Merge remote-tracking branch 'jaimeMF/opengraph'

[youtube-dl] / youtube_dl / extractor / arte.py

diff --git a/youtube_dl/extractor/arte.py b/youtube_dl/extractor/arte.py
index f5267249051e6d0e516a7b2561de8ebf62823f12..993e30f7ad31cbbaa6c746863d3344527a3e8946 100644 (file)
--- a/youtube_dl/extractor/arte.py
+++ b/youtube_dl/extractor/arte.py
@@ -4,10 +4,8 @@ import xml.etree.ElementTree
 
 from .common import InfoExtractor
 from ..utils import (
-    # This is used by the not implemented extractLiveStream method
-    compat_urllib_parse,
-
     ExtractorError,
+    find_xpath_attr,
     unified_strdate,
 )
 
@@ -28,6 +26,7 @@ class ArteTvIE(InfoExtractor):
         return any(re.match(regex, url) for regex in (cls._EMISSION_URL, cls._VIDEOS_URL))
 
     # TODO implement Live Stream
+    # from ..utils import compat_urllib_parse
     # def extractLiveStream(self, url):
     #     video_lang = url.split('/')[-4]
     #     info = self.grep_webpage(
@@ -57,7 +56,6 @@ class ArteTvIE(InfoExtractor):
     def _real_extract(self, url):
         mobj = re.match(self._EMISSION_URL, url)
         if mobj is not None:
-            name = mobj.group('name')
             lang = mobj.group('lang')
             # This is not a real id, it can be for example AJT for the news
             # http://www.arte.tv/guide/fr/emissions/AJT/arte-journal
@@ -77,12 +75,8 @@ class ArteTvIE(InfoExtractor):
 
     def _extract_emission(self, url, video_id, lang):
         """Extract from www.arte.tv/guide"""
-        if video_id.replace('-','').isdigit():
-            json_url = 'http://org-www.arte.tv/papi/tvguide/videos/stream/player/F/%s_PLUS7-F/ALL/ALL.json' % video_id
-        else:
-            # We don't know the real id of the video, we have to search in the webpage
-            webpage = self._download_webpage(url, video_id)
-            json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
+        webpage = self._download_webpage(url, video_id)
+        json_url = self._html_search_regex(r'arte_vp_url="(.*?)"', webpage, 'json url')
 
         json_info = self._download_webpage(json_url, video_id, 'Downloading info json')
         self.report_extraction(video_id)
@@ -126,7 +120,7 @@ class ArteTvIE(InfoExtractor):
         ref_xml_url = ref_xml_url.replace('.html', ',view,asPlayerXml.xml')
         ref_xml = self._download_webpage(ref_xml_url, video_id, note=u'Downloading metadata')
         ref_xml_doc = xml.etree.ElementTree.fromstring(ref_xml)
-        config_node = ref_xml_doc.find('.//video[@lang="%s"]' % lang)
+        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')