domains.py 文件源码

def sitesManager( media_url ):
    #picks which class will handle the media identification and extraction for website_name

    #first resolve url shortener
    shorteners=['bit.ly','goo.gl','tinyurl.com']
    if any(shortener in media_url for shortener in shorteners):
        #v=sitesBase.requests_get('https://unshorten.me/s/'+ urllib.quote_plus( media_url ) )
        v = requests.head( media_url, timeout=REQUEST_TIMEOUT, allow_redirects=True )
        log('  short url(%s)=%s'%(media_url,repr(v.url)))
        media_url=v.url

    for subcls in sitesBase.__subclasses__():
        regex=subcls.regex
        if regex:
            match=re.compile( regex  , re.I).findall( media_url )
            #log("testing:{0}[{1}] {2}".format(media_url,regex, repr(match)) )
            if match :
                return subcls( media_url )