[francetv] Add an extractor for France2

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

diff --git a/youtube_dl/extractor/francetv.py b/youtube_dl/extractor/francetv.py
index 6e11764704b9afbf1a25e33a62cee92a49b7a805..5e915bc03edef5cbdb00a1e0bc19663a985e96ba 100644 (file)
--- a/youtube_dl/extractor/francetv.py
+++ b/youtube_dl/extractor/francetv.py
@@ -8,32 +8,12 @@ from ..utils import (
 )
 
 
-class PluzzIE(InfoExtractor):
-    IE_NAME = u'pluzz.francetv.fr'
-    _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
-
-    _TEST = {
-        u'url': u'http://pluzz.francetv.fr/videos/allo_rufo_saison5_,88439064.html',
-        u'file': u'88439064.mp4',
-        u'info_dict': {
-            u'title': u'Allô Rufo',
-            u'description': u'md5:d909f1ebdf963814b65772aea250400e',
-        },
-        u'params': {
-            u'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        title = re.match(self._VALID_URL, url).group(1)
-        webpage = self._download_webpage(url, title)
-        video_id = self._search_regex(
-            r'data-diffusion="(\d+)"', webpage, 'ID')
-
+class FranceTVBaseInfoExtractor(InfoExtractor):
+    def _extract_video(self, video_id):
         xml_desc = self._download_webpage(
-            'http://www.pluzz.fr/appftv/webservices/video/'
+            'http://www.francetvinfo.fr/appftv/webservices/video/'
             'getInfosOeuvre.php?id-diffusion='
-            + video_id, title, 'Downloading XML config')
+            + 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
@@ -45,6 +25,65 @@ class PluzzIE(InfoExtractor):
                 'ext': 'mp4',
                 'url': video_url,
                 'title': info.find('titre').text,
-                'thumbnail': compat_urlparse.urljoin(url, thumbnail_path),
+                'thumbnail': compat_urlparse.urljoin('http://pluzz.francetv.fr', thumbnail_path),
                 'description': info.find('synopsis').text,
                 }
+
+
+class PluzzIE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'pluzz.francetv.fr'
+    _VALID_URL = r'https?://pluzz\.francetv\.fr/videos/(.*?)\.html'
+
+    # Can't use tests, videos expire in 7 days
+
+    def _real_extract(self, url):
+        title = re.match(self._VALID_URL, url).group(1)
+        webpage = self._download_webpage(url, title)
+        video_id = self._search_regex(
+            r'data-diffusion="(\d+)"', webpage, 'ID')
+        return self._extract_video(video_id)
+
+
+class FranceTvInfoIE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'francetvinfo.fr'
+    _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
+
+    _TEST = {
+        u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
+        u'file': u'84981923.mp4',
+        u'info_dict': {
+            u'title': u'Soir 3',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        page_title = mobj.group('title')
+        webpage = self._download_webpage(url, page_title)
+        video_id = self._search_regex(r'id-video=(\d+?)"', webpage, u'video id')
+        return self._extract_video(video_id)
+
+
+class France2IE(FranceTVBaseInfoExtractor):
+    IE_NAME = u'france2.fr'
+    _VALID_URL = r'https?://www\.france2\.fr/emissions/.*?/videos/(?P<id>\d+)'
+
+    _TEST = {
+        u'url': u'http://www.france2.fr/emissions/13h15-le-samedi-le-dimanche/videos/75540104',
+        u'file': u'75540104.mp4',
+        u'info_dict': {
+            u'title': u'13h15, le samedi...',
+            u'description': u'md5:2e5b58ba7a2d3692b35c792be081a03d',
+        },
+        u'params': {
+            u'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        mobj = re.match(self._VALID_URL, url)
+        video_id = mobj.group('id')
+        return self._extract_video(video_id)