包图网素材视频爬取

import requests
from  lxml import  etree

try:
    page = 1
    start_url = 'https://ibaotu.com/shipin/7-0-0-0-0-{}.html'

    for page in range(1, 223):
        url = start_url.format(page)
        headers = {'UserAgent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.14; rv:66.0) Gecko/20100101 Firefox/66.0'}

        response = requests.get(url, headers=headers).text
        sp = etree.HTML(response)
        data_url = sp.xpath('//div[@class="video-play"]/video/@src')
        data_title = sp.xpath('//span[@class="video-title"]/text()')

        for sc_url,sc_title in zip(data_url,data_title):
            html_url = 'https:'+sc_url
            html_title = sc_title
            # print(html_title,html_url)
            content_  = requests.get(html_url,headers=headers)
            with open('包图网视频素材/{}.mp4'.format(html_title),'wb') as f:
                f.write(content_.content)
                print("正在下载"+html_title)
                print("已完成"+html_title+"下载")










except Exception as error:
    print(error)

转载于:https://www.cnblogs.com/LQ970811/p/10715096.html