debian/control: Update list of extractors.

[youtubedl] / youtube_dl / extractor / francetv.py

diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index b1530e54964530157ce22476b0ee7d5f49f48143..6e1971043b3853b9fe54e682473a61621c9989e2 100644 (file)
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -1,6 +1,5 @@
 # encoding: utf-8
 import re
 # encoding: utf-8
 import re

-import xml.etree.ElementTree

 import json
 
 from .common import InfoExtractor
 import json
 
 from .common import InfoExtractor


@@ -11,11 +10,10 @@ from ..utils import (
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
     def _extract_video(self, video_id):
 
 class FranceTVBaseInfoExtractor(InfoExtractor):
     def _extract_video(self, video_id):

-        xml_desc = self._download_webpage(
+        info = self._download_xml(

             'http://www.francetvinfo.fr/appftv/webservices/video/'
             'getInfosOeuvre.php?id-diffusion='
             + video_id, video_id, 'Downloading XML config')
             'http://www.francetvinfo.fr/appftv/webservices/video/'
             'getInfosOeuvre.php?id-diffusion='
             + video_id, video_id, 'Downloading XML config')

-        info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))

 
         manifest_url = info.find('videos/video/url').text
         video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
 
         manifest_url = info.find('videos/video/url').text
         video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')


@@ -70,7 +68,11 @@ class FranceTvInfoIE(FranceTVBaseInfoExtractor):
 
 class France2IE(FranceTVBaseInfoExtractor):
     IE_NAME = u'france2.fr'
 
 class France2IE(FranceTVBaseInfoExtractor):
     IE_NAME = u'france2.fr'

-    _VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P<id>\d+)'
+    _VALID_URL = r'''(?x)https?://www\.france2\.fr/
+        (?:
+            emissions/.*?/videos/(?P<id>\d+)
+        |   emission/(?P<key>[^/?]+)
+        )'''

 
     _TEST = {
         u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
 
     _TEST = {
         u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',


@@ -86,12 +88,20 @@ class France2IE(FranceTVBaseInfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)

-        video_id = mobj.group('id')
+        if mobj.group('key'):
+            webpage = self._download_webpage(url, mobj.group('key'))
+            video_id = self._html_search_regex(
+                r'''(?x)<div\s+class="video-player">\s*
+                    <a\s+href="http://videos.francetv.fr/video/([0-9]+)"\s+
+                    class="francetv-video-player">''',
+                webpage, u'video ID')
+        else:
+            video_id = mobj.group('id')

         return self._extract_video(video_id)
 
 
 class GenerationQuoiIE(InfoExtractor):
         return self._extract_video(video_id)
 
 
 class GenerationQuoiIE(InfoExtractor):

-    IE_NAME = u'http://generation-quoi.france2.fr'
+    IE_NAME = u'france2.fr:generation-quoi'

     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 
     _TEST = {
     _VALID_URL = r'https?://generation-quoi\.france2\.fr/portrait/(?P<name>.*)(\?|$)'
 
     _TEST = {