自动下载Tumblr某用户所有视频的脚本

python .\TumblrModel.py -u'http://xxx.tumblr.com' 0      --搜集http://xxx.tumblr.com的所有视频，但不将文件保存到本地
python .\TumblrModel.py -u'http://xxx.tumblr.com' 1      --下载http://xxx.tumblr.com的所有视频，并且将文件保存到本地
python .\TumblrModel.py -f'filename' 1                   --下载filename中所有的链接中的所有视频，并且将文件保存到本地

# -*- coding: utf-8 -*-
#--------------------------------------
#Author:waitig.com
#Date:2016-04-01
#Desc:自动下载Tumblr用户所有视频的脚本
#--------------------------------------

#-----------------关键代码--------------

    def get_video_urls(self,text):
        video_urls=re.findall('(?P<video_urls>https://www.tumblr.com/video/[^/]*?/\d+/\d+/)',text)
        return video_urls
    def get_video_files(self,url):
        url=url.strip('/')
        print 'Start to deal video url : '+url
        #-----------------------------------------------------------
        self.set_headers(url)
        self.headers={
        'Host': 'www.tumblr.com',
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:45.0) Gecko/20100101 Firefox/45.0',
        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
        'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',
        'Accept-Encoding': 'gzip, deflate, br',
        'Connection': 'keep-alive'
        }
        Reslut=self.se.get(url,headers=self.headers)
        sourceUrl=''
        sourceUrls=re.findall('src=\"(?P<video_urls>https://www.tumblr.com/video_file/\d+/[^\"]*?)\"',Reslut.text)
        if(sourceUrls!=[]):
            sourceUrl=sourceUrls[0]
        print 'Source url : '+sourceUrl
        SourceType=''
        SourceTypes=re.findall('type=\"video/(?P<vide_type>[^\"]*?)\"',Reslut.text)
        if(SourceTypes!=[]):
            SourceType=SourceTypes[0]
        sourceUrl=re.sub('https://www.tumblr.com/video_file/\d+/','',sourceUrl)
        sourceUrl=sourceUrl.replace('/','_')
        sourceUrl='https://vt.tumblr.com/'+sourceUrl
        trueUrl=sourceUrl+'.'+SourceType
        return trueUrl
    def deal_blogs_page(self,url):
        print 'Start to deal url : '+url
        self.set_headers(url)
        Result=self.se.get(url,headers=self.headers)
        text=Result.text
        img_urls=self.get_img_urls(text)
        video_urls=self.get_video_urls(text)
        for img in img_urls:
            self.save_img_file(img,self.img_path)
        for videoUrl in video_urls:
            self.save_video_file(videoUrl,self.video_path)
        nextUrls=re.findall('href=\"/page/(?P<next>\d+)\"',text)
        if(nextUrls!=[]):
            nextPage=str(self.curPage+1)
            if(nextPage in nextUrls):
                nextUrl=self.index_url+'page/'+nextPage
                self.curPage+=1
                self.deal_blogs_page(nextUrl)
        else:
            return
    def deal_save_path(self):
        userNames=re.findall('http://(?P<PATH>[^\.]*?)\.tumblr\.com/',self.index_url)
        if(userNames!=[]):
            userName=userNames[0]
        self.img_path=userName+'/img/'
        self.video_path=userName+'/videos/'
        if(os.path.exists(self.video_path)==False):
            os.makedirs(self.video_path)
        self.video_url_file=open(self.video_path+'video_url','w')