趣直播网

image.png

里面很多免费的视频,因为习惯了看技术视频按2倍速度看,所以就下载下来看

#coding=utf-8
import re,urllib2,urllib,json,time,os

def getHtmlCode(url):
    request = urllib2.Request(url)
    request.add_header('X-Session','xxx')
    response = urllib2.urlopen(request,timeout=30)
    return response.read()

def getVideo():
    for i in range(1,10000):
        print 'id---' + str(i)
        url = 'http://m.quzhiboapp.com/api/lives/' + str(i)
        htmlCode = getHtmlCode(url)
        decodeJson = json.loads(htmlCode)
        result = decodeJson["result"]

        subject = ''
        beginTs = ''
        videoUrl = ''
        coursewareUrl = ''

        if result.has_key('subject'):
            subject = result["subject"]
        if result.has_key('beginTs'):
            beginTs = result["beginTs"]
        if result.has_key('videoUrl'):
            videoUrl = result["videoUrl"]
        if result.has_key('coursewareUrl'):
            coursewareUrl = result["coursewareUrl"]

        if len(beginTs) > 10:
            timesArray = beginTs.split('-')
            time = timesArray[0] + timesArray[1] + timesArray[2][0:2]
            fileName = time + subject

        if len(fileName) > 25:
            fileName = fileName[0:25]

        fileName = fileName + '(' + str(i) + ')'

        try:
            if len(videoUrl) > 1:
                if os.path.isfile('download/' + fileName + '.mp4') == False:
                    print fileName
                    print(videoUrl)
                    urllib.urlretrieve(videoUrl,"%s.mp4" %("download/" + fileName))
                    print (fileName + '---video---done')
            if len(coursewareUrl) > 1:
                urllib.urlretrieve(coursewareUrl,"%s.pdf" %("download/" + fileName))
                print (fileName + '---pdf---done')
        except:
            print (fileName + '---error')

getVideo()

然后免费的视频都下载下来了(看代码也看到服务器是验证X-session的,就是一个固定的sessionToken)

image.png