nanan/green_classroom
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix fzrb bug : add support catch fzrb

Browse Source
This commit is contained in:
yuangyaa
2025-08-15 02:38:14 +08:00
parent 83d1b21686
commit d64bf93988
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
core/utils.py
View File

@@ -618,7 +618,7 @@ def process_article(url, website):
soup.find("div", class_="article-body") soup.find("div", class_="article-body")
) )
# 如果找到content-two，需要进一步处理去除内部的标题 # 如果找到content-two，需要进一步处理去除内部的标题元素（避免重复）
if content_tag and content_tag.get('class') and 'content-two' in content_tag.get('class', []): if content_tag and content_tag.get('class') and 'content-two' in content_tag.get('class', []):
# 查找并移除内容中的标题元素（避免重复） # 查找并移除内容中的标题元素（避免重复）
inner_titles = content_tag.find_all(['h1', 'h2']) inner_titles = content_tag.find_all(['h1', 'h2'])
@@ -1205,6 +1205,7 @@ def full_site_crawler(start_url, website, max_pages=1000):
soup.find("div", class_="main-content") is not None or soup.find("div", class_="main-content") is not None or
soup.find("div", class_="article") is not None or soup.find("div", class_="article") is not None or
soup.find("div", class_="article-body") is not None or soup.find("div", class_="article-body") is not None or
("/content/" in path and "content_" in path) or # 法治日报特有的文章URL模式
("/article/" in path) or ("/article/" in path) or
("/content/" in path) or ("/content/" in path) or
(path.startswith("/detail/") and len(path) > 10) (path.startswith("/detail/") and len(path) > 10)