爬取糗事百科多页

coding=utf-8

import urllib2
import urllib
import re
i=0
j=0
for j in range(1,5):
print “第%s页”%j
fo=open(“renwu3.txt”,“a”)
url = ‘https://www.qiushibaike.com/8hr/page/’+ str(j) + “/”
user_agent = ‘Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)’
headers = {‘User-Agent’:user_agent}
request = urllib2.Request(url,headers = headers)
response = urllib2.urlopen(request)
content = response.read().decode(‘utf-8’)
content= content.replace("
",",")
content= content.replace("\n",",")
pattern = re.compile(r’

(.?)

.? (.?).? (.*?)’,re.S)
items = re.findall(pattern,content)

for a in items:
    print a[0]
    print a[1]
    print a[2]
    fo.write('发布人：')
    fo.write(a[0].encode('UTF-8')+'\n')
    fo.write('发布内容：')
    fo.write(a[1].encode('UTF-8')+'\n')
    fo.write('点赞数：')
    fo.write(a[2].encode('UTF-8')+'\n\n')
    fo.write('==================================================\n')
    i+=1

fo.close()
学习总结：
掌握了re模块（正则的使用），
python中文件的存储，文件的读取，文件的写入，内容查找和替换。。。（文件的操作）