python 爬取影视网站下载链接

更新时间：2021年05月28日 10:58:51 作者：GriffinLewis2001

一个简单的爬取影视网站下载链接的爬虫，非常适合新手学习，感兴趣的朋友可以参考下

项目地址：

https://github.com/GriffinLewis2001/Python_movie_links_scraper

运行效果

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()

以上就是python 爬取影视网站下载链接的详细内容，更多关于python 爬取下载链接的资料请关注脚本之家其它相关文章！

您可能感兴趣的文章:

使用apidocJs快速生成在线文档的实例讲解
下面小编就为大家分享一篇使用apidocJs快速生成在线文档的实例讲解，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧
2018-02-02
Python实现PS图像抽象画风效果的方法
这篇文章主要介绍了Python实现PS图像抽象画风效果的方法,涉及Python基于skimage模块进行图像处理的相关操作技巧,需要的朋友可以参考下
2018-01-01
用python实现超强的加密软件
大家好，本篇文章主要讲的是用python实现超强的加密软件，感兴趣的同学赶快来看一看吧，对你有帮助的话记得收藏一下，方便下次浏览
2022-01-01
python3的一个天坑问题及解决方法:报错UnicodeDecodeError: ‘utf-8‘
在调试程序发现python3的一个天坑问题:报错UnicodeDecodeError: ‘utf-8‘ codec can‘t decode byte 0xa3 in position 59: invalid,特此曝光,为众位开发朋友提个醒
2023-09-09
Scipy稀疏矩阵bsr_array的使用
本文主要介绍了Scipy稀疏矩阵bsr_array的使用，文中通过示例代码介绍的非常详细，对大家的学习或者工作具有一定的参考学习价值，需要的朋友们下面随着小编来一起学习学习吧
2023-02-02
Python中切片的详细操作篇
在Python中切片(slice)是对序列型对象(如list, string, tuple)的一种高级索引方法,下面这篇文章主要给大家介绍了关于Python中切片操作的相关资料,文中通过实例代码介绍的非常详细,需要的朋友可以参考下
2022-08-08
python venv和virtualenv模块详解
venv 是 Python 内置标准库中创建轻量级虚拟环境的工具,本文通过示例代码介绍python venv和virtualenv的相关知识,感兴趣的朋友跟随小编一起看看吧
2024-08-08
使用Python的Tornado框架实现一个Web端图书展示页面
Tornado是Python的一款高人气Web开发框架,这里我们来展示使用Python的Tornado框架实现一个Web端图书展示页面的实例,通过该实例可以清楚地学习到Tornado的模板使用及整个Web程序的执行流程.
2016-07-07
python3处理含有中文的url方法
今天小编就为大家分享一篇python3处理含有中文的url方法，具有很好的参考价值，希望对大家有所帮助。一起跟随小编过来看看吧
2018-05-05
基于Pytorch实现分类器的示例详解
这篇文章主要为大家详细介绍了如何基于Pytorch实现两个分类器: softmax分类器和感知机分类器，文中的示例代码讲解详细，需要的可以参考一下
2023-04-04

python 爬取影视网站下载链接

目录

项目地址：

运行效果

导入模块

爬虫主代码

完整代码

相关文章

最新评论

大家感兴趣的内容

最近更新的内容

常用在线小工具