电影天堂电影链接爬取

 1 import requests,re
 2 
 3 
 4 def getdetail(url):
 5 
 6     response = requests.get(url)
 7     html = response.content.decode('gbk')
 8     # 电影详情页标题
 9     movie_title_name = re.search('<h1><font color=#07519a>(.*)</f',html)
10     movie_title = movie_title_name.group(1)
11     # 电影 磁力   magnet
12     movie_magnet_url = re.search('/><a href="(.*)"><str',html)
13     # print(movie_magnet.group(1))
14     movie_magnet = movie_magnet_url.group(1)
15     # torrent种子
16     movie_torrent_url = re.search('ddf"><a href="(.*)">ft',html)
17     movie_torrent = movie_torrent_url.group(1)
18     # print(movie_torrent.group(1))
19     # 这个列表用来title
20     movie_title_list = []
21     movie_title_list.append(movie_title)
22 
23     # 这个列表两个下载的链接
24     movie_down_url = []
25     movie_down_url.append(movie_magnet)
26     movie_down_url.append(movie_torrent)
27     movie_down_url_all = []
28     movie_down_url_all.append(movie_down_url)
29 
30 
31     movie_dict = dict(zip(movie_title_list,movie_down_url_all))
32     print(movie_dict)
33 
34 
35 
36 def getpage():
37 
38     for i in range(1,178):
39         lurl = 'http://www.dytt8.net/html/gndy/dyzz/list_23_%s.html' % i
40 
41         response = requests.get(lurl)
42 
43         html = response.text
44 
45         movie_url_list = re.findall('<a href="(.*)" class="ulink"',html)
46 
47         for movie_item in movie_url_list:
48             movie_url = 'http://www.dytt8.net'+movie_item
49             getdetail(movie_url)
50 
51 
52 if __name__ == '__main__':
53     getpage()