本来晚上是准备写贴吧爬虫的，但是在分析页面时就遇到了大麻烦！选取了某个帖子，在爬取的时候，发现正则匹配不全..很尴尬！！先来看看吧，

1 #!/usr/bin/env python 2 # -*- coding:utf-8 -*- 3 __author__ = 'ziv·chan' 4  5  6 import requests 7 import re 8  9 url = 'http://tieba.baidu.com/p/3138733512?see_lz=1&pn=3'10 html = requests.get(url)11 html.encoding = 'utf-8'12 pageCode = html.text13 14 pattern = re.compile('d_post_content j_d_post_content ">(.*?)
',re.S)15 items = re.findall(pattern,pageCode)16 i = 117 for item in items:18     hasImg = re.search('
     

')23 item = re.sub(pattern_1,'',item)24 # 过滤href25 if hasHref:26 pattern_2 = re.compile('οnclick="Stats.sendRequest.*?class="at">(.*?)',re.S)27 item = re.findall(pattern_2,item)28 29 print str(i) + ':'30 # 提取href标签下的用户31 if type(item) is list:32 for each in item:33 print each34 else:35 # 过滤多余标签 '

'36 pattern_Br = re.compile('

')37 item = re.sub(pattern_Br, '\n', item)38 # 默认删除空白符39 print item.strip()40 print '\n'41 i += 142 # if not hasImg and not hasHref:43 # print i44 # print item.strip()45 # i += 1