From b00e52e1e0b41ea7959c8bb7e3b63e1522159f0a Mon Sep 17 00:00:00 2001 From: ZJPB Admin Date: Tue, 30 Dec 2025 23:44:27 +0800 Subject: [PATCH] =?UTF-8?q?release:=20v2.2.0=20-=20=E5=8D=9A=E6=9F=A5?= =?UTF-8?q?=E6=96=B0=E9=97=BB=E6=90=9C=E7=B4=A2=E5=8A=9F=E8=83=BD=20(?= =?UTF-8?q?=E7=94=9F=E4=BA=A7=E7=8E=AF=E5=A2=83=E9=83=A8=E7=BD=B2=E7=89=88?= =?UTF-8?q?)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 核心功能： - 集成博查Web Search API自动获取网站相关新闻 - 智能新闻更新机制（每日首次访问触发） - 精确新闻搜索（使用引号强制匹配网站名称） - News模型扩展（source_name, source_icon字段） - 网站详情页新闻展示模块 - 新闻来源网站信息展示 - 自动去重防止重复新闻 技术实现： - NewsSearcher工具类封装博查API - 数据库迁移脚本migrate_news_fields.py - 测试脚本test_news_feature.py - 定期任务脚本fetch_news_cron.py - API路由：/api/fetch-site-news, /api/fetch-all-news 配置优化： - 修复manage.sh路径和启动命令 - 博查API配置（BOCHA_API_KEY, BOCHA_BASE_URL） - 新闻搜索参数配置 界面优化： - 详情页新闻模块（左侧主栏） - 相似推荐模块（右侧边栏） - 首页标签图标修复 - 后台添加修改密码功能 - 登录页面优化 部署信息： - 部署日期: 2025-12-30 - 部署方式: 手动上传文件 - 数据库: 已迁移（添加source_name和source_icon字段） --- app.py | 278 +++++++++++++++++++++++++++++++++++- config.py | 14 ++ fetch_news_cron.py | 167 ++++++++++++++++++++++ manage.sh | 4 +- migrate_news_fields.py | 99 +++++++++++++ models.py | 2 + templates/admin/master.html | 6 + templates/admin_login.html | 142 ++++++++++++------ templates/detail_new.html | 83 +++++++---- templates/index_new.html | 154 ++++++++++++++++---- test_news_feature.py | 142 ++++++++++++++++++ utils/news_searcher.py | 271 +++++++++++++++++++++++++++++++++++ 12 files changed, 1255 insertions(+), 107 deletions(-) create mode 100644 fetch_news_cron.py create mode 100644 migrate_news_fields.py create mode 100644 test_news_feature.py create mode 100644 utils/news_searcher.py diff --git a/app.py b/app.py index 7a2e392..2160534 100644 --- a/app.py +++ b/app.py @@ -9,6 +9,7 @@ from config import config from models import db, Site, Tag, Admin as AdminModel, News, site_tags, PromptTemplate from utils.website_fetcher import WebsiteFetcher from utils.tag_generator import TagGenerator +from utils.news_searcher import NewsSearcher def create_app(config_name='default'): """应用工厂函数""" @@ -115,6 +116,70 @@ def create_app(config_name='default'): site.view_count += 1 db.session.commit() + # 智能新闻更新：检查今天是否已更新过新闻 + from datetime import date + today = date.today() + + # 检查该网站最新一条新闻的创建时间 + latest_news = News.query.filter_by( + site_id=site.id + ).order_by(News.created_at.desc()).first() + + # 判断是否需要更新新闻 + need_update = False + if not latest_news: + # 没有任何新闻，需要获取 + need_update = True + elif latest_news.created_at.date() < today: + # 最新新闻不是今天创建的，需要更新 + need_update = True + + # 如果需要更新，自动获取最新新闻 + if need_update: + api_key = app.config.get('BOCHA_API_KEY') + if api_key: + try: + # 创建新闻搜索器 + searcher = NewsSearcher(api_key) + + # 获取新闻（限制3条，一周内的） + news_items = searcher.search_site_news( + site_name=site.name, + site_url=site.url, + count=3, + freshness='oneWeek' + ) + + # 保存新闻到数据库 + if news_items: + for item in news_items: + # 检查是否已存在（根据URL去重） + existing = News.query.filter_by( + site_id=site.id, + url=item['url'] + ).first() + + if not existing: + news = News( + site_id=site.id, + title=item['title'], + content=item.get('summary') or item.get('snippet', ''), + url=item['url'], + source_name=item.get('site_name', ''), + source_icon=item.get('site_icon', ''), + published_at=item.get('published_at'), + news_type='Search Result', + is_active=True + ) + db.session.add(news) + + db.session.commit() + + except Exception as e: + # 获取新闻失败，不影响页面显示 + print(f"自动获取新闻失败：{str(e)}") + db.session.rollback() + # 获取该网站的相关新闻（最多显示5条） news_list = News.query.filter_by( site_id=site.id, @@ -442,6 +507,205 @@ def create_app(config_name='default'): 'message': f'生成失败: {str(e)}' }), 500 + # ========== 新闻获取路由 ========== + @app.route('/api/fetch-site-news', methods=['POST']) + @login_required + def fetch_site_news(): + """为指定网站获取最新新闻""" + try: + data = request.get_json() + site_id = data.get('site_id') + count = data.get('count', app.config.get('NEWS_SEARCH_COUNT', 10)) + freshness = data.get('freshness', app.config.get('NEWS_SEARCH_FRESHNESS', 'oneMonth')) + + if not site_id: + return jsonify({ + 'success': False, + 'message': '请提供网站ID' + }), 400 + + # 获取网站信息 + site = Site.query.get(site_id) + if not site: + return jsonify({ + 'success': False, + 'message': '网站不存在' + }), 404 + + # 检查博查API配置 + api_key = app.config.get('BOCHA_API_KEY') + if not api_key: + return jsonify({ + 'success': False, + 'message': '博查API未配置，请在.env文件中设置BOCHA_API_KEY' + }), 500 + + # 创建新闻搜索器 + searcher = NewsSearcher(api_key) + + # 搜索新闻 + news_items = searcher.search_site_news( + site_name=site.name, + site_url=site.url, + count=count, + freshness=freshness + ) + + if not news_items: + return jsonify({ + 'success': False, + 'message': '未找到相关新闻' + }), 404 + + # 保存新闻到数据库 + saved_count = 0 + for item in news_items: + # 检查新闻是否已存在（根据URL判断） + existing_news = News.query.filter_by( + site_id=site_id, + url=item['url'] + ).first() + + if not existing_news: + # 创建新闻记录 + news = News( + site_id=site_id, + title=item['title'], + content=item.get('summary') or item.get('snippet', ''), + url=item['url'], + source_name=item.get('site_name', ''), + source_icon=item.get('site_icon', ''), + published_at=item.get('published_at'), + news_type='Search Result', + is_active=True + ) + db.session.add(news) + saved_count += 1 + + # 提交事务 + db.session.commit() + + return jsonify({ + 'success': True, + 'message': f'成功获取并保存 {saved_count} 条新闻', + 'total_found': len(news_items), + 'saved': saved_count, + 'news_items': searcher.format_news_for_display(news_items) + }) + + except Exception as e: + db.session.rollback() + return jsonify({ + 'success': False, + 'message': f'获取失败: {str(e)}' + }), 500 + + @app.route('/api/fetch-all-news', methods=['POST']) + @login_required + def fetch_all_news(): + """批量为所有网站获取新闻""" + try: + data = request.get_json() + count_per_site = data.get('count', 5) # 每个网站获取的新闻数量 + freshness = data.get('freshness', app.config.get('NEWS_SEARCH_FRESHNESS', 'oneMonth')) + limit = data.get('limit', 10) # 限制处理的网站数量 + + # 检查博查API配置 + api_key = app.config.get('BOCHA_API_KEY') + if not api_key: + return jsonify({ + 'success': False, + 'message': '博查API未配置，请在.env文件中设置BOCHA_API_KEY' + }), 500 + + # 获取启用的网站（按更新时间排序，优先处理旧的） + sites = Site.query.filter_by(is_active=True).order_by(Site.updated_at).limit(limit).all() + + if not sites: + return jsonify({ + 'success': False, + 'message': '没有可用的网站' + }), 404 + + # 创建新闻搜索器 + searcher = NewsSearcher(api_key) + + # 统计信息 + total_saved = 0 + total_found = 0 + processed_sites = [] + + # 为每个网站获取新闻 + for site in sites: + try: + # 搜索新闻 + news_items = searcher.search_site_news( + site_name=site.name, + site_url=site.url, + count=count_per_site, + freshness=freshness + ) + + site_saved = 0 + for item in news_items: + # 检查是否已存在 + existing_news = News.query.filter_by( + site_id=site.id, + url=item['url'] + ).first() + + if not existing_news: + news = News( + site_id=site.id, + title=item['title'], + content=item.get('summary') or item.get('snippet', ''), + url=item['url'], + source_name=item.get('site_name', ''), + source_icon=item.get('site_icon', ''), + published_at=item.get('published_at'), + news_type='Search Result', + is_active=True + ) + db.session.add(news) + site_saved += 1 + + total_found += len(news_items) + total_saved += site_saved + + processed_sites.append({ + 'id': site.id, + 'name': site.name, + 'found': len(news_items), + 'saved': site_saved + }) + + except Exception as e: + # 单个网站失败不影响其他网站 + processed_sites.append({ + 'id': site.id, + 'name': site.name, + 'error': str(e) + }) + continue + + # 提交事务 + db.session.commit() + + return jsonify({ + 'success': True, + 'message': f'批量获取完成，共处理 {len(processed_sites)} 个网站', + 'total_found': total_found, + 'total_saved': total_saved, + 'processed_sites': processed_sites + }) + + except Exception as e: + db.session.rollback() + return jsonify({ + 'success': False, + 'message': f'批量获取失败: {str(e)}' + }), 500 + # ========== 批量导入路由 ========== @app.route('/admin/batch-import', methods=['GET', 'POST']) @login_required @@ -908,9 +1172,9 @@ def create_app(config_name='default'): # 显示操作列 column_display_actions = True - column_list = ['id', 'site', 'title', 'news_type', 'published_at', 'is_active'] - column_searchable_list = ['title', 'content'] - column_filters = ['site', 'news_type', 'is_active', 'published_at'] + column_list = ['id', 'site', 'title', 'source_name', 'news_type', 'published_at', 'is_active'] + column_searchable_list = ['title', 'content', 'source_name'] + column_filters = ['site', 'news_type', 'source_name', 'is_active', 'published_at'] column_labels = { 'id': 'ID', 'site': '关联网站', @@ -918,16 +1182,19 @@ def create_app(config_name='default'): 'content': '新闻内容', 'news_type': '新闻类型', 'url': '新闻链接', + 'source_name': '来源网站', + 'source_icon': '来源图标', 'published_at': '发布时间', 'is_active': '是否启用', 'created_at': '创建时间', 'updated_at': '更新时间' } - form_columns = ['site', 'title', 'content', 'news_type', 'url', 'published_at', 'is_active'] + form_columns = ['site', 'title', 'content', 'news_type', 'url', 'source_name', 'source_icon', 'published_at', 'is_active'] # 可选的新闻类型 form_choices = { 'news_type': [ + ('Search Result', 'Search Result'), ('Product Update', 'Product Update'), ('Industry News', 'Industry News'), ('Company News', 'Company News'), @@ -935,6 +1202,9 @@ def create_app(config_name='default'): ] } + # 默认排序 + column_default_sort = ('published_at', True) # 按发布时间倒序排列 + # Prompt模板管理视图 class PromptAdmin(SecureModelView): can_edit = True diff --git a/config.py b/config.py index a604c05..d50f3f8 100644 --- a/config.py +++ b/config.py @@ -41,6 +41,20 @@ class Config: UPLOAD_FOLDER = 'static/uploads' MAX_CONTENT_LENGTH = 5 * 1024 * 1024 # 5MB ALLOWED_EXTENSIONS = {'png', 'jpg', 'jpeg', 'gif', 'webp'} + + # DeepSeek API配置 + DEEPSEEK_API_KEY = os.environ.get('DEEPSEEK_API_KEY') + DEEPSEEK_BASE_URL = os.environ.get('DEEPSEEK_BASE_URL') or 'https://api.deepseek.com' + + # 博查 Web Search API配置 + BOCHA_API_KEY = os.environ.get('BOCHA_API_KEY') + BOCHA_BASE_URL = os.environ.get('BOCHA_BASE_URL') or 'https://api.bocha.cn' + BOCHA_SEARCH_ENDPOINT = '/v1/web-search' + + # 新闻搜索配置 + NEWS_SEARCH_COUNT = 10 # 每次搜索返回的新闻数量 + NEWS_SEARCH_FRESHNESS = 'oneMonth' # 默认搜索一个月内的新闻 + NEWS_SEARCH_SUMMARY = True # 是否显示摘要 class DevelopmentConfig(Config): """开发环境配置""" diff --git a/fetch_news_cron.py b/fetch_news_cron.py new file mode 100644 index 0000000..9e6b092 --- /dev/null +++ b/fetch_news_cron.py @@ -0,0 +1,167 @@ +""" +定期新闻获取任务脚本 +用途：定期为网站批量获取最新新闻 +使用：python fetch_news_cron.py [options] + +可以通过crontab定时执行： +# 每天早上8点执行，获取10个网站的新闻 +0 8 * * * cd /path/to/zjpb && /path/to/venv/bin/python fetch_news_cron.py --limit 10 >> logs/news_fetch.log 2>&1 +""" +import os +import sys +import argparse +from datetime import datetime +from dotenv import load_dotenv + +# 加载环境变量 +load_dotenv() + +# 添加项目根目录到Python路径 +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) + +from app import create_app +from models import db, Site, News +from utils.news_searcher import NewsSearcher + + +def fetch_news_for_sites(limit=10, count_per_site=5, freshness='oneMonth'): + """ + 批量为网站获取新闻 + + Args: + limit: 处理的网站数量限制 + count_per_site: 每个网站获取的新闻数量 + freshness: 新闻时间范围 + """ + # 创建Flask应用上下文 + app = create_app(os.getenv('FLASK_ENV', 'production')) + + with app.app_context(): + # 检查博查API配置 + api_key = app.config.get('BOCHA_API_KEY') + if not api_key: + print(f"[{datetime.now()}] 错误：未配置BOCHA_API_KEY") + return False + + # 获取启用的网站（按更新时间排序，优先处理旧的） + sites = Site.query.filter_by(is_active=True).order_by(Site.updated_at).limit(limit).all() + + if not sites: + print(f"[{datetime.now()}] 没有可处理的网站") + return False + + print(f"[{datetime.now()}] 开始批量获取新闻，共 {len(sites)} 个网站") + print(f"配置：每个网站 {count_per_site} 条新闻，时间范围：{freshness}") + print("-" * 60) + + # 创建新闻搜索器 + searcher = NewsSearcher(api_key) + + # 统计信息 + total_saved = 0 + total_found = 0 + success_count = 0 + error_count = 0 + + # 为每个网站获取新闻 + for i, site in enumerate(sites, 1): + print(f"[{i}/{len(sites)}] 处理网站: {site.name}") + + try: + # 搜索新闻 + news_items = searcher.search_site_news( + site_name=site.name, + site_url=site.url, + count=count_per_site, + freshness=freshness + ) + + if not news_items: + print(f" └─ 未找到新闻") + continue + + site_saved = 0 + for item in news_items: + # 检查是否已存在 + existing_news = News.query.filter_by( + site_id=site.id, + url=item['url'] + ).first() + + if not existing_news: + news = News( + site_id=site.id, + title=item['title'], + content=item.get('summary') or item.get('snippet', ''), + url=item['url'], + source_name=item.get('site_name', ''), + source_icon=item.get('site_icon', ''), + published_at=item.get('published_at'), + news_type='Search Result', + is_active=True + ) + db.session.add(news) + site_saved += 1 + + # 提交该网站的新闻 + db.session.commit() + + total_found += len(news_items) + total_saved += site_saved + success_count += 1 + + print(f" └─ 找到 {len(news_items)} 条，保存 {site_saved} 条新闻") + + except Exception as e: + error_count += 1 + print(f" └─ 错误: {str(e)}") + db.session.rollback() + continue + + print("-" * 60) + print(f"[{datetime.now()}] 批量获取完成") + print(f"成功: {success_count} 个网站, 失败: {error_count} 个网站") + print(f"共找到 {total_found} 条新闻，保存 {total_saved} 条新新闻") + print("=" * 60) + + return True + + +def main(): + """主函数""" + parser = argparse.ArgumentParser(description='定期新闻获取任务') + parser.add_argument('--limit', type=int, default=10, help='处理的网站数量限制（默认：10）') + parser.add_argument('--count', type=int, default=5, help='每个网站获取的新闻数量（默认：5）') + parser.add_argument('--freshness', type=str, default='oneMonth', + choices=['noLimit', 'oneDay', 'oneWeek', 'oneMonth', 'oneYear'], + help='新闻时间范围（默认：oneMonth）') + + args = parser.parse_args() + + print("=" * 60) + print(f"定期新闻获取任务 - 开始时间: {datetime.now()}") + print("=" * 60) + + try: + success = fetch_news_for_sites( + limit=args.limit, + count_per_site=args.count, + freshness=args.freshness + ) + + if success: + print(f"\n任务执行成功！") + sys.exit(0) + else: + print(f"\n任务执行失败！") + sys.exit(1) + + except Exception as e: + print(f"\n[{datetime.now()}] 严重错误: {str(e)}") + import traceback + traceback.print_exc() + sys.exit(1) + + +if __name__ == '__main__': + main() diff --git a/manage.sh b/manage.sh index 51cf1e9..d541b14 100644 --- a/manage.sh +++ b/manage.sh @@ -4,7 +4,7 @@ # 用法: ./manage.sh [start|stop|restart|status|logs] APP_NAME="zjpb" -APP_DIR="/www/wwwroot/zjpb" +APP_DIR="/opt/1panel/apps/zjpb" VENV_DIR="$APP_DIR/venv" PID_FILE="$APP_DIR/logs/gunicorn.pid" @@ -14,7 +14,7 @@ case "$1" in start) echo "启动 $APP_NAME..." source $VENV_DIR/bin/activate - gunicorn -c gunicorn_config.py app:app + gunicorn -c gunicorn_config.py wsgi:app echo "$APP_NAME 已启动" ;; diff --git a/migrate_news_fields.py b/migrate_news_fields.py new file mode 100644 index 0000000..5020516 --- /dev/null +++ b/migrate_news_fields.py @@ -0,0 +1,99 @@ +""" +数据库迁移脚本 - 为News表添加source_name和source_icon字段 +版本：v2.2.0 +日期：2025-01-30 +""" +import pymysql +import os +from dotenv import load_dotenv + +# 加载环境变量 +load_dotenv() + +def migrate(): + """执行数据库迁移""" + # 数据库配置 + db_config = { + 'host': os.environ.get('DB_HOST', 'localhost'), + 'port': int(os.environ.get('DB_PORT', 3306)), + 'user': os.environ.get('DB_USER', 'root'), + 'password': os.environ.get('DB_PASSWORD', ''), + 'database': os.environ.get('DB_NAME', 'ai_nav'), + 'charset': 'utf8mb4' + } + + try: + # 连接数据库 + connection = pymysql.connect(**db_config) + cursor = connection.cursor() + + print("=" * 60) + print("开始执行数据库迁移 v2.2.0") + print("=" * 60) + + # 检查字段是否已存在 + cursor.execute(""" + SELECT COLUMN_NAME + FROM INFORMATION_SCHEMA.COLUMNS + WHERE TABLE_SCHEMA = %s + AND TABLE_NAME = 'news' + AND COLUMN_NAME IN ('source_name', 'source_icon') + """, (db_config['database'],)) + + existing_columns = [row[0] for row in cursor.fetchall()] + + # 添加 source_name 字段 + if 'source_name' not in existing_columns: + print("\n1. 添加 source_name 字段...") + cursor.execute(""" + ALTER TABLE news + ADD COLUMN source_name VARCHAR(100) + COMMENT '新闻来源网站名称' + AFTER url + """) + print(">>> source_name 字段添加成功") + else: + print("\n1. source_name 字段已存在，跳过") + + # 添加 source_icon 字段 + if 'source_icon' not in existing_columns: + print("\n2. 添加 source_icon 字段...") + cursor.execute(""" + ALTER TABLE news + ADD COLUMN source_icon VARCHAR(500) + COMMENT '新闻来源网站图标URL' + AFTER source_name + """) + print(">>> source_icon 字段添加成功") + else: + print("\n2. source_icon 字段已存在，跳过") + + # 提交事务 + connection.commit() + + print("\n" + "=" * 60) + print(">>> 数据库迁移完成！") + print("=" * 60) + + # 显示表结构 + print("\n当前 news 表结构：") + cursor.execute("DESCRIBE news") + for row in cursor.fetchall(): + print(f" - {row[0]}: {row[1]} {row[2]}") + + except Exception as e: + print(f"\n>>> 迁移失败：{str(e)}") + if 'connection' in locals(): + connection.rollback() + raise + + finally: + if 'cursor' in locals(): + cursor.close() + if 'connection' in locals(): + connection.close() + print("\n数据库连接已关闭") + + +if __name__ == '__main__': + migrate() diff --git a/models.py b/models.py index fae1c97..8f6ba00 100644 --- a/models.py +++ b/models.py @@ -90,6 +90,8 @@ class News(db.Model): content = db.Column(db.Text, comment='新闻内容') news_type = db.Column(db.String(50), default='Industry News', comment='新闻类型') url = db.Column(db.String(500), comment='新闻链接') + source_name = db.Column(db.String(100), comment='新闻来源网站名称') + source_icon = db.Column(db.String(500), comment='新闻来源网站图标URL') published_at = db.Column(db.DateTime, default=datetime.now, comment='发布时间') is_active = db.Column(db.Boolean, default=True, comment='是否启用') created_at = db.Column(db.DateTime, default=datetime.now, comment='创建时间') diff --git a/templates/admin/master.html b/templates/admin/master.html index e499e4a..47ca379 100644 --- a/templates/admin/master.html +++ b/templates/admin/master.html @@ -85,6 +85,12 @@ 批量导入 +
  • + + lock_reset + 修改密码 + +
  • open_in_new diff --git a/templates/admin_login.html b/templates/admin_login.html index 5c57f62..6500337 100644 --- a/templates/admin_login.html +++ b/templates/admin_login.html @@ -1,67 +1,97 @@ -{% extends "base.html" %} + + + + + + 管理员登录 - ZJPB 焦提示词 -{% block title %}管理员登录 - ZJPB 焦提示词{% endblock %} + + + + -{% block extra_css %} - -{% endblock %} + + -{% block content %} - - - - + + + + + +
    -
    -
    +
    +
    - -
    + +
    arrow_back
    返回首页     -
    +
    -
    +
    -
    +
    shield_person
    - System Access + System Access
    -

    管理员登录

    -

    输入您的登录凭据以访问后台管理系统

    +

    管理员登录

    +

    输入您的登录凭据以访问后台管理系统

    {% with messages = get_flashed_messages(with_categories=true) %} {% if messages %} {% for category, message in messages %} -
    - error -

    {{ message }}

    +
    + error +

    {{ message }}

    {% endfor %} {% endif %} @@ -71,16 +101,16 @@
    - +
    - -
    +
    person
    @@ -88,34 +118,56 @@
    - +
    + +
    - -
    +
    lock
    +
    - -
    -

    +

    +

    ZJPB - 焦提示词 管理系统

    + + -{% endblock %} + diff --git a/templates/detail_new.html b/templates/detail_new.html index c84192f..b6ac54b 100644 --- a/templates/detail_new.html +++ b/templates/detail_new.html @@ -628,15 +628,51 @@ {% for news in news_list %}
    - {{ news.news_type }} -

    {{ news.title }}

    -

    {{ news.content[:200] }}...

    -
    {{ news.published_at.strftime('%b %d, %Y') }}
    +
    + {{ news.news_type }} + {% if news.source_name %} +
    + {% if news.source_icon %} + {{ news.source_name }} + {% endif %} + {{ news.source_name }} +
    + {% endif %} +
    +

    + {% if news.url %} + + {{ news.title }} + + {% else %} + {{ news.title }} + {% endif %} +

    + {% if news.content %} +

    {{ news.content[:200] }}{% if news.content|length > 200 %}...{% endif %}

    + {% endif %} +
    +
    + {% if news.published_at %} + {{ news.published_at.strftime('%Y年%m月%d日') }} + {% else %} + 未知日期 + {% endif %} +
    + {% if news.url %} + + 阅读全文 ↗ + + {% endif %} +
    {% endfor %}
    {% endif %} +
    + +
    {% if recommended_sites %}
    @@ -644,35 +680,22 @@ ✨ 相似推荐 -
    - {% for rec_site in recommended_sites %} - - {% if rec_site.logo %} - - {% else %} - - {% endif %} -
    -

    {{ rec_site.name }}

    -

    {{ rec_site.short_desc or rec_site.description }}

    -
    - {% for tag in rec_site.tags[:2] %} - {{ tag.name }} - {% endfor %} -
    -
    - ↗ -     - {% endfor %} -
    + {% for rec_site in recommended_sites %} + + {% if rec_site.logo %} + {{ rec_site.name }} + {% else %} +
    + {% endif %} +
    +

    {{ rec_site.name }}

    +

    {{ rec_site.short_desc or rec_site.description }}

    +
    +     + {% endfor %}
    {% endif %}
    - - -
    - -
    {% endblock %} diff --git a/templates/index_new.html b/templates/index_new.html index 79f208a..1a6fa31 100644 --- a/templates/index_new.html +++ b/templates/index_new.html @@ -41,6 +41,7 @@ display: flex; gap: 8px; flex-wrap: wrap; + position: relative; } .category-tab { @@ -58,6 +59,74 @@ gap: 8px; } + .category-tab .tag-count { + display: inline-flex; + align-items: center; + justify-content: center; + min-width: 20px; + height: 20px; + padding: 0 6px; + background: rgba(100, 116, 139, 0.1); + color: var(--text-secondary); + font-size: 12px; + font-weight: 600; + border-radius: 10px; + transition: all 0.2s; + } + + .category-tab.active .tag-count { + background: rgba(255, 255, 255, 0.25); + color: white; + } + + .category-tab:hover .tag-count { + background: rgba(59, 130, 246, 0.15); + color: var(--primary-blue); + } + + .category-tab.active:hover .tag-count { + background: rgba(255, 255, 255, 0.35); + color: white; + } + + .category-tab.hidden-tag { + display: none; + } + + .category-tab.show-all .hidden-tag { + display: inline-flex; + } + + .more-tags-btn { + padding: 10px 20px; + border: 1px solid var(--border-color); + border-radius: 50px; + background: var(--bg-white); + color: var(--primary-blue); + font-size: 14px; + font-weight: 500; + cursor: pointer; + transition: all 0.2s; + display: inline-flex; + align-items: center; + gap: 8px; + user-select: none; + } + + .more-tags-btn:hover { + border-color: var(--primary-blue); + background: rgba(59, 130, 246, 0.05); + } + + .more-tags-btn .expand-icon { + font-size: 14px; + transition: transform 0.2s; + } + + .more-tags-btn.expanded .expand-icon { + transform: rotate(180deg); + } + .category-tab:hover { border-color: var(--primary-blue); color: var(--primary-blue); @@ -69,8 +138,8 @@ color: white; } - .category-tab .material-symbols-outlined { - font-size: 18px; + .category-tab .icon { + font-size: 16px; } /* 工具网格 */ @@ -187,10 +256,6 @@ white-space: nowrap; } - .tool-views .material-symbols-outlined { - font-size: 16px; - } - /* 分页 */ .pagination { display: flex; @@ -243,7 +308,7 @@ padding: 80px 20px; } - .empty-state .material-symbols-outlined { + .empty-state .icon { font-size: 64px; color: var(--text-muted); margin-bottom: 16px; @@ -286,25 +351,32 @@
    - visibility + 👁 {% if site.view_count >= 1000 %}{{ (site.view_count / 1000) | round(1) }}k{% else %}{{ site.view_count | default(0) }}{% endif %}
    @@ -354,11 +426,11 @@ {% if pagination.has_prev %} - chevron_left + ◀ {% else %} - chevron_left + ◀ {% endif %} @@ -391,22 +463,52 @@ {% if pagination.has_next %} - chevron_right + ▶ {% else %} - chevron_right + ▶ {% endif %}
    {% endif %} {% else %}
    - search_off + 🔍

    暂无工具

    {% if selected_tag %}该分类下还没有工具{% else %}还没有添加任何工具{% endif %}

    {% endif %}
    + + {% endblock %} diff --git a/test_news_feature.py b/test_news_feature.py new file mode 100644 index 0000000..3ac30e3 --- /dev/null +++ b/test_news_feature.py @@ -0,0 +1,142 @@ +""" +测试v2.2新闻功能 - 完整流程测试 +""" +import os +import sys +from dotenv import load_dotenv + +# 加载环境变量 +load_dotenv() + +# 添加项目路径 +sys.path.insert(0, os.path.dirname(os.path.abspath(__file__))) + +from app import create_app +from models import db, Site, News +from utils.news_searcher import NewsSearcher + +def test_news_feature(): + """测试新闻功能""" + print("=" * 60) + print("v2.2 新闻功能测试") + print("=" * 60) + + # 创建应用上下文 + app = create_app('development') + + with app.app_context(): + # 1. 测试API配置 + print("\n[1/4] 检查API配置...") + api_key = app.config.get('BOCHA_API_KEY') + if not api_key: + print(">>> 错误：BOCHA_API_KEY未配置") + return False + print(f">>> API Key: {api_key[:20]}...") + + # 2. 测试数据库连接 + print("\n[2/4] 检查数据库...") + try: + site_count = Site.query.filter_by(is_active=True).count() + print(f">>> 找到 {site_count} 个启用的网站") + + if site_count == 0: + print(">>> 警告：没有可用的网站") + return False + + except Exception as e: + print(f">>> 数据库错误：{e}") + return False + + # 3. 测试新闻搜索 + print("\n[3/4] 测试新闻搜索...") + searcher = NewsSearcher(api_key) + + # 获取第一个网站 + site = Site.query.filter_by(is_active=True).first() + print(f">>> 测试网站：{site.name}") + + try: + news_items = searcher.search_site_news( + site_name=site.name, + site_url=site.url, + count=3, + freshness='oneWeek' + ) + + print(f">>> 找到 {len(news_items)} 条新闻") + + if news_items: + print("\n新闻列表：") + for i, item in enumerate(news_items, 1): + print(f" {i}. {item['title'][:50]}...") + print(f" 来源：{item.get('site_name', '未知')}") + print(f" URL：{item['url'][:60]}...") + + except Exception as e: + print(f">>> 搜索失败：{e}") + return False + + # 4. 测试保存到数据库 + print(f"\n[4/4] 测试保存到数据库...") + + if not news_items: + print(">>> 没有新闻可保存") + return True + + try: + saved_count = 0 + for item in news_items[:2]: # 只保存前2条作为测试 + # 检查是否已存在 + existing = News.query.filter_by( + site_id=site.id, + url=item['url'] + ).first() + + if not existing: + news = News( + site_id=site.id, + title=item['title'], + content=item.get('summary') or item.get('snippet', ''), + url=item['url'], + source_name=item.get('site_name', ''), + source_icon=item.get('site_icon', ''), + published_at=item.get('published_at'), + news_type='Search Result', + is_active=True + ) + db.session.add(news) + saved_count += 1 + + db.session.commit() + print(f">>> 成功保存 {saved_count} 条新闻") + + # 验证保存 + total_news = News.query.filter_by(site_id=site.id).count() + print(f">>> 该网站共有 {total_news} 条新闻记录") + + except Exception as e: + db.session.rollback() + print(f">>> 保存失败：{e}") + return False + + print("\n" + "=" * 60) + print(">>> 所有测试通过！") + print("=" * 60) + + # 提供下一步建议 + print("\n下一步操作：") + print(f"1. 访问网站详情页查看新闻：http://localhost:5000/site/{site.code}") + print(f"2. 访问后台新闻管理：http://localhost:5000/admin/newsadmin/") + print(f"3. 运行定期任务脚本：python fetch_news_cron.py --limit 5") + + return True + +if __name__ == '__main__': + try: + success = test_news_feature() + sys.exit(0 if success else 1) + except Exception as e: + print(f"\n严重错误：{e}") + import traceback + traceback.print_exc() + sys.exit(1) diff --git a/utils/news_searcher.py b/utils/news_searcher.py new file mode 100644 index 0000000..cfced90 --- /dev/null +++ b/utils/news_searcher.py @@ -0,0 +1,271 @@ +""" +新闻搜索工具 - 使用博查 Web Search API +""" +import requests +import json +from datetime import datetime +from typing import List, Dict, Optional + + +class NewsSearcher: + """博查新闻搜索器""" + + def __init__(self, api_key: str, base_url: str = 'https://api.bocha.cn'): + """ + 初始化新闻搜索器 + + Args: + api_key: 博查API密钥 + base_url: API基础URL + """ + self.api_key = api_key + self.base_url = base_url + self.endpoint = f"{base_url}/v1/web-search" + + def search_news( + self, + query: str, + count: int = 10, + freshness: str = 'oneMonth', + summary: bool = True, + include: Optional[str] = None, + exclude: Optional[str] = None + ) -> Dict: + """ + 搜索新闻 + + Args: + query: 搜索关键词 + count: 返回结果数量（1-50） + freshness: 时间范围（noLimit/oneDay/oneWeek/oneMonth/oneYear） + summary: 是否显示摘要 + include: 指定搜索的网站范围（多个域名用|或,分隔） + exclude: 排除搜索的网站范围（多个域名用|或,分隔） + + Returns: + 搜索结果字典 + """ + headers = { + 'Authorization': f'Bearer {self.api_key}', + 'Content-Type': 'application/json' + } + + payload = { + 'query': query, + 'count': count, + 'freshness': freshness, + 'summary': summary + } + + # 添加可选参数 + if include: + payload['include'] = include + if exclude: + payload['exclude'] = exclude + + try: + response = requests.post( + self.endpoint, + headers=headers, + data=json.dumps(payload), + timeout=30 + ) + response.raise_for_status() + return response.json() + + except requests.exceptions.RequestException as e: + return { + 'success': False, + 'error': str(e), + 'code': getattr(response, 'status_code', None) if 'response' in locals() else None + } + + def parse_news_items(self, search_result: Dict) -> List[Dict]: + """ + 解析搜索结果为新闻列表 + + Args: + search_result: 博查API返回的搜索结果 + + Returns: + 新闻列表，每个新闻包含：title, url, snippet, summary, site_name, published_at等 + """ + news_items = [] + + # 检查返回数据格式 + if 'data' not in search_result: + return news_items + + data = search_result['data'] + if 'webPages' not in data or 'value' not in data['webPages']: + return news_items + + # 解析每条新闻 + for item in data['webPages']['value']: + news_item = { + 'title': item.get('name', ''), + 'url': item.get('url', ''), + 'snippet': item.get('snippet', ''), + 'summary': item.get('summary', ''), + 'site_name': item.get('siteName', ''), + 'site_icon': item.get('siteIcon', ''), + 'published_at': self._parse_date(item.get('datePublished')), + 'display_url': item.get('displayUrl', ''), + 'language': item.get('language', ''), + } + news_items.append(news_item) + + return news_items + + def search_site_news( + self, + site_name: str, + site_url: Optional[str] = None, + count: int = 10, + freshness: str = 'oneMonth' + ) -> List[Dict]: + """ + 搜索特定网站的相关新闻 + + Args: + site_name: 网站名称（用于搜索关键词） + site_url: 网站URL（可选，用于排除网站自身） + count: 返回结果数量 + freshness: 时间范围 + + Returns: + 新闻列表 + """ + # 构建搜索关键词：网站名称 + "最新" + "新闻" + query = f'"{site_name}" 新闻' + + # 如果提供了网站URL，排除网站自身的结果 + exclude = None + if site_url: + # 提取域名 + try: + from urllib.parse import urlparse + parsed = urlparse(site_url) + domain = parsed.netloc or parsed.path + # 移除 www. 前缀 + domain = domain.replace('www.', '') + exclude = domain + except Exception: + pass + + # 执行搜索 + search_result = self.search_news( + query=query, + count=count, + freshness=freshness, + summary=True, + exclude=exclude + ) + + # 解析结果 + return self.parse_news_items(search_result) + + def _parse_date(self, date_str: Optional[str]) -> Optional[datetime]: + """ + 解析日期字符串 + + Args: + date_str: 日期字符串（例如：2025-02-23T08:18:30+08:00） + + Returns: + datetime对象，如果解析失败返回None + """ + if not date_str: + return None + + try: + # 尝试解析 ISO 8601 格式 + # 博查API返回格式：2025-02-23T08:18:30+08:00 + if '+' in date_str or 'Z' in date_str: + # 使用 fromisoformat（Python 3.7+） + return datetime.fromisoformat(date_str.replace('Z', '+00:00')) + else: + # 简单格式 + return datetime.strptime(date_str, '%Y-%m-%dT%H:%M:%S') + except Exception: + # 如果解析失败，返回None + return None + + def format_news_for_display(self, news_items: List[Dict]) -> List[Dict]: + """ + 格式化新闻用于前端展示 + + Args: + news_items: 新闻列表 + + Returns: + 格式化后的新闻列表 + """ + formatted_news = [] + + for item in news_items: + formatted_item = { + 'title': item['title'], + 'url': item['url'], + 'description': item.get('summary') or item.get('snippet', ''), + 'source': item.get('site_name', '未知来源'), + 'published_date': self._format_date(item.get('published_at')), + 'icon': item.get('site_icon', '') + } + formatted_news.append(formatted_item) + + return formatted_news + + def _format_date(self, dt: Optional[datetime]) -> str: + """ + 格式化日期用于显示 + + Args: + dt: datetime对象 + + Returns: + 格式化的日期字符串 + """ + if not dt: + return '未知日期' + + try: + # 返回格式：2025-01-30 + return dt.strftime('%Y-%m-%d') + except Exception: + return '未知日期' + + +# 测试代码 +if __name__ == '__main__': + import os + from dotenv import load_dotenv + + load_dotenv() + + # 从环境变量获取API密钥 + api_key = os.environ.get('BOCHA_API_KEY') + if not api_key: + print("错误：未设置BOCHA_API_KEY环境变量") + exit(1) + + # 创建搜索器 + searcher = NewsSearcher(api_key) + + # 测试搜索 + print("正在搜索：ChatGPT 最新新闻...") + news_items = searcher.search_site_news( + site_name='ChatGPT', + count=5, + freshness='oneWeek' + ) + + # 显示结果 + print(f"\n找到 {len(news_items)} 条新闻：\n") + for i, news in enumerate(news_items, 1): + print(f"{i}. {news['title']}") + print(f" 来源：{news['site_name']}") + print(f" 日期：{searcher._format_date(news['published_at'])}") + print(f" URL：{news['url']}") + print(f" 摘要：{news.get('summary', news.get('snippet', ''))[:100]}...") + print()