下载36氪 播氪的音频

image.png

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

def getHtmlCode(url):
    response = urllib2.urlopen(url)
    return response.read()

def getEntityId(htmlString):
    regEntityId = re.compile("\"(.+?)\",\"goods_id")
    return regEntityId.findall(htmlString)

def getMp3Url(htmlString):
    regMp3Url = re.compile("mp3\",\"url\":\"(.+?).mp3")
    return regMp3Url.findall(htmlString)

def getTitle(htmlString):
    regTitle = re.compile("\"title\":\"(.+?)\"")
    return regTitle.findall(htmlString)

def getPublishTime(htmlString):
    regUpdateTime = re.compile("published_at\":\"(.+?) ")
    return regUpdateTime.findall(htmlString)

if __name__ == '__main__':
    url = 'http://36kr.com/user/947181171'
    htmlCode = getHtmlCode(url)
    entityIds = getEntityId(htmlCode)
    for content in entityIds:
        contentSplitArray = content.split("\"")
        entityId = contentSplitArray[len(contentSplitArray) - 1]
        contentUrl = 'http://36kr.com/p/' + entityId + '.html'
        contentHtmlCode = getHtmlCode(contentUrl)
        mp3Urls = getMp3Url(contentHtmlCode)
        titles = getTitle(contentHtmlCode)
        publishTimes = getPublishTime(contentHtmlCode)
        fileName = publishTimes[0] + ' ' + titles[0]
        # if len(fileName) > 35:
        #     fileName = fileName[0:35]
        print fileName
        mp3Url = mp3Urls[0] + '.mp3'
        print mp3Url
        if os.path.isfile('/Users/wuxueying/Desktop/python/audios/' + fileName + '.mp3') == False:
            urllib.urlretrieve(mp3Url,"%s.mp3" %("audios/" + fileName))
            print (fileName + '------done')