- def fetch_webpage(self, url):
- request = compat_urllib_request.Request(url)
- try:
- self.report_download_webpage(url)
- webpage = compat_urllib_request.urlopen(request).read()
- except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
- raise ExtractorError(u'Unable to retrieve video webpage: %s' % compat_str(err))
- except ValueError as err:
- raise ExtractorError(u'Invalid URL: %s' % url)
- return webpage
-
- def grep_webpage(self, url, regex, regexFlags, matchTuples):
- page = self.fetch_webpage(url)
- mobj = re.search(regex, page, regexFlags)
- info = {}
-
- if mobj is None:
- raise ExtractorError(u'Invalid URL: %s' % url)
-
- for (i, key, err) in matchTuples:
- if mobj.group(i) is None:
- raise ExtractorError(err)
- else:
- info[key] = mobj.group(i)
-
- return info
-
- def extractLiveStream(self, url):
- video_lang = url.split('/')[-4]
- info = self.grep_webpage(
- url,
- r'src="(.*?/videothek_js.*?\.js)',
- 0,
- [
- (1, 'url', u'Invalid URL: %s' % url)
- ]
- )
- http_host = url.split('/')[2]
- next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
- info = self.grep_webpage(
- next_url,
- r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
- '(http://.*?\.swf).*?' +
- '(rtmp://.*?)\'',
- re.DOTALL,
- [
- (1, 'path', u'could not extract video path: %s' % url),
- (2, 'player', u'could not extract video player: %s' % url),
- (3, 'url', u'could not extract video url: %s' % url)
- ]
- )
- video_url = u'%s/%s' % (info.get('url'), info.get('path'))
+ # TODO implement Live Stream
+ # def extractLiveStream(self, url):
+ # video_lang = url.split('/')[-4]
+ # info = self.grep_webpage(
+ # url,
+ # r'src="(.*?/videothek_js.*?\.js)',
+ # 0,
+ # [
+ # (1, 'url', u'Invalid URL: %s' % url)
+ # ]
+ # )
+ # http_host = url.split('/')[2]
+ # next_url = 'http://%s%s' % (http_host, compat_urllib_parse.unquote(info.get('url')))
+ # info = self.grep_webpage(
+ # next_url,
+ # r'(s_artestras_scst_geoFRDE_' + video_lang + '.*?)\'.*?' +
+ # '(http://.*?\.swf).*?' +
+ # '(rtmp://.*?)\'',
+ # re.DOTALL,
+ # [
+ # (1, 'path', u'could not extract video path: %s' % url),
+ # (2, 'player', u'could not extract video player: %s' % url),
+ # (3, 'url', u'could not extract video url: %s' % url)
+ # ]
+ # )
+ # video_url = u'%s/%s' % (info.get('url'), info.get('path'))