【无标题】

Python学习笔记

爬取视频

1.从网页获取视频播放链接
2.使用第三方视频解析网站解析视频地址
3.使用手机抓包软件抓包
4.获取视频下载地址

import requests
import time
from lxml import etree

test_url= "https://mp.weixin.qq.com/s/4oLnJvfGCZneoErkrh0sHw"
headers = {
    'Host': 'mp.weixin.qq.com',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64)AppleWebKit/537.36' '(KHTML, like Gecko) Chrome/96.0.4664.110 Safari/537.36'
}

#视频获取的接口URL
video_parse_url = 'http://v.ranks.xin/video-parse.php'
#视频获取接口的请求头
video_parse_headers = {
    'User-Agent': 'Mozilla/5.0(Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML,like Gecko)',
    'Host': 'v.ranks.xin',
    'Referer': 'http://v.rsnks.xin/',
    'X-Requested-With': 'XMLHttpRequest'
}

#解析获得视频链接
def get_video_url(content):
    video_list = content.xpath("//iframe/@data-src")
    for video in video_list:
        download_video(video)

#下载视频的方法
def download_video(url):
    print("开始解析视频链接："+url)
    video_resp = requests.get(video_parse_url, headers=video_parse_headers,params={'url': url})
    if video_resp is not None:
        video_url = video_resp.json()['data'][0]['url']
        print("解析完成，开始下载视频："+video_url)
        try:
            video_name = str(int(time.time()))+'.mp4'
            video_resp = requests.get(video_url).content
            if video_resp is not None:
                with open(video_name,"wb+") as f:
                    f.write(video_resp)
                    print("视频下载完成："+video_name)
        except Exception as reason:
            print(str(reason))


if __name__ == '__main__':
    resp = requests.get(url=test_url, headers=headers).text
    #print(resp)
    html = etree.HTML(resp)
    get_video_url(html)