python

关注公众号 jb51net

关闭
首页 > 脚本专栏 > python > Python爬取腾讯视频

Python爬虫小练习之爬取并分析腾讯视频m3u8格式

作者：松鼠爱吃饼干

读万卷书不如行万里路，学的扎不扎实要通过实战才能看出来，本篇文章手把手带你爬下腾讯视频的m3u8格式来分析,大家可以在过程中查缺补漏，看看自己掌握程度怎么样

普通爬虫正常流程:

环境介绍

【付费VIP完整版】只要看了就能学会的教程，80集Python基础入门视频教学

点这里即可免费在线观看

分析网站

先打开开发者工具，然后搜索m3u8，会返回给你很多的ts的文件，像这种ts文件，就是视频的片段

我们可以复制url地址，在新的浏览页打开

然后会给我们下载ts的文件，打开文件，就会发现是十多秒的视频片段

所以说这些数据的数据还是比较好找的，只要我们找到地址是从哪里来的

找到url地址，因为是post请求，所以需要下面的表达参数

开始代码

导入模块

import requests
import re
from tqdm import tqdm # 进度条展示

数据请求

url = 'https://vd.l.qq.com/proxyhttp'
data = {"buid":"vinfoad","adparam":"pf=in&ad_type=LD%7CKB%7CPVL&pf_ex=pc&url=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fj3czmhisqin799r.html&refer=https%3A%2F%2Fv.qq.com%2Fx%2Fsearch%2F&ty=web&plugin=1.0.0&v=3.5.57&coverid=j3czmhisqin799r&vid=z002615k57t&pt=&flowid=e9b3e49b2593efd194cbcd24030ed803_10201&vptag=www_baidu_com%7Cvideo%3Aposter_tle&pu=-1&chid=0&adaptor=2&dtype=1&live=0&resp_type=json&guid=4b4e192e83f4abaf8b68df3e4f5be769&req_type=1&from=0&appversion=1.0.166&uid=522810848&tkn=fbYfeWDCLKtAaOd_OGvCNg..&lt=qq&platform=10201&opid=5FE180427A4C883F69CADDED665CE99B&atkn=49C1A486316C8D269AC65AAC080CFB29&appid=101483052&tpid=1&rfid=86c3f668da63d8bc7aab3fbc1eb7378a_1633763084","vinfoparam":"spsrt=1&charge=0&defaultfmt=auto&otype=ojson&guid=4b4e192e83f4abaf8b68df3e4f5be769&flowid=e9b3e49b2593efd194cbcd24030ed803_10201&platform=10201&sdtfrom=v1010&defnpayver=1&appVer=3.5.57&host=v.qq.com&ehost=https%3A%2F%2Fv.qq.com%2Fx%2Fcover%2Fj3czmhisqin799r.html&refer=v.qq.com&sphttps=1&tm=1633767536&spwm=4&logintoken=%7B%22main_login%22%3A%22qq%22%2C%22openid%22%3A%225FE180427A4C883F69CADDED665CE99B%22%2C%22appid%22%3A%22101483052%22%2C%22access_token%22%3A%2249C1A486316C8D269AC65AAC080CFB29%22%2C%22vuserid%22%3A%22522810848%22%2C%22vusession%22%3A%22fbYfeWDCLKtAaOd_OGvCNg..%22%7D&vid=z002615k57t&defn=fhd&fhdswitch=0&show1080p=1&isHLS=1&dtype=3&sphls=2&spgzip=1&dlver=2&drm=32&hdcp=0&spau=1&spaudio=15&defsrc=2&encryptVer=9.1&cKey=W5agxKnJ7N56KJEItZs_lpJX5WB4a2CdS8kEIo8rVaqtHEZQ1c_W6myJ8hQXnmDDG8ErEJDMLjvm2vPBr-xE-uhvZyEMY131vUh1H4pgCXe2OphM_H32Jqtu2hFoqfA-un0sVBkIXYfWkOdABnbLUo4RgzSXkBHF3N3K7dNKPg_56X9JO3gwBMyBeAex05x8SbbQKY5AXaDVSM7hsBQ8XEeHzIEGJzlCt94ONgPYVSRkZqo51NVr_Bs8h4-UNLT0jG-obbyNs2IJhrZ4JUBeuGEk8zAOhE9HTZPNDViLRIyt2mNDud09qSLLKl4XAj3CE6i26P6BRyAy1_qatijXkm9J1hs3ZYC7dgYmAZD6BE9UGX4hkziTy-Y8cCBppeEBGSaj9w&fp2p=1&spadseg=3"}

headers = {
    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36'
}
response = requests.post(url=url, json=data, headers=headers)

提取数据

html_data = response.json()['vinfo']
# 正则表达式
m3u8_url = re.findall("url(.*?),", html_data)[3].split('"')[2]
m3u8_data = requests.get(url=m3u8_url).text
m3u8_data = re.sub('#EXTM3U', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-VERSION:\d', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-MEDIA-SEQUENCE:\d', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-TARGETDURATION:\d+', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-PLAYLIST-TYPE:VOD', '', m3u8_data)
m3u8_data = re.sub('#EXTINF:\d+\.\d+,', '', m3u8_data)
m3u8_data = re.sub('#EXT-X-ENDLIST', '', m3u8_data).split()

遍历

for ts in tqdm(m3u8_data):
    ts_url = 'https://apd-57c5d150c8b9788baf40ea4f65feddf8.v.smtcdns.com/moviets.tc.qq.com/A2k4JuW9ATia8thdFQ6y5HWRUGLqAr4L5fk9KFbAUEI8/uwMROfz2r5xgoaQXGdGnC2df64gVTKzl5C_X6A3JOVT0QIb-/doVi4hWq0sqexPo_ylKYxVIJdr9zz2VweWbcY7x70kRnbVNPvBaoTsjwfOq1uojOtsRKJ8r3372HRaTOVg4VyKOFFvzjq2EeMdpleIIyTv0tb-C3CzXmkZz-34hK4Fc-r4mZK55L9W1RqJMpsvrORZr_sqpqvGZrrRq830get0NLJGkeAQ9SBg/' + ts
    ts_content = requests.get(url=ts_url).content

保存数据

with open('霸王别姬.mp4', mode='ab') as f:
    f.write(ts_content)
print('下载完成')

运行代码

到此这篇关于Python爬虫小练习之爬取并分析腾讯视频m3u8格式的文章就介绍到这了,更多相关Python爬取腾讯视频内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家！

您可能感兴趣的文章:
阅读全文