基于python2的豆瓣Top250爬虫练习

 1 # coding=utf-8
 2 import urllib
 3 import re
 4 #获取源码
 5 def gethtml(pg):
 6     url = ‘https://movie.douban.com/top250?start=%d&filter=‘ % pg
 7     html = urllib.urlopen(url).read()
 8     return html
 9 
10 #爬取数据
11 if __name__ == ‘__main__‘:
12     pat = re.compile(‘<em class="">(.*?)</em>.*?<a href="(.*?)">.*?<img.*?alt="(.*?)" src="(.*?)".*?>‘,re.S)
13     for i in range(0,226,25):
14         html = gethtml(i)
15         listnum = re.findall(pat,html) #findall返回的是一个tuple
16         for i in range(25):
17             for j in range(4):
18                 print listnum[i][j]