Python_爬虫_猫眼电影网电影预告片批量下载

非常简单的一个基础爬虫代码，可以根据不同的url自动下载同一页中的所有预告片

import requests
from lxml import etree
import re

# 1.确定url地址
url = "https://maoyan.com/news?showTab=3&offset=30"

# 1.商品图片 设置ua
ua = {
'User-Agent':'Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:72.0) Gecko/20100101 Firefox/72.0'
}


# 商品图片.请求
result = requests.get(url, headers=ua).text

# 3.筛选数据(xpath, 正则表达式)
dom = etree.HTML(result)
movie_urls = dom.xpath('//h4[@class="video-name one-line"]/a[@href]/@href')
movie_names = dom.xpath('//h4[@class="video-name one-line"]/a[@href]/text()')


for movie_name, movie_url in zip(movie_names, movie_urls):
    # print(movie_name)
    # print(movie_url)
    movie_string = requests.get(movie_url).text

    mp4_urls = re.search('source src="(.*?)"', movie_string).group(1)
    print(mp4_urls)

    mp4 = requests.get(mp4_urls).content

    # 4.保存数据
    with open('./1/%s.mp4' % movie_name, 'wb') as file:
        file.write(mp4)