1 # -*- coding:utf-8 -*-
2 #python 2.7
3 #XiaoDeng
4 #http://tieba.baidu.com/p/2460150866
5 #标签操作
6
7
8 from bs4 import BeautifulSoup
9 import urllib.request
10 import re
11
12
13 #如果是网址，可以用这个办法来读取网页
14 #html_doc = "http://tieba.baidu.com/p/2460150866"
15 #req = urllib.request.Request(html_doc)
16 #webpage = urllib.request.urlopen(req)
17 #html = webpage.read()
18
19
20
21 html="""
22 <html><head><title>The Dormouse's story</title></head>
23 <body>
24 <p class="title" name="dromouse"><b>The Dormouse's story</b></p>
25 <p class="story">Once upon a time there were three little sisters; and their names were
26 <a href="http://example.com/elsie" class="sister" id="xiaodeng"><!-- Elsie --></a>,
27 <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
28 <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
29 <a href="http://example.com/lacie" class="sister" id="xiaodeng">Lacie</a>
30 and they lived at the bottom of a well.</p>
31 <div class="ntopbar_loading"><img src="http://simg.sinajs.cn/blog7style/images/common/loading.gif">加载中…</div>
32
33 <div class="SG_connHead">
34 <span class="title" comp_title="个人资料">个人资料</span>
35 <span class="edit">
36 </span>
37 <div class="info_list">
38 <ul class="info_list1">
39 <li><span class="SG_txtc">博客等级：</span><span id="comp_901_grade"><img src="http://simg.sinajs.cn/blog7style/images/common/sg_trans.gif" real_src="http://simg.sinajs.cn/blog7style/images/common/number/9.gif" /></span></li>
40 <li><span class="SG_txtc">博客积分：</span><span id="comp_901_score"><strong>0</strong></span></li>
41 </ul>
42 <ul class="info_list2">
43 <li><span class="SG_txtc">博客访问：</span><span id="comp_901_pv"><strong>3,971</strong></span></li>
44 <li><span class="SG_txtc">关注人气：</span><span id="comp_901_attention"><strong>0</strong></span></li>
45 <li><span class="SG_txtc">获赠金笔：</span><strong id="comp_901_d_goldpen">0支</strong></li>
46 <li><span class="SG_txtc">赠出金笔：</span><strong id="comp_901_r_goldpen">0支</strong></li>
47 <li class="lisp" id="comp_901_badge"><span class="SG_txtc">荣誉徽章：</span></li>
48 </ul>
49 </div>
50 <div class="atcTit_more"><span class="SG_more"><a href="http://blog.sina.com.cn/" target="_blank">更多>></a></span></div>
51 <p class="story">...</p>
52 """
53 soup = BeautifulSoup(html, 'html.parser') #文档对象
54
55
56
57 # 类名为xxx而且文本内容为hahaha的div
58 for k in soup.find_all('div',class_='atcTit_more'):#,string='更多'
59 print(k)
60 #<div class="atcTit_more"><span class="SG_more"><a href="http://blog.sina.com.cn/" target="_blank">更多>></a></span></div>
