fix: extract author_username from <b> tags in postuserinfo div

crawlers/crawl_today.py

@@ -75,7 +75,7 @@ class YichensTodaySpider(PaginationSpider):
         soup = BeautifulSoup(html, "html.parser")
         page_text = soup.get_text()
         
-        match = re.search(r"ID=(\d+)", url)
+        match = re.search(r"\&ID=(\d+)", url)
         post_id = match.group(1) if match else None
         
         title = None
@@ -135,6 +135,18 @@ class YichensTodaySpider(PaginationSpider):
             elif "马钞" in title:
                 category = "马钞"
         
+        # 从 postuserinfo div 的 <b> 标签提取用户名（跳过电话号码）
+        if not author:
+            userinfos = soup.find_all('div', class_='postuserinfo')
+            for ui in userinfos:
+                for b in ui.find_all('b'):
+                    text = b.get_text(strip=True)
+                    if text and not re.match(r'^1\d{10}$', text) and len(text) > 1:
+                        author = text
+                        break
+                if author:
+                    break
+
         return {
             "post_id": post_id,
             "title": title,