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

Support CCTV Plamforms

Browse Source
This commit is contained in:
yuangyaa
2025-08-15 01:08:53 +08:00
parent ac98ac0057
commit 89909d2781
5 changed files with 18 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
core/utils.py
View File

@@ -233,8 +233,12 @@ def process_article(url, website):
soup.find("div", id="content") or
soup.find("div", class_="text") or
soup.find("div", class_="main-content") or
soup.find("div", class_="article")
soup.find("div", class_="article") or
# 添加央视新闻特有的内容容器
soup.find("div", class_="content_area") or
soup.find("div", id="content_area")
)
elif "求是" in website.name:
# 求是网站的文章结构处理 - 修复两个标题问题
title_tag = (
@@ -553,7 +557,6 @@ def process_article(url, website):
title_tag = (
soup.find("h1", class_="title") or
soup.find("h1") or
soup.find("p", class_="f_container_title") or # 添加中国妇女报特有标题容器
soup.find("title")
)
content_tag = (
@@ -563,9 +566,7 @@ def process_article(url, website):
soup.find("div", class_="text") or
soup.find("div", class_="main-content") or
soup.find("div", class_="article") or
soup.find("div", class_="article-body") or
soup.find("div", class_="f_container_left") or # 添加中国妇女报特有内容容器
soup.find("div", class_="f_container") # 添加另一种可能的内容容器
soup.find("div", class_="article-body")
)
elif "法治日报" in website.name or "legaldaily" in website.name:
# 法治日报的文章结构处理 - 修复无法爬取问题