Python 爬虫实例（13）下载 m3u8 格式视频

Python requests 下载 m3u8 格式视频

最近爬取一个视频网站，遇到 m3u8 格式的视频需要下载。

抓包分析，视频文件是多个 ts 文件，什么是 ts文件，请去百度吧：

附图：抓包分析过程

直接把 ts文件请求下来，然后合并 ts文件，如果想把 ts文件转换 MP4 格式，请自行百度吧。

完整下载代码：

#coding=utf-8
import requests
import re
import time
from bs4 import BeautifulSoup
import os


session = requests.session()

def spider():
    url = 'http://xueyuan.91yunxiao.com/videoLesson/play/4028e4115fc893fb015fecfc56240b66.html'
    headers = {

        "Host":"xueyuan.91yunxiao.com",
        "Connection":"keep-alive",
        "Upgrade-Insecure-Requests":"1",
        "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36",
        "Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
        "Referer":"http://xueyuan.91yunxiao.com/videoLesson/detail/4028e4115fc893fb015fecfafe200b63.html",
        "Accept-Encoding":"gzip, deflate",
        "Accept-Language":"zh-CN,zh;q=0.9",
        "Cookie":"UM_distinctid=163cae8de9816e-0d08a36800162a-454c092b-ff000-163cae8de99141; _qddaz=QD.n4xqjl.egbt1i.ji0ex7zv; pgv_pvi=6411171840; SERVERID=s50; JSESSIONID=5D1C6375394E84E931FBD1C774876563; CNZZDATA1261509255=2100416221-1528114457-%7C1528207774",

    }

    try:
        result = session.get(url=url,headers=headers).content

    except:
        result = session.get(url=url,headers=headers).content

    result_replace = str(result).replace('\n','')
    print result_replace
    item_url = re.findall('<source type="application/x-mpegURL" src="(.*?)" />',result_replace)[0].replace('1.m3u8','')
    print item_url

    # for page in range(1,11):

    headers2 = {

        "Host":"data.xueyuan.91yunxiao.com",
        "Connection":"keep-alive",
        "User-Agent":"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36",
        "X-Requested-With":"ShockwaveFlash/29.0.0.171",
        "Accept":"*/*",
        "Referer":"http://xueyuan.91yunxiao.com/videoLesson/play/4028e4115fc893fb015fecf8e4d60b61.html",
        "Accept-Encoding":"gzip, deflate",
        "Accept-Language":"zh-CN,zh;q=0.9",
        "Cookie":"UM_distinctid=163cae8de9816e-0d08a36800162a-454c092b-ff000-163cae8de99141; _qddaz=QD.n4xqjl.egbt1i.ji0ex7zv;
 pgv_pvi=6411171840; SERVERID=s4222",


    }

    for page in range(0,16):

        if page < 10:
            page_str = "0" + str(page)
        else:
            page_str = str(page)

        "http://data.xueyuan.91yunxiao.com/convert/m3u8/2017/11/24/ed/ededf4dc7471a05550cc521196d28ebc/file006.ts"
        item_url1 = item_url + "file0" + str(page_str) + ".ts"
        print item_url1


        dir_path = "E:/1"
        file_name = page_str + ".ts"
        response = session.get(url=item_url1,headers=headers2)

        if response.status_code == 200:
            if not os.path.exists(dir_path):
                os.makedirs(dir_path)
            total_path = dir_path + '/' + file_name
            if len(response.content) == int(response.headers['Content-Length']):
                # print total_path
                with open(total_path, 'wb') as f:
                    for chunk in response.iter_content(1024):
                        f.write(chunk)
                    f.close()







spider()