Day01 爬虫视频

import time
import  requests
def get_page(url):
    response = requests.get(url)
    return response
import  re
def parse_index(html):
    detail_urls = re.findall(
        '<div class="items"><a class="imglink" href="(.*?)"',html,re.S)
    print(detail_urls)
    return  detail_urls
def parse_detail(html):
    movie_url = re.findall('<source 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。。。请官人观赏！！！')
if __name__ == '__main__':
    for line in range(6):
        url=f'http://www.xiaohuar.com/list-3-{line}.html'
        response = get_page(url)
        detail_urls = parse_index(response.text)
        for detail_url in detail_urls:
            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)

转载于:https://www.cnblogs.com/xtx642/p/11114271.html