添加富途直播新闻蜘蛛并优化经济学家世界简报

rsshub/blueprints/main.py

@@ -248,6 +248,11 @@ def economist_wordlbrief(category=''):
     from rsshub.spiders.economist.worldbrief import ctx
     return render_template('main/atom.xml', **filter_content(ctx(category)))
 
+@bp.route('/futu/live/<string:lang>')
+def futu_live(lang=''):
+    from rsshub.spiders.futu.live import ctx
+    return render_template('main/atom.xml', **filter_content(ctx(lang)))    
+
 @bp.route('/baidu/suggest/<string:category>')
 def baidu_suggest(category=''):
     from rsshub.spiders.baidu.suggest import ctx

rsshub/spiders/economist/worldbrief.py

@@ -20,10 +20,10 @@ def parse_news(gobbet):
     """
     生成单条 news 的新闻内容，提取标题和正文。
     """   
-    title = gobbet.strip()
+    title = re.sub(r'<[^>]+>', '', gobbet.strip())
     item = {
         'title': title,  
-        'description': title,   # 简单设置正文为描述
+        'description': gobbet,   # 简单设置正文为描述
         'link': f"{domain}/the-world-in-brief?from={title[:30]}"  # 生成链接
     }
     return item
@@ -32,7 +32,7 @@ def ctx(category=''):
     """
     解析 JSON 数据，提取所有brief news的内容。
     """
-    url = f"{domain}/"
+    url = f"{domain}/the-world-in-brief"
     html = fetch(url, headers=DEFAULT_HEADERS).get()
     soup = BeautifulSoup(html, 'html.parser')
     script_tag = soup.find('script', id="__NEXT_DATA__", type="application/json")
@@ -43,15 +43,10 @@ def ctx(category=''):
     # Load JSON content
     data = json.loads(script_tag.string)
 
-    news_list = data.get('props', {}).get('pageProps', {}).get('worldInBrief', {}).get('text', [])[:-2]
-    
-    news_list_new = []
-    for item in news_list:
-        if item['type'] == 'tag' and item['name'] == 'p':  # 确保是段落
-            news_list_new.append(extract_text(item['children']))    
+    news_list = data.get('props', {}).get('pageProps', {}).get('content', {}).get('gobbets', [])
 
     # 使用 parse_gobbet 解析每一条新闻
-    items = [parse_news(news) for news in news_list_new]
+    items = [parse_news(news) for news in news_list]
 
     return {
         'title': 'World Brief - Economist',

rsshub/spiders/futu/live.py

@@ -0,0 +1,49 @@
+import re
+import json
+import requests
+from datetime import datetime
+from rsshub.utils import DEFAULT_HEADERS
+
+domain = 'https://news.futunn.com'
+
+def parse_news(news):
+    title = news.get('content', '') if news.get('title', '')=='' else news.get('title', '')
+
+    content = news.get('content', '')
+    detail_url = news.get('detailUrl', '')
+    time = datetime.utcfromtimestamp(int(news['time'])).strftime('%Y-%m-%dT%H:%M:%SZ')
+
+    item = {
+        'title': title,
+        'description': content,
+        'link': detail_url,
+        'pubDate': time
+    }
+    
+    return item
+
+def ctx(lang=''):
+    """
+    解析 JSON 数据，提取所有live news的内容。
+    """
+    url = f"{domain}/news-site-api/main/get-flash-list?pageSize=50&lang={lang}"
+    response = requests.get(url, headers=DEFAULT_HEADERS)
+    data = response.json()
+
+    # 检查数据是否有效
+    if data['code'] != 0 or not data['data']['data']['news']:
+        return Response("No data available", mimetype='text/plain')
+
+    news_list = data.get('data', {}).get('data', {}).get('news', [])
+    print(news_list)
+
+    # 使用 parse_gobbet 解析每一条新闻
+    items = [parse_news(news) for news in news_list]
+
+    return {
+        'title': 'Futunn Live News',
+        'link': url,
+        'description': 'Futunn Live News',
+        'author': 'hillerliao',
+        'items': items
+    }