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

Init code

Browse Source
This commit is contained in:
yuangyaa
2025-08-12 17:14:10 +08:00
parent 130999364f
commit baea50bfa0
2 changed files with 15 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
core/management/commands/crawl_cngov.py
View File

@@ -17,4 +17,4 @@ class Command(BaseCommand):
start_url = "https://www.gov.cn/"
self.stdout.write(f"开始全站爬取: {start_url}")
full_site_crawler(start_url, website, max_pages=500)
self.stdout.write("爬取完成")
self.stdout.write("爬取完成")

28
core/utils.py
View File

@@ -95,11 +95,11 @@ def process_article(url, website):
title_tag = soup.find("h1") or soup.find("title")
# 查找主要内容区域，通常在.mainBody或content中
content_tag = (
soup.find("div", class_="pages_content") or
soup.find("div", class_="article_con") or
soup.find("div", class_="content") or
soup.find("div", id="content") or
soup.find("div", class_="mainBody")
soup.find("div", class_="pages_content") or
soup.find("div", class_="article_con") or
soup.find("div", class_="content") or
soup.find("div", id="content") or
soup.find("div", class_="mainBody")
)
else:
# 默认处理方式
@@ -205,14 +205,14 @@ def full_site_crawler(start_url, website, max_pages=1000):
parsed_url = urlparse(url)
path = parsed_url.path
is_article_page = (
soup.find("div", class_="pages_content") is not None or
soup.find("div", class_="article_con") is not None or
soup.find("div", class_="content") is not None or
soup.find("div", id="content") is not None or
soup.find("div", class_="mainBody") is not None or
("/zhengce/" in path) or
("/xinwen/" in path) or
("/huoban/" in path)
soup.find("div", class_="pages_content") is not None or
soup.find("div", class_="article_con") is not None or
soup.find("div", class_="content") is not None or
soup.find("div", id="content") is not None or
soup.find("div", class_="mainBody") is not None or
("/zhengce/" in path) or
("/xinwen/" in path) or
("/huoban/" in path)
)
else:
# 默认判断逻辑
@@ -230,4 +230,4 @@ def full_site_crawler(start_url, website, max_pages=1000):
for link in soup.find_all("a", href=True):
href = urljoin(url, link["href"])
if href not in visited and is_valid_url(href, base_netloc):
queue.append(href)
queue.append(href)