requests处理iframe②

 

之前因为网站被封，

之前的文章

现在补充讲解iframe链接的获取

电影链接：http://www.meiju8.cc/movie/94753.html

请求链接进入该电影的首页，

提取电影播放界面的网址并拼接

 代码如下：

def mv_page(self,url):
        '''
        请求输入的链接，获取电影播放界面的网址
        '''
        res = requests.get(url)
        soup = BeautifulSoup(res.text, "html.parser")
        data = soup.find_all("ul", class_="mn_list_li_movie")[0].find("li")
        mv_url = self.input_url.split("/movie")[0] + data.find("a").get("href")
        return self.iframe(mv_url)

找到iframe链接

通过观察script发现，链接是直接拼接而成

def iframe(self,url):
        '''
        请求播放页链接，获取iframe链接
        '''
        res = requests.get(url,headers=self.headers,verify=False)
        compile = re.compile('"Url":"(?P<url>.*?)","bUrl"',re.S)
        data = compile.search(res.text).group("url")
        iframe_url = "https://jx.fqzy.cc/jx.php?url="+data
        return self.video(iframe_url)

 在请求时遇到问题，

iframe链接需要一些参数：

headers、referer和cookie

加上以上参数后，就能得到m3u8文件地址

 

import requests,re
from bs4 import BeautifulSoup

class MeiJuWang:
    def __init__(self):
        input_url = input("请输入要下载的电影链接：")
        # 为方便测试使用
        # self.input_url = "http://www.meiju8.cc/movie/94753.html"
        self.headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36",
            "cookie": "Hm_lvt_b2b84ee87a8af3f8ad100a3da41c8ad0=1636809421,1636895260,1638451748,1638537010; Hm_lpvt_b2b84ee87a8af3f8ad100a3da41c8ad0=1638537010; Hm_lvt_b5093235610ff1922206ff61ddb2a910=1636807512,1636895261,1638451756,1638537011; Hm_lpvt_b5093235610ff1922206ff61ddb2a910=1638537011; prec=94769%3A2322363%2C94800%3A2322547%2C60215%3A2153100%2C60173%3A2151552%2C60204%3A2152665%2C94789%3A2322520%2C94768%3A2322357%2C94753%3A2321496%2C94654%3A2321560",
            "Referer": "http://www.meiju8.cc/movie/94769.html"
        }
        # 爬虫正式执行
        # self.mv_page(self.input_url)

        ''' 为方便测试用
        url = "https://jx.fqzy.cc/jx.php?url=FQ:a1924f01f35f3e7eaa1f04507beecae2045329abcc180890491dd6a818b492c130b9572cd03424e0ba11a21613f1b64911147986fbb401ac50"
        self.video(url)
        '''
    def video(self,url):
        '''
         请求iframe链接,获取视频地址
        '''
        res = requests.get(url, headers=self.headers,verify=False)
        compile = re.compile('"blob:(?P<url>.*?)"', re.S)
        video_url = compile.search(res.text).group("url")
        return video_url
        # return self.download(video_url)

剩下的就不重复了  ┑(￣Д ￣)┍