电影/电视剧/综艺/动漫/游戏 下载链接搜索引擎

---

前言

本文介绍如何通过python网络爬虫实现电影/电视剧/综艺/动漫/游戏 下载链接的爬取，用户只需要输入搜索的关键字，选择搜索类型，程序就会返回搜索下载链接的结果，用户可以使用迅雷或者其他的一些下载工具来下载对应的视频。

---

提示：以下是本篇文章正文内容

一、设计思路

1. 首先使用requests模块对电影天堂发起url请求，获得对应的html文本。
2. 使用re与BeautifulSoup对获取到的html进行解析，得到对应的电影信息与下载链接。

二、源码展示

1.自动检测并安装必须的数据库

代码如下（示例）：

import os

try:
    import requests as rq
    from bs4 import BeautifulSoup as BS
    import lxml as lx
except Exception as e:
    print("正在自动安装必须的数据库, 请稍等...")
    info1 = os.popen(cmd="pip install requests -i https://pypi.doubanio.com/simple/").read()
    info2 = os.popen(cmd="pip install bs4 -i https://pypi.doubanio.com/simple/").read()
    info3 = os.popen(cmd="pip install lxml -i https://pypi.doubanio.com/simple/").read()
    print("数据库安装完成!\n\n")
else:
    pass

2.编写对应的函数模块

代码如下（示例）：

1）爬取主界面信息, 返回搜索结果与url地址

def crawl_main_interface(typeid, keyword, pagesize=10000):
    """ 爬取主界面信息, 返回搜索结果与子界面地址 """
    a = time.localtime().tm_year
    b = time.localtime().tm_mon
    if a <= 2 * (10 ** 3) + 21 and b <= 5:
        pass
    else:
        print('\n\tThe tool has expired. Please contact <shusheng.yuan@foxmail.com>.\n')
        input('Click enter to exit!')
        sys.exit()

    global response
    url = "http://s.ygdy8.com/plus/s0.php"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    params = {"typeid": str(typeid), "keyword": str(keyword).encode('gb2312'), "pagesize": str(pagesize)}
    while True:
        """ 解决访问超时失败的问题, 不断的尝试访问 """
        try:
            response = requests.get(url=url, headers=headers, params=params, timeout=3)
        except:
            continue
        else:
            break
    print("\t搜索响应码:", response.status_code)
    response.encoding = 'gb2312'  # Cause:<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
    text_data = response.text
    response.close()  # 停止访问

    soup = BeautifulSoup(text_data, "lxml")
    # print(soup)
    list_info = soup.find_all(name="td", attrs={"width": "55%"})
    # print(list_info)

    list_movie_name = []
    list_sub_url = []
    for info in list_info:
        # print("http://www.ygdy8.com" + info.a["href"], '\t\t', info.a.get_text())
        list_sub_url.append(str("http://www.ygdy8.com" + info.a["href"]))
        list_movie_name.append(info.a.get_text())

    print(f"\t网络世界搜索的条数: {len(list_movie_name)}")
    # print(f"电影子页URL个数: {len(list_sub_url)}")
    return list_movie_name, list_sub_url

2）爬取每个url信息, 返回搜索结果(电影名称+下载地址)

def crawl_sub_interface(sub_url):
    """ 爬取子页信息, 返回搜索结果(电影名称+下载地址) """
    global response
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    while True:
        """ 解决访问超时失败的问题, 不断的尝试访问 """
        try:
            response = requests.get(url=sub_url, headers=headers, timeout=3)
        except:
            continue
        else:
            break
    # print("\t资源响应码:", response.status_code)
    response.encoding = "gb2312"
    sub_text_data = response.text
    response.close()  # 停止访问

    """ 使用正则表达式进行数据提取 """
    list_download = []
    pattern1 = re.compile(r'href="(?P<link1>magnet:.*?)">', re.S)
    pattern2 = re.compile(r'>(?P<link2>ftp://.*?)<', re.S)

    list_link_1 = re.findall(pattern1, str(sub_text_data))
    list_link_2 = re.findall(pattern2, str(sub_text_data))
    # print(f"list_link_1 = {len(list_link_1)}", list_link_1)
    # print(f"list_link_2 = {len(list_link_2)}", list_link_2)

    if len(list_link_1) > 0:
        for link1 in list_link_1:
            list_download.append(str(link1))
    if len(list_link_2) > 0:
        for link2 in list_link_2:
            list_download.append(str(link2))

    return list_download

3）每日推荐一部电影或者电视剧, 返回一部电影信息, 一部电视剧信息

def daily_recommendations():
    """ 每日推荐一部电影或者电视剧, 返回一部电影信息, 一部电视剧信息 """
    global response_movie, response_tv  # 定义全局变量
    url_movie = "https://www.ygdy8.com/html/gndy/dyzz/index.html"
    url_tv = "http://www.ygdy8.com/html/tv/hytv/index.html"
    headers = {
        "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) "
                      "Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0"
    }
    while True:
        """ 解决访问超时失败的问题, 不断的尝试访问 """
        try:
            response_movie = requests.get(url=url_movie, headers=headers, timeout=3)
            response_tv = requests.get(url=url_tv, headers=headers, timeout=3)
        except:
            continue
        else:
            break
    # print("\t电影搜索响应码:", response_movie.status_code)
    # print("\t电视剧搜索响应码:", response_tv.status_code)
    response_movie.encoding = "gb2312"  # Cause:<meta http-equiv="Content-Type" content="text/html; charset=gb2312" />
    response_tv.encoding = "gb2312"
    movie_text = response_movie.text    # 返回电影数据
    movie_tv = response_tv.text         # 返回电视剧数据
    response_movie.close()  # 停止访问
    response_tv.close()     # 停止访问

    """ 解析电影数据 """
    soup_movie = BeautifulSoup(movie_text, "lxml")
    # print(soup_movie)
    movie_info = soup_movie.find("table", {"width":"100%", "border":"0", "cellspacing":"0",
                                           "cellpadding":"0", "class":"tbspan", "style":"margin-top:6px"})
    # print("https://www.ygdy8.com" + movie_info.b.a['href'])
    # print(movie_info.b.a.get_text())
    # print(movie_info.find("td", {"colspan":"2", "style":"padding-left:3px"}).get_text())

    sub_url = "https://www.ygdy8.com" + movie_info.b.a['href']
    while True:
        """ 解决访问超时失败的问题, 不断的尝试访问 """
        try:
            response_sub = requests.get(url=sub_url, headers=headers, timeout=3)
        except:
            continue
        else:
            break
    response_sub.encoding = "gb2312"
    sub_text = response_sub.text  # 返回电影数据
    response_sub.close()

    """ 使用正则表达式进行数据提取 """
    list_download = []
    pattern1 = re.compile(r'href="(?P<link1>magnet:.*?)">', re.S)
    pattern2 = re.compile(r'>(?P<link2>ftp://.*?)<', re.S)

    list_link_1 = re.findall(pattern1, str(sub_text))
    list_link_2 = re.findall(pattern2, str(sub_text))
    # print(f"list_link_1 = {len(list_link_1)}", list_link_1)
    # print(f"list_link_2 = {len(list_link_2)}", list_link_2)

    if len(list_link_1) > 0:
        for link1 in list_link_1:
            list_download.append(str(link1))
    if len(list_link_2) > 0:
        for link2 in list_link_2:
            list_download.append(str(link2))

    movie_name = movie_info.b.a.get_text()
    movie_description = movie_info.find("td", {"colspan":"2", "style":"padding-left:3px"}).get_text()
    # print("电影名称:", movie_name)
    # print("电影简介:", movie_description)
    # print("下载链接地址:", list_download)


    """ 解析电视剧数据 """
    soup_tv = BeautifulSoup(movie_tv, "lxml")
    # print(soup_tv)
    tv_info = soup_tv.find("table", {"width":"100%", "border":"0", "cellspacing":"0",
                                           "cellpadding":"0", "class":"tbspan", "style":"margin-top:6px"})
    tv_sub_url = "https://www.ygdy8.com" + tv_info.b.a['href']
    while True:
        """ 解决访问超时失败的问题, 不断的尝试访问 """
        try:
            response_sub_tv = requests.get(url=tv_sub_url, headers=headers, timeout=3)
        except:
            continue
        else:
            break
    response_sub_tv.encoding = "gb2312"
    sub_tv_text = response_sub_tv.text  # 返回电影数据
    response_sub_tv.close()

    """ 使用正则表达式进行数据提取 """
    list_tv_download = []
    pattern11 = re.compile(r'href="(?P<link11>magnet:.*?)">', re.S)
    pattern22 = re.compile(r'>(?P<link22>ftp://.*?)<', re.S)

    list_link_11 = re.findall(pattern11, str(sub_tv_text))
    list_link_22 = re.findall(pattern22, str(sub_tv_text))
    if len(list_link_11) > 0:
        for link1 in list_link_11:
            list_tv_download.append(str(link1))
    if len(list_link_22) > 0:
        for link2 in list_link_22:
            list_tv_download.append(str(link2))

    tv_name = tv_info.b.a.get_text()
    tv_description = tv_info.find("td", {"colspan":"2", "style":"padding-left:3px"}).get_text()
    # print("TV名称:", tv_name)
    # print("TV简介:", tv_description)
    # print("TV下载链接地址:", list_tv_download)

    return movie_name, movie_description, list_download, tv_name, tv_description, list_tv_download

4）主函数调用上面的函数模块

if __name__ == '__main__':
    Author()
    movie_name, movie_description, list_download, tv_name, tv_description, list_tv_download = daily_recommendations()
    print("-----------------------------------------------------------")
    print("- 每日推荐电影:")
    print(f"- 电影名: {movie_name}")
    print(f"- 电影简介: {movie_description}")
    for link in list_download:
        print(f"- 下载链接: {link}")
    print("-----------------------------------------------------------")
    print("- 每日推荐电视剧:")
    print(f"- 电视剧名: {tv_name}")
    print(f"- 电视剧简介: {tv_description}")
    for link in list_tv_download:
        print(f"- 下载链接: {link}")
    print("-----------------------------------------------------------")
    print('\n')
    while True:
        global typeid  # 定义一个全局变量
        keyword = str(input("请输入您要搜索的关键字:")).strip()
        while True:
            print("************")
            print("* 1: 电影   *")
            print("* 2: 电视剧 *")
            print("* 3: 综艺   *")
            print("* 4: 动漫   *")
            print("* 5: 游戏   *")
            print("************")
            try:
                typeid = int(input("请选择您要搜索的类型(1/2/3/4/5):"))
                if typeid == 3:
                    typeid = 99
                if typeid == 4:
                    typeid = 16
                if typeid == 5:
                    typeid = 19

                if typeid in [1, 2, 99, 16, 19]:
                    pass
                else:
                    7 / 0
            except:
                print("输入错误, 请重试!(1/2/3/4/5)")
                continue
            else:
                break
        print()
        print("\t************************")
        list_movie_name, list_sub_url = crawl_main_interface(typeid=typeid, keyword=keyword)
        print("\t************************")
        if len(list_movie_name) > 0 and len(list_sub_url) > 0:
            i = 1
            for movie_name, sub_url in zip(list_movie_name, list_sub_url):
                print("\t----------------------------------------------------------->")
                print(f"\t第 {i} 个结果")
                print(f"\t搜索名称: {movie_name}")
                list_download = crawl_sub_interface(sub_url=sub_url)
                for download in list_download:
                    print(f"\t下载链接地址:", download)
                i += 1
                # print("\t\t~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
                # print(f"\n\t\t当然, 更多的信息也可访问: {sub_url} --不推荐")
                # print("\t\t~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
            print("\t----------------------------------------------------------->")
        else:
            # print("\n\t对不起, 我没有找到您想要的答案！")
            print("\n\t绕了网络一圈, 啥也没找到~")

        select = str(input("\n\t\t你打算继续搜索不?(y/n):"))
        if select in ["n", "N", "NO", "No", "no"]:
            break
        else:
            print()
            continue

---