优化URL抓取:增加超时时间和备用方案
- 浏览器超时从20秒增加到60秒 - 浏览器失败时使用 requests 备用方案抓取静态内容 - 解决部分网站加载慢导致超时的问题
This commit is contained in:
@@ -224,16 +224,17 @@ class SearchService:
|
||||
return None
|
||||
|
||||
def fetch_url_content(self, url):
|
||||
"""抓取网页内容(使用 agent-browser 浏览器方式,绑过反爬虫)"""
|
||||
"""抓取网页内容(使用 agent-browser 浏览器方式,绕过反爬虫)"""
|
||||
try:
|
||||
# 使用浏览器方式抓取
|
||||
stdout, stderr, code = self._run_browser('open', url, '--timeout', '20000')
|
||||
# 使用浏览器方式抓取,增加超时时间到60秒
|
||||
stdout, stderr, code = self._run_browser('open', url, '--timeout', '60000')
|
||||
if code != 0:
|
||||
print(f"打开页面失败: {stderr}")
|
||||
return None
|
||||
# 浏览器失败,尝试使用 requests 备用方案
|
||||
return self._fetch_with_requests(url)
|
||||
|
||||
# 等待页面加载
|
||||
self._run_browser('wait', '5000')
|
||||
# 等待页面加载(增加到10秒)
|
||||
self._run_browser('wait', '10000')
|
||||
|
||||
# 获取页面标题
|
||||
stdout, stderr, code = self._run_browser('get', 'title', '--timeout', '5000')
|
||||
@@ -309,6 +310,46 @@ class SearchService:
|
||||
|
||||
return result
|
||||
|
||||
def _fetch_with_requests(self, url):
|
||||
"""备用方案:使用 requests 抓取静态内容"""
|
||||
try:
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
|
||||
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
|
||||
'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8'
|
||||
}
|
||||
response = requests.get(url, headers=headers, timeout=30)
|
||||
response.raise_for_status()
|
||||
|
||||
soup = BeautifulSoup(response.text, 'html.parser')
|
||||
|
||||
# 获取标题
|
||||
title = soup.title.string.strip() if soup.title else ''
|
||||
|
||||
# 移除不需要的标签
|
||||
for tag in soup(['script', 'style', 'nav', 'footer', 'header', 'aside']):
|
||||
tag.decompose()
|
||||
|
||||
# 获取主要内容
|
||||
text = soup.get_text(separator='\n', strip=True)
|
||||
# 清理多余空白行
|
||||
lines = [line.strip() for line in text.split('\n') if line.strip()]
|
||||
text = '\n'.join(lines)
|
||||
|
||||
# 提取描述(前200字符)
|
||||
description = text[:200].strip() if text else ''
|
||||
|
||||
return {
|
||||
'title': title,
|
||||
'description': description,
|
||||
'content': text,
|
||||
'url': url,
|
||||
'fetch_date': datetime.now().isoformat()
|
||||
}
|
||||
except Exception as e:
|
||||
print(f"备用抓取失败: {url}, 错误: {str(e)}")
|
||||
return None
|
||||
|
||||
def search_articles(self, keyword, category=None):
|
||||
"""从内容库搜索"""
|
||||
return db.search_articles(keyword, category)
|
||||
|
||||
Reference in New Issue
Block a user