soundcloud.py 文件源码

def _real_extract(self, url):
        mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
        if mobj is None:
            raise ExtractorError('Invalid URL: %s' % url)

        track_id = mobj.group('track_id')
        token = None
        if track_id is not None:
            info_json_url = 'http://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
            full_title = track_id
            token = mobj.group('secret_token')
            if token:
                info_json_url += "&secret_token=" + token
        elif mobj.group('player'):
            query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
            real_url = query['url'][0]
            # If the token is in the query of the original url we have to
            # manually add it
            if 'secret_token' in query:
                real_url += '?secret_token=' + query['secret_token'][0]
            return self.url_result(real_url)
        else:
            # extract uploader (which is in the url)
            uploader = mobj.group('uploader')
            # extract simple title (uploader + slug of song title)
            slug_title = mobj.group('title')
            token = mobj.group('token')
            full_title = resolve_title = '%s/%s' % (uploader, slug_title)
            if token:
                resolve_title += '/%s' % token

            self.report_resolve(full_title)

            url = 'http://soundcloud.com/%s' % resolve_title
            info_json_url = self._resolv_url(url)
        info = self._download_json(info_json_url, full_title, 'Downloading info JSON')

        return self._extract_info_dict(info, full_title, secret_token=token)