Python编程
搜索
分类

python 爬取影视网站下载链接

作者：GriffinLewis2001 时间：2022-07-30 00:59:42　

项目地址：

https://github.com/GriffinLewis2001/Python_movie_links_scraper

运行效果

python 爬取影视网站下载链接

python 爬取影视网站下载链接

导入模块


import requests,re
from requests.cookies import RequestsCookieJar
from fake_useragent import UserAgent
import os,pickle,threading,time
import concurrent.futures
from goto import with_goto

爬虫主代码


def get_content_url_name(url):
   send_headers = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
   "Connection": "keep-alive",
   "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
   "Accept-Language": "zh-CN,zh;q=0.8"

}
   cookie_jar = RequestsCookieJar()
   cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
   response=requests.get(url,send_headers,cookies=cookie_jar)
   response.encoding='utf-8'
   content=response.text
   reg=re.compile(r'<a href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="thumbnail-img" title="(.*?)"')
   url_name_list=reg.findall(content)
   return url_name_list

def get_content(url):
   send_headers = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
   "Connection": "keep-alive",
   "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
   "Accept-Language": "zh-CN,zh;q=0.8"

}
   cookie_jar = RequestsCookieJar()
   cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
   response=requests.get(url,send_headers,cookies=cookie_jar)
   response.encoding='utf-8'
   return response.text

def search_durl(url):
   content=get_content(url)
   reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
   index=reg.findall(content)[0]
   download_url=url[:-5]+r'/downloadList?decriptParam='+index
   content=get_content(download_url)
   reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow" ')
   download_list=reg1.findall(content)
   return download_list
def get_page(url):
   send_headers = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
   "Connection": "keep-alive",
   "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
   "Accept-Language": "zh-CN,zh;q=0.8"

}
   cookie_jar = RequestsCookieJar()
   cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
   response=requests.get(url,send_headers,cookies=cookie_jar)
   response.encoding='utf-8'
   content=response.text
   reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  title="(.*?)">(.*?)<\/a>')
   url_name_list=reg.findall(content)
   return url_name_list
@with_goto
def main():

print("=========================================================")
   name=input("请输入剧名(输入quit退出):")
   if name == "quit":
       exit()
   url="http://www.yikedy.co/search?query="+name
   dlist=get_page(url)
   print("\n")
   if(dlist):
       num=0
       count=0
       for i in dlist:
           if (name in i[1]) :
               print(f"{num} {i[1]}")
               num+=1
           elif num==0 and count==len(dlist)-1:
               goto .end
           count+=1
       dest=int(input("\n\n请输入剧的编号(输100跳过此次搜寻):"))
       if dest == 100:
           goto .end
       x=0
       print("\n以下为下载链接:\n")
       for i in dlist:
           if (name in i[1]):
               if(x==dest):
                   for durl in search_durl(i[0]):
                       print(f"{durl}\n")

print("\n")

break
               x+=1

else:
       label .end
       print("没找到或不想看\n")

完整代码


import requests,re
from requests.cookies import RequestsCookieJar
from fake_useragent import UserAgent
import os,pickle,threading,time
import concurrent.futures
from goto import with_goto

def get_content_url_name(url):
   send_headers = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
   "Connection": "keep-alive",
   "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
   "Accept-Language": "zh-CN,zh;q=0.8"

}
   cookie_jar = RequestsCookieJar()
   cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
   response=requests.get(url,send_headers,cookies=cookie_jar)
   response.encoding='utf-8'
   content=response.text
   reg=re.compile(r'<a href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  class="thumbnail-img" title="(.*?)"')
   url_name_list=reg.findall(content)
   return url_name_list

def get_content(url):
   send_headers = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
   "Connection": "keep-alive",
   "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
   "Accept-Language": "zh-CN,zh;q=0.8"

}
   cookie_jar = RequestsCookieJar()
   cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
   response=requests.get(url,send_headers,cookies=cookie_jar)
   response.encoding='utf-8'
   return response.text

def search_durl(url):
   content=get_content(url)
   reg=re.compile(r"{'\\x64\\x65\\x63\\x72\\x69\\x70\\x74\\x50\\x61\\x72\\x61\\x6d':'(.*?)'}")
   index=reg.findall(content)[0]
   download_url=url[:-5]+r'/downloadList?decriptParam='+index
   content=get_content(download_url)
   reg1=re.compile(r'title=".*?" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow" ')
   download_list=reg1.findall(content)
   return download_list
def get_page(url):
   send_headers = {
    "User-Agent":"Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36",
   "Connection": "keep-alive",
   "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
   "Accept-Language": "zh-CN,zh;q=0.8"

}
   cookie_jar = RequestsCookieJar()
   cookie_jar.set("mttp", "9740fe449238", domain="www.yikedy.co")
   response=requests.get(url,send_headers,cookies=cookie_jar)
   response.encoding='utf-8'
   content=response.text
   reg=re.compile(r'<a target="_blank" class="title" href="(.*?)" rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  rel="external nofollow"  title="(.*?)">(.*?)<\/a>')
   url_name_list=reg.findall(content)
   return url_name_list
@with_goto
def main():

print("=========================================================")
   name=input("请输入剧名(输入quit退出):")
   if name == "quit":
       exit()
   url="http://www.yikedy.co/search?query="+name
   dlist=get_page(url)
   print("\n")
   if(dlist):
       num=0
       count=0
       for i in dlist:
           if (name in i[1]) :
               print(f"{num} {i[1]}")
               num+=1
           elif num==0 and count==len(dlist)-1:
               goto .end
           count+=1
       dest=int(input("\n\n请输入剧的编号(输100跳过此次搜寻):"))
       if dest == 100:
           goto .end
       x=0
       print("\n以下为下载链接:\n")
       for i in dlist:
           if (name in i[1]):
               if(x==dest):
                   for durl in search_durl(i[0]):
                       print(f"{durl}\n")

print("\n")

break
               x+=1

else:
       label .end
       print("没找到或不想看\n")

print("本软件由CLY.所有\n\n")
while(True):
   main()

来源：https://github.com/GriffinLewis2001/Python_movie_links_scraper

标签：python,爬虫,下载链接,影视网站
0
投稿

猜你喜欢

  • 教你一步步利用python实现贪吃蛇游戏

    2023-09-21 13:23:27

  • Javascript(es2016) import和require用法和区别详解

    2024-04-19 09:57:04

  • FrontPage 2002应用技巧四则

    2008-08-17 10:57:00

  • PyCharm导入python项目并配置虚拟环境的教程详解

    2023-08-18 13:31:41

  • 如何利用Vue3管理系统实现动态路由和动态侧边菜单栏

    2024-05-05 09:25:34

  • Pycharm安装scrapy及初始化爬虫项目的完整步骤

    2023-04-03 10:49:43

  • ASP实例:幻灯片新闻代码

    2008-11-21 17:40:00

  • 制作Python数字华容道的实现(可选择关卡)

    2022-12-20 19:32:18

  • 快速掌握 Mysql数据库对文件操作的封装

    2009-02-23 17:37:00

  • WEB页面工具之语言XML的定义

    2008-05-29 11:29:00

  • jsp+ajax实现无刷新上传文件的方法

    2024-04-17 10:39:30

  • Python 加密与解密小结

    2021-04-28 00:35:47

  • python 微信好友特征数据分析及可视化

    2021-09-10 15:45:20

  • python实现文件快照加密保护的方法

    2022-08-21 20:01:29

  • Linux下安装PHP MSSQL扩展教程

    2024-03-11 10:41:47

  • 一条SQL语句修改多表多字段的信息的具体实现

    2024-01-18 13:22:56

  • Python利用openpyxl库遍历Sheet的实例

    2023-10-20 20:19:01

  • pyqt5 QScrollArea设置在自定义侧(任何位置)

    2023-05-22 09:33:51

  • 初学vue出现空格警告的原因及其解决方案

    2024-05-09 09:51:40

  • CentOS 6、7下mysql 5.7 详细安装教程

    2024-01-24 18:00:47
    • asp之家 网络编程 m.aspxhome.com