1. 程式人生 > >獲取電影天堂的影視連結

獲取電影天堂的影視連結

import requests
from lxml import etree
import re
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36'
}

# def xiangqingt(url):

# def ugturl():
for i in range(1,4):
    lurl = 'http://www.dytt8.net/html/gndy/dyzz/list_23_%s.html'
% i response = requests.get(lurl,headers=headers) html_ele = response.text # print(html_ele) movie_url_list = re.findall('<a href="(.*)" class="ulink"',html_ele) # print(movie_url_list) for movie_item in movie_url_list: # print(movie_item) movie_url = 'http://www.dytt8.net'
+movie_item # print(movie_url) # xiangqingt(movie_url) response = requests.get(movie_url) htmls = response.content.decode('gbk') # print(htmls) #標題 titlt_name = re.search('<h1><font color=#07519a>(.*)</f',htmls) # print(titlt_name)
movie_title = titlt_name.group(1) # print(movie_title) #磁力 cili_name= re.search('/><a href="(.*)"><str', htmls) # print(cili_name) movie_cili = cili_name.group(1) print(movie_cili) #種子 zhongzi_name = re.search('ddf"><a href="(.*)">ft',htmls) movie_zhongzi = zhongzi_name.group(1) print(movie_zhongzi) list_title = [] list_title.append(movie_title) lianjie_name = [] lianjie_name.append(movie_cili) lianjie_name.append(movie_zhongzi) # print(lianjie_name) lianjie_tite = [] lianjie_tite.append(lianjie_name) # print(lianjie_tite) movie_dict = (zip(list_title,lianjie_tite)) print(movie_dict)