1.爬取糗百段子

python学习笔记

声明：学习笔记主要是根据廖雪峰官方网站python学习学习及博客

---

#糗百提取一页内容

# -*- coding=utf-8 -*-

import urllib

import urllib2

import re

import sys

reload(sys)

sys.setdefaultencoding('utf8')

page =1

url ='https://www.qiushibaike.com/hot/page/1/'

user_agent ='Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.84 Safari/537.36'

headers = {'User-Agent' : user_agent }

try:

request = urllib2.Request(url,headers = headers)

response = urllib2.urlopen(request)

content=  response.read().decode("utf-8")

items = re.findall(r'\n+\s+(.*?)\s+\n+',content,re.S)

#'\n\n+(.*?)\n\n+'

    for itemin items:

if '
' in item:

new_each = re.sub(r'
','\n',item)

print(new_each)

# 没有就照常输出

        else:

print(item)

except urllib2.URLError, e:

if hasattr(e,"code"):

print e.code

if hasattr(e,"reason"):

print e.reason