python 百思不得姐视频下载

运用两次正则提取带换行符的网页源代码

import requests
import re


class Budejie():
    def __init__(self):
        self.headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko)"
                                      " Chrome/64.0.3282.186 Safari/537.36"}
        self.spyder = requests.session()

    def get_html(self,url):
        """获取网页源代码"""
        response = self.spyder.get(url, headers=self.headers)
        html = response.text
        self.html = html

    def get_content(self,url):
        response = self.spyder.get(url, headers=self.headers)
        html = response.content
        return html

    def get_mp4(self):
        """下载MP4视频"""
        reg = re.compile(r'(<div class="j-r-list-c">.*?</div>.*?</div>)',re.S)
        content = re.findall(reg, self.html)
        reg = r'data-mp4="(.*?)"'
        movie_address = re.findall(reg, str(content))
        reg = r'data-title="(.*?)"'
        movie_name = re.findall(reg, str(content))
        length = len(movie_name)
        for i in range(0,length):
            self.down_load_mp4(movie_address[i], movie_name[i])
            print("第"+str(i)+"个视频已下载成功")


    def down_load_mp4(self, url, path):
        path = ''.join(path.split())
        path = "C:\\Users\\wwxy\\Desktop\\百思不得姐\\{}.mp4".format(path)
        with open(path,"wb") as f:
            content = self.get_content(url)
            f.write(content)


if __name__ == '__main__':
    url = "http://www.budejie.com/video/"
    spyder = Budejie()
    spyder.get_html(url)
    spyder.get_mp4()