网页解析三种方法（beautifulsoup）

qq_41611056

于 2018-02-25 14:59:09 发布

阅读量2.5k

点赞数 2

CC 4.0 BY-SA版权

分类专栏： python

本文链接：https://blog.youkuaiyun.com/qq_41611056/article/details/79368889

python 专栏收录该内容

26 篇文章

订阅专栏

# -*- coding:utf-8 -*-
from bs4 import BeautifulSoup
import re//正则
html_doc = '''
<html>
<head>
   <script>
      location.replace(location.href.replace("https://","http://"));
   </script>
</head>
<body>
   <noscript><meta http-equiv="refresh" content="0;url=http://www.baidu.com/"></noscript>
   <a href="https://www.imooc.com/video/10687">happy</a>
   <a href="http://www.baidu.com">baidu</a>
</body>
</html>
'''
soup = BeautifulSoup(html_doc,'html.parser',from_encoding='utf-8')
links = soup.find_all('a')
for link in links:
    print(link.name,link.get_text(),link["href"])
print('特定')
link = soup.find('a',href='http://www.baidu.com')
print(link.name,link.get_text(),link["href"])
print('正则匹配')
link = soup.find('a',href=re.compile(r"moo"))
print(link.name,link.get_text(),link["href"])
print('获取script')
script = soup.find('script')
print(script.name,script.get_text())