- IE_NAME = u'arte.tv'
-
- 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)
+ IE_NAME = 'arte.tv'
+
+ @classmethod
+ def suitable(cls, url):
+ return any(re.match(regex, url) for regex in (cls._VIDEOS_URL, cls._LIVEWEB_URL))
+
+ # TODO implement Live Stream
+ # from ..utils import compat_urllib_parse
+ # def extractLiveStream(self, url):
+ # video_lang = url.split('/')[-4]
+ # info = self.grep_webpage(
+ # url,
+ # r'src="(.*?/videothek_js.*?\.js)',
+ # 0,
+ # [
+ # (1, 'url', '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', 'could not extract video path: %s' % url),
+ # (2, 'player', 'could not extract video player: %s' % url),
+ # (3, 'url', 'could not extract video url: %s' % url)
+ # ]
+ # )
+ # video_url = '%s/%s' % (info.get('url'), info.get('path'))
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VIDEOS_URL, url)
+ if mobj is not None:
+ id = mobj.group('id')
+ lang = mobj.group('lang')
+ return self._extract_video(url, id, lang)
+
+ mobj = re.match(self._LIVEWEB_URL, url)
+ if mobj is not None:
+ name = mobj.group('name')
+ lang = mobj.group('lang')
+ return self._extract_liveweb(url, name, lang)
+
+ if re.search(self._LIVE_URL, url) is not None:
+ raise ExtractorError(u'Arte live streams are not yet supported, sorry')
+ # self.extractLiveStream(url)
+ # return
+
+ def _extract_video(self, url, video_id, lang):
+ """Extract from videos.arte.tv"""
+ ref_xml_url = url.replace('/videos/', '/do_delegate/videos/')
+ ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
+ ref_xml_doc = self._download_xml(ref_xml_url, video_id, note=u'Downloading metadata')
+ config_node = find_xpath_attr(ref_xml_doc, './/video', 'lang', lang)
+ config_xml_url = config_node.attrib['ref']
+ config_xml = self._download_webpage(config_xml_url, video_id, note=u'Downloading configuration')
+
+ video_urls = list(re.finditer(r'<url quality="(?P<quality>.*?)">(?P<url>.*?)</url>', config_xml))
+ def _key(m):
+ quality = m.group('quality')
+ if quality == 'hd':
+ return 2