开始免费使用
当前位置：首页 > Python > Python实现影视网站资源链接抓取工具

Python实现影视网站资源链接抓取工具

拾柒
拾柒
发布时间：2026-10-14| 5人浏览过
原创

本文介绍使用Python编写的影视网站资源抓取工具，通过requests和re模块解析网页结构，结合多线程与并发处理提升效率。代码包含自定义请求头、Cookie管理及正则提取逻辑，支持批量获取指定影视内容的下载链接，适合对Python爬虫感兴趣的用户参考学习。

项目源码托管地址如下所示：

https://github.com/GriffinLewis2001/Python_movie_links_scraper

程序运行效果展示

所需依赖模块导入


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

核心爬虫逻辑代码


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")

完整可运行代码


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()

以上是关于使用Python从影视网站抓取下载链接的详细教程，如需了解更多Python相关资源，请持续关注本站后续更新的文章。

相关文章

相关标签: Python 爬虫 Python爬虫

免责声明：本文内容仅供参考，不代表本站观点。转载或引用请注明出处。

作者最新文章

全部文章

Python 相关产品和应用

全部下载
PythonSelenium
Selenium

Selenium

4.51.0 · Windows

用于浏览器自动化和 Web 测试的 Python 工具。

Python机器学习
scikit-learn

scikit-learn

1.9.1 · Windows

常用 Python 机器学习算法与模型评估工具库。

Python代码质量
Black

Black

26.10.1 · Windows

强调一致性的 Python 自动代码格式化工具。

Python代码质量
Ruff

Ruff

0.17.1 · macOS

由 Rust 编写的高速 Python 代码检查和格式化工具。

Pythonpytest
pytest

pytest

9.1.1 · Windows

简洁而强大的 Python 自动化测试框架。

PythonFastAPI
FastAPI

FastAPI

0.146.0 · Windows

高性能 Python API 框架，支持类型提示和自动接口文档。

PythonFlask
Flask

Flask

3.1.3 · Windows

轻量灵活的 Python Web 应用框架。

PythonDjango
Django

Django

6.1.2 · Windows

成熟的 Python Web 框架，适合构建内容站点和业务系统。

PythonSpyder
Spyder

Spyder

6.1.7 · Windows

面向科学计算与数据分析的 Python 集成开发环境。

PythonSciPy
SciPy

SciPy

1.18.1 · Windows

面向科学、工程和技术计算的 Python 算法库。