Day 01

import requests
def get_page(url):
    response = requests.get(url)
    return response

import re
def parse_index(html):
    detail_urls = re.findall('<li><a title="第.*?href="(.*?)"',html,re.S)
    for detail_url in detail_urls:
        print(detail_url)
    return detail_urls

def parse_detail(html):
    movie_url = re.findall('<iframe id.*?src="(.*?)"',html,re.S)
    if movie_url:
        return movie_url[0]

import uuid
def save_video(content):
    with open(f'{uuid.uuid4()}.mp4','wb') as f:
        f.write(content)
        print('视频下载完毕')


if __name__ == '__main__':
    url = 'https://www.biepa.net/'

    response = get_page(url)

    detail_urls = parse_index(response.text)

    for detail_url in detail_urls:
        # print(detail_url)
        detail_res = get_page(detail_url)
        movie_url = parse_detail(detail_res.text)
        if movie_url:
            print(movie_url)
            movie_res = get_page(movie_url)
            save_video(movie_res.content)