电影天堂信息爬取

最新推荐文章于 2023-06-23 05:07:36 发布

silencknight

最新推荐文章于 2023-06-23 05:07:36 发布

阅读量540

点赞数

文章标签：电影天堂

本文链接：https://blog.csdn.net/silencekinght/article/details/81865189

版权

import requests
import re, os, time


def dytt(num):
    for page in range(1,num+1):
        url = 'http://www.dytt8.net/html/gndy/dyzz/list_23_%d.html' % page
        print(url)
        response = requests.get(url)
        # print(response.text)
        pattern = '<a href="(.*)" class="ulink"'
        res_list = re.findall(pattern, response.text)
        # print(res_list)
        path = 'dytt_download/'
        pattern2 = '"magnet.*?"'
        pattern3 = 'style="WORD-WRAP: break-word".*?href="(.*?)">'
        pattern4 = '<title>(.*)</'
        for item in res_list:
            try:
                url = 'http://www.dytt8.net%s' % item
                response = requests.get(url)
                magnet = re.search(pattern2, response.text).group(0)
                print(magnet)
                th_url = re.search(pattern3, response.content.decode('gbk')).group(1)
                print(th_url)
                title = re.search(pattern4, response.content.decode('gbk')).group(1)
                print(title)
                doc_path = path + '/' + item.split('/')[-1]
                if not os.path.exists(doc_path):
                    os.mkdir(doc_path)
                with open(doc_path + '/' + 'magnet.txt', 'w') as f:
                    f.write(magnet)
                with open(doc_path + '/' + item.split('/')[-1] + '.torrent', 'w') as f:
                    f.write(th_url)
                time.sleep(2)
            except:
                print(url)


if __name__ == '__main__':
    num = 3
    dytt(num)