 - gx_gp_monitor - INFO - 结果公告 爬取完成，共获取 100 条公告，耗时 0.34秒
-2026-05-06 15:08:17 - gx_gp_monitor - INFO - 开始爬取 合同公告
-2026-05-06 15:08:17 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:17 - gx_gp_monitor - INFO - 合同公告 爬取完成，共获取 100 条公告，耗时 0.31秒
-2026-05-06 15:08:17 - gx_gp_monitor - INFO - 开始爬取 更正公告
-2026-05-06 15:08:18 - gx_gp_monitor.crawler.parsers - INFO - 成功解析 100/100 条公告记录
-2026-05-06 15:08:18 - gx_gp_monitor - INFO - 更正公告 爬取完成，共获取 100 条公告，耗时 0.33秒
-2026-05-06 15:08:18 - gx_gp_monitor - INFO - 开始爬取 招标文件预公示

onu.md

@@ -1,8 +0,0 @@
-📋 关键词搜索: `未知` - 总公告数: `0`
-
-**更新时间: 2026-05-06 15:08:57**
-
-
-## 无匹配公告
-
-在指定时间范围内没有找到符合条件的公告。

pyproject.toml

@@ -0,0 +1,44 @@
+[project]
+name = "gx-gp-notify"
+version = "2.0.0"
+description = "广西政府采购网公告监控系统"
+requires-python = ">=3.12"
+dependencies = [
+    "fastapi>=0.115.0",
+    "uvicorn[standard]>=0.30.0",
+    "sqlalchemy[asyncio]>=2.0.30",
+    "asyncpg>=0.29.0",
+    "alembic>=1.13.0",
+    "httpx>=0.27.0",
+    "apscheduler>=3.10.0",
+    "pydantic-settings>=2.3.0",
+    "beautifulsoup4>=4.12.0",
+    "lxml>=5.2.0",
+    "pycryptodome>=3.20.0",
+    "python-dateutil>=2.9.0",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.2.0",
+    "pytest-asyncio>=0.23.0",
+    "pytest-cov>=5.0.0",
+    "ruff>=0.4.0",
+]
+
+[tool.setuptools.packages.find]
+include = ["app*"]
+
+[tool.ruff]
+target-version = "py312"
+line-length = 100
+
+[tool.ruff.lint]
+select = ["E", "F", "I", "N", "W", "UP"]
+
+[tool.ruff.lint.per-file-ignores]
+"app/wechat/*.py" = ["N802", "N803", "N806"]
+
+[tool.pytest.ini_options]
+asyncio_mode = "auto"
+testpaths = ["tests"]

tests/conftest.py

@@ -0,0 +1,13 @@
+import pytest
+
+
+@pytest.fixture
+def sample_announcement_data():
+    return {
+        "title": "测试公告标题",
+        "publish_date": "2026-05-09",
+        "purchase_name": "测试单位",
+        "content_url": "https://example.com/detail/123",
+        "source_code": "ZcyAnnouncement1",
+        "source_name": "采购公告",
+    }

tests/test_api/test_health.py

@@ -0,0 +1,13 @@
+import pytest
+from httpx import ASGITransport, AsyncClient
+
+from app.main import app
+
+
+@pytest.mark.asyncio
+async def test_health():
+    transport = ASGITransport(app=app)
+    async with AsyncClient(transport=transport, base_url="http://test") as client:
+        response = await client.get("/health")
+        assert response.status_code == 200
+        assert response.json() == {"status": "ok"}

tests/test_crawler/test_base.py

@@ -0,0 +1,78 @@
+from datetime import datetime
+
+import pytest
+
+from app.crawler.base import BaseSpider, CrawlResult, PipelineConfig, PipelineResult
+
+
+class FakeSpider(BaseSpider):
+    name = "test_spider"
+    source_code = "test_source"
+    source_name = "测试来源"
+
+    async def crawl(self) -> CrawlResult:
+        return CrawlResult(
+            source_code=self.source_code,
+            source_name=self.source_name,
+            total_count=5,
+            new_count=3,
+            crawled_at=datetime.now(),
+        )
+
+    def get_pipeline_config(self) -> PipelineConfig:
+        return PipelineConfig(
+            filter_enabled=True,
+            keywords=["测试"],
+            dedup_enabled=True,
+            notify_mode="filtered",
+            mark_sent=False,
+        )
+
+
+@pytest.mark.asyncio
+async def test_base_spider_crawl():
+    spider = FakeSpider()
+    result = await spider.crawl()
+    assert result.source_code == "test_source"
+    assert result.total_count == 5
+    assert result.new_count == 3
+    assert result.success is True
+
+
+def test_pipeline_config_defaults():
+    config = PipelineConfig()
+    assert config.filter_enabled is True
+    assert config.keywords == []
+    assert config.dedup_enabled is True
+    assert config.notify_mode == "filtered"
+    assert config.mark_sent is False
+
+
+def test_pipeline_result_defaults():
+    result = PipelineResult()
+    assert result.stored == 0
+    assert result.filtered == 0
+    assert result.notified == 0
+    assert result.markdown_generated is False
+
+
+def test_generate_content_hash():
+    h = BaseSpider.generate_content_hash(
+        "title", "2026-05-09", "unit", "https://x.com", "source"
+    )
+    assert len(h) == 64
+    assert all(c in "0123456789abcdef" for c in h)
+
+
+def test_generate_content_hash_deterministic():
+    h1 = BaseSpider.generate_content_hash("t", "d", "p", "u", "s")
+    h2 = BaseSpider.generate_content_hash("t", "d", "p", "u", "s")
+    assert h1 == h2
+
+
+def test_crawl_result_failure():
+    result = CrawlResult(
+        source_code="s", source_name="n",
+        error_message="连接超时"
+    )
+    assert result.success is False

tests/test_crawler/test_dahuagov_spider.py

@@ -0,0 +1,64 @@
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from app.crawler.base import PipelineConfig
+from app.crawler.dahuagov_spider import DahuagovSpider
+
+
+@pytest.mark.asyncio
+async def test_dahuagov_spider_attributes():
+    spider = DahuagovSpider()
+    assert spider.name == "dahuagov"
+    assert spider.source_code == "dahuagov"
+    assert spider.source_name == "大化县政府网采购公告"
+
+
+@pytest.mark.asyncio
+async def test_dahuagov_spider_pipeline_config():
+    spider = DahuagovSpider()
+    config = spider.get_pipeline_config()
+    assert isinstance(config, PipelineConfig)
+    assert config.filter_enabled is False
+    assert config.notify_mode == "all"
+    assert config.mark_sent is True
+
+
+@pytest.mark.asyncio
+async def test_dahuagov_spider_crawl():
+    spider = DahuagovSpider()
+
+    html = """
+    <html><body>
+      <ul class="more-list">
+        <li><span>2026-05-08</span>
+            <a href="./detail/1.html" title="公告1">公告1</a></li>
+        <li><span>2026-05-07</span>
+            <a href="./detail/2.html" title="公告2">公告2</a></li>
+      </ul>
+    </body></html>
+    """
+
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.text = html
+
+    with patch("httpx.AsyncClient.get", AsyncMock(return_value=mock_response)):
+        result = await spider.crawl()
+        assert result.total_count == 2
+        assert len(result.announcements) == 2
+        assert result.success is True
+
+
+@pytest.mark.asyncio
+async def test_dahuagov_spider_crawl_empty():
+    spider = DahuagovSpider()
+
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.text = "<html><body></body></html>"
+
+    with patch("httpx.AsyncClient.get", AsyncMock(return_value=mock_response)):
+        result = await spider.crawl()
+        assert result.total_count == 0
+        assert result.success is True

tests/test_crawler/test_gxgp_spider.py

@@ -0,0 +1,73 @@
+from unittest.mock import AsyncMock, MagicMock, patch
+
+import pytest
+
+from app.crawler.base import PipelineConfig
+from app.crawler.gxgp_spider import GXGPSpider
+
+
+@pytest.mark.asyncio
+async def test_gxgp_spider_attributes():
+    spider = GXGPSpider()
+    assert spider.name == "gxgp"
+    assert spider.source_code == "gxgp"
+    assert spider.source_name == "广西政府采购网"
+
+
+@pytest.mark.asyncio
+async def test_gxgp_spider_pipeline_config():
+    spider = GXGPSpider()
+    config = spider.get_pipeline_config()
+    assert isinstance(config, PipelineConfig)
+    assert config.filter_enabled is True
+    assert config.notify_mode == "filtered"
+    assert config.mark_sent is False
+
+
+@pytest.mark.asyncio
+async def test_gxgp_spider_crawl_empty():
+    spider = GXGPSpider()
+
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.json.return_value = {
+        "success": True,
+        "result": {"data": {"data": [], "total": 0, "pageNo": 1, "pageSize": 100,
+                            "pages": 0, "empty": True, "hasNext": False, "hasPrevious": False}},
+    }
+
+    with patch("httpx.AsyncClient.post", AsyncMock(return_value=mock_response)):
+        result = await spider.crawl(sources=["ZcyAnnouncement1"])
+        assert result.total_count == 0
+        assert len(result.announcements) == 0
+        assert result.success is True
+
+
+@pytest.mark.asyncio
+async def test_gxgp_spider_crawl_with_data():
+    spider = GXGPSpider()
+
+    mock_data = {
+        "success": True,
+        "result": {
+            "data": {
+                "data": [{
+                    "title": "测试采购公告",
+                    "publishDate": 1746720000000,
+                    "purchaseName": "测试单位",
+                    "articleId": 12345,
+                }],
+                "total": 1, "pageNo": 1, "pageSize": 100,
+                "pages": 1, "empty": False, "hasNext": False, "hasPrevious": False,
+            }
+        },
+    }
+
+    mock_response = MagicMock()
+    mock_response.status_code = 200
+    mock_response.json.return_value = mock_data
+
+    with patch("httpx.AsyncClient.post", AsyncMock(return_value=mock_response)):
+        result = await spider.crawl(sources=["ZcyAnnouncement1"])
+        assert result.total_count >= 0
+        assert result.success is True

tests/test_crawler/test_parsers.py

@@ -0,0 +1,107 @@
+from datetime import datetime
+
+from app.crawler.parsers import (
+    extract_pagination,
+    parse_dahuagov_html,
+    parse_gxgp_api_response,
+)
+
+
+def make_api_response(records_data):
+    return {
+        "success": True,
+        "result": {
+            "data": {
+                "data": records_data,
+                "total": len(records_data),
+                "pageNo": 1,
+                "pageSize": 100,
+                "pages": 1,
+                "empty": len(records_data) == 0,
+                "hasNext": False,
+                "hasPrevious": False,
+            }
+        },
+    }
+
+
+def test_parse_gxgp_single_record():
+    response = make_api_response([
+        {
+            "title": "测试采购公告",
+            "publishDate": 1746720000000,
+            "purchaseName": "测试采购单位",
+            "articleId": 12345,
+        }
+    ])
+    crawled_at = datetime(2026, 5, 9, 10, 0, 0)
+    results = parse_gxgp_api_response(
+        response,
+        source_code="ZcyAnnouncement1",
+        source_name="采购公告",
+        crawled_at=crawled_at,
+        category_id=66485,
+    )
+    assert len(results) == 1
+    assert results[0]["title"] == "测试采购公告"
+    assert results[0]["source_code"] == "ZcyAnnouncement1"
+    assert "content_hash" in results[0]
+
+
+def test_parse_gxgp_empty_response():
+    response = make_api_response([])
+    crawled_at = datetime(2026, 5, 9, 10, 0, 0)
+    results = parse_gxgp_api_response(
+        response, "ZcyAnnouncement1", "采购公告", crawled_at, 66485
+    )
+    assert len(results) == 0
+
+
+def test_parse_gxgp_missing_title():
+    response = make_api_response([
+        {"title": "", "publishDate": 1746720000000, "purchaseName": "x", "articleId": 1}
+    ])
+    crawled_at = datetime(2026, 5, 9, 10, 0, 0)
+    results = parse_gxgp_api_response(
+        response, "ZcyAnnouncement1", "采购公告", crawled_at, 66485
+    )
+    assert len(results) == 0
+
+
+def test_extract_pagination():
+    response = make_api_response([])
+    pagination = extract_pagination(response)
+    assert pagination["total"] == 0
+    assert pagination["page_no"] == 1
+    assert pagination["has_next"] is False
+
+
+def test_parse_dahuagov_html():
+    html = """
+    <html><body>
+      <ul class="more-list">
+        <li>
+          <span>2026-05-08</span>
+          <a href="./detail/123.html" title="大化县某项目采购公告">大化县某项目采购公告</a>
+        </li>
+        <li>
+          <span>2026-05-07</span>
+          <a href="./detail/124.html" title="大化县另一采购公告">大化县另一采购公告</a>
+        </li>
+      </ul>
+    </body></html>
+    """
+    crawled_at = datetime(2026, 5, 9, 10, 0, 0)
+    results = parse_dahuagov_html(html, crawled_at)
+    assert len(results) == 2
+    assert results[0]["title"] == "大化县某项目采购公告"
+    assert results[0]["source_code"] == "dahuagov"
+    assert results[0]["source_name"] == "大化县政府网采购公告"
+    assert results[0]["purchase_name"] == "大化瑶族自治县"
+
+
+def test_parse_dahuagov_html_no_list():
+    html = "<html><body></body></html>"
+    crawled_at = datetime(2026, 5, 9, 10, 0, 0)
+    results = parse_dahuagov_html(html, crawled_at)
+    assert len(results) == 0

tests/test_services/test_crawl_service.py

@@ -0,0 +1,87 @@
+
+import pytest
+
+from app.crawler.base import BaseSpider, CrawlResult, PipelineConfig
+from app.services.crawl_service import CrawlService
+
+
+class MockGXGPSpider(BaseSpider):
+    name = "mock_gxgp"
+    source_code = "mock_gxgp"
+    source_name = "Mock GXGP"
+
+    async def crawl(self, **kwargs):
+        return CrawlResult(
+            source_code=self.source_code,
+            source_name=self.source_name,
+            total_count=10,
+            new_count=5,
+            announcements=[],
+        )
+
+    def get_pipeline_config(self):
+        return PipelineConfig(
+            filter_enabled=True,
+            keywords=["大化"],
+            notify_mode="filtered",
+        )
+
+
+class MockDahuagovSpider(BaseSpider):
+    name = "mock_dahuagov"
+    source_code = "mock_dahuagov"
+    source_name = "Mock Dahuagov"
+
+    async def crawl(self, **kwargs):
+        return CrawlResult(
+            source_code=self.source_code,
+            source_name=self.source_name,
+            total_count=3,
+            new_count=3,
+            announcements=[],
+        )
+
+    def get_pipeline_config(self):
+        return PipelineConfig(
+            filter_enabled=False,
+            notify_mode="all",
+            mark_sent=True,
+        )
+
+
+@pytest.mark.asyncio
+async def test_crawl_service_registers_spiders():
+    service = CrawlService()
+    service.register(MockGXGPSpider())
+    service.register(MockDahuagovSpider())
+    assert len(service.spiders) == 2
+
+
+@pytest.mark.asyncio
+async def test_crawl_service_run_all():
+    service = CrawlService()
+    service.register(MockGXGPSpider())
+    service.register(MockDahuagovSpider())
+    results = await service.run_all()
+    assert len(results) == 2
+    assert results[0].total_count == 10
+    assert results[1].total_count == 3
+    assert all(r.success for r in results)
+
+
+@pytest.mark.asyncio
+async def test_crawl_service_run_specific():
+    service = CrawlService()
+    service.register(MockGXGPSpider())
+    service.register(MockDahuagovSpider())
+    results = await service.run_spider("mock_dahuagov")
+    assert len(results) == 1
+    assert results[0].source_code == "mock_dahuagov"
+
+
+@pytest.mark.asyncio
+async def test_crawl_service_run_unknown():
+    service = CrawlService()
+    results = await service.run_spider("nonexistent")
+    assert len(results) == 1
+    assert results[0].success is False

tests/test_services/test_filter_service.py

@@ -0,0 +1,39 @@
+from datetime import datetime
+
+from app.services.filter_service import filter_by_date, filter_by_keywords
+
+
+def test_filter_by_keywords_match():
+    announcements = [
+        {"title": "大化县采购公告", "purchase_name": "大化县财政局",
+         "source_code": "test", "source_name": "test"},
+        {"title": "南宁市采购公告", "purchase_name": "南宁市财政局",
+         "source_code": "test", "source_name": "test"},
+    ]
+    result = filter_by_keywords(announcements, ["大化"])
+    assert len(result) == 1
+    assert result[0]["title"] == "大化县采购公告"
+
+
+def test_filter_by_keywords_no_keywords():
+    announcements = [
+        {"title": "大化县采购公告", "purchase_name": "x",
+         "source_code": "test", "source_name": "test"},
+    ]
+    result = filter_by_keywords(announcements, [])
+    assert len(result) == 1
+
+
+def test_filter_by_date_range():
+    today = datetime(2026, 5, 9)
+    announcements = [
+        {"title": "t1", "publish_date": datetime(2026, 5, 9),
+         "source_code": "test", "source_name": "test"},
+        {"title": "t2", "publish_date": datetime(2026, 5, 1),
+         "source_code": "test", "source_name": "test"},
+        {"title": "t3", "publish_date": datetime(2026, 4, 30),
+         "source_code": "test", "source_name": "test"},
+    ]
+    result = filter_by_date(announcements, start_date=today, end_date=today)
+    assert len(result) == 1
+    assert result[0]["title"] == "t1"

tests/test_services/test_notification_service.py

@@ -0,0 +1,42 @@
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from app.services.notification_service import NotificationService
+
+
+@pytest.mark.asyncio
+async def test_notification_send():
+    svc = NotificationService()
+    announcements = [
+        {
+            "title": "测试公告",
+            "publish_date": None,
+            "purchase_name": "测试单位",
+            "content_url": "https://x.com/1",
+            "source_code": "test",
+            "source_name": "测试来源",
+            "announcement_type": "purchase",
+        }
+    ]
+
+    with patch.object(svc.client, "send_textcard", AsyncMock(return_value=True)):
+        count = await svc.send(announcements)
+        assert count == 1
+
+
+@pytest.mark.asyncio
+async def test_notification_send_empty():
+    svc = NotificationService()
+    count = await svc.send([])
+    assert count == 0
+
+
+@pytest.mark.asyncio
+async def test_notification_send_disabled():
+    svc = NotificationService()
+    announcements = [{"title": "test"}]
+
+    with patch.object(svc.client, "send_textcard", AsyncMock(return_value=False)):
+        count = await svc.send(announcements)
+        assert count == 0

tests/test_services/test_pipeline.py

@@ -0,0 +1,95 @@
+from datetime import datetime
+from unittest.mock import AsyncMock, patch
+
+import pytest
+
+from app.crawler.base import CrawlResult, PipelineConfig
+from app.services.pipeline import PostCrawlPipeline
+
+
+@pytest.mark.asyncio
+async def test_pipeline_filtered_mode():
+    config = PipelineConfig(
+        filter_enabled=True,
+        keywords=["大化"],
+        dedup_enabled=True,
+        notify_mode="filtered",
+        mark_sent=False,
+    )
+    result = CrawlResult(
+        source_code="test", source_name="test",
+        total_count=3, new_count=3,
+        announcements=[
+            {
+                "title": "大化县公告", "publish_date": datetime(2026, 5, 9),
+                "purchase_name": "大化县", "content_url": "https://1.com",
+                "source_code": "test", "source_name": "测试",
+                "announcement_type": "purchase", "crawl_mode": "auto",
+                "is_new": True, "is_today": True,
+                "content_hash": "abc123",
+            },
+            {
+                "title": "南宁市公告", "publish_date": datetime(2026, 5, 9),
+                "purchase_name": "南宁市", "content_url": "https://2.com",
+                "source_code": "test", "source_name": "测试",
+                "announcement_type": "purchase", "crawl_mode": "auto",
+                "is_new": True, "is_today": True,
+                "content_hash": "def456",
+            },
+        ],
+    )
+
+    mock_db = AsyncMock()
+    mock_notify = AsyncMock()
+
+    pipeline = PostCrawlPipeline(db_session=mock_db, notification_service=mock_notify)
+
+    with patch.object(pipeline, "_save_to_db", AsyncMock(return_value=2)):
+        with patch.object(pipeline, "_send_notifications", AsyncMock(return_value=1)):
+            pipe_result = await pipeline.process(
+                result.announcements, config
+            )
+            assert pipe_result.stored == 2
+            assert pipe_result.filtered == 1
+            assert pipe_result.notified == 1
+
+
+@pytest.mark.asyncio
+async def test_pipeline_all_mode():
+    config = PipelineConfig(
+        filter_enabled=False,
+        keywords=[],
+        dedup_enabled=True,
+        notify_mode="all",
+        mark_sent=True,
+    )
+    result = CrawlResult(
+        source_code="dahuagov", source_name="大化县政府网",
+        total_count=2, new_count=2,
+        announcements=[
+            {
+                "title": f"公告{i}", "publish_date": datetime(2026, 5, 9),
+                "purchase_name": "大化县", "content_url": f"https://x.com/{i}",
+                "source_code": "dahuagov", "source_name": "大化县政府网采购公告",
+                "announcement_type": "purchase", "crawl_mode": "auto",
+                "is_new": True, "is_today": True,
+                "content_hash": f"hash{i}",
+            }
+            for i in range(2)
+        ],
+    )
+
+    mock_db = AsyncMock()
+    mock_notify = AsyncMock()
+    pipeline = PostCrawlPipeline(db_session=mock_db, notification_service=mock_notify)
+
+    with patch.object(pipeline, "_save_to_db", AsyncMock(return_value=2)):
+        with patch.object(pipeline, "_send_notifications", AsyncMock(return_value=2)):
+            with patch.object(pipeline, "_mark_sent", AsyncMock(return_value=2)):
+                pipe_result = await pipeline.process(
+                    result.announcements, config
+                )
+                assert pipe_result.stored == 2
+                assert pipe_result.filtered == 0
+                assert pipe_result.notified == 2
+                pipeline._mark_sent.assert_awaited_once()