python3 获取糗事百科首页的段子

标签：

# -*- coding:utf-8 -*-
import urllib
import urllib.request
import re

page = 1
url = ‘http://www.qiushibaike.com/hot/page/1‘+str(page)
user_agent = ‘Mozilla/4.0 (compatible;MSIE 5.5;Windows NT)‘
headers = { ‘User-Agent‘:user_agent}

try:
request = urllib.request.Request(url,headers = headers)
response = urllib.request.urlopen(request)
content = response.read().decode(‘UTF-8‘)
pattern = re.compile(‘<div.*?author">.*?<a.*?<img.*?>(.*?)</a>.*?<div.*?‘+
‘content">(.*?)<!--(.*?)-->.*?</div>(.*?)<div class="stats.*?class="number">(.*?)</i>‘,re.S)
items = re.findall(pattern,content)
for item in items:
haveImg = re.search("img",item[3])
if not haveImg:
print(item[0],item[1],item[2],item[4])
except urllib.request.URLError :
if hasattr(e,‘code‘):
print(e.code)
if hasattr(e,‘reason‘):
print(e.reason)

python3 获取糗事百科首页的段子

标签：

原文地址：http://www.cnblogs.com/pkmnexp/p/4706019.html