【爬虫】爬取猫眼热门电影预告片

import re
import requests
from lxml import etree
from requests.exceptions import RequestException


def get_one_page(url):
    try:
        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36'}
        response = requests.get(url, headers=headers, verify=False)
        if response.status_code == 200:
            return response.text
        return None
    except RequestException:
        return None


def process_movie(html):
    dom = etree.HTML(html)
    movie_urls = dom.xpath('//h4[@class="video-name one-line"]/a[@href]/@href')
    movie_names = dom.xpath('//h4[@class="video-name one-line"]/a/text()')
    for movie_url, movie_name in zip(movie_urls, movie_names):
        movie_id_string = requests.get(movie_url).text
        movie_mp4_url = re.search('source src="(.*)"', movie_id_string).group(1)

        movie_result = requests.get(movie_mp4_url).content

        with open('%s.mp4' % movie_name, 'wb') as f:
            print('正在下载{}'.format(movie_name))
            f.write(movie_result)


def main():
    url = 'https://maoyan.com/news?showTab=3'
    html = get_one_page(url)
    process_movie(html)


if __name__ == '__main__':
    main()