[francetv] Add an extractor for francetvinfo.fr (closes #1317)

It uses the same system as Pluzz, create a base class for both extractors.

youtube_dl/extractor/__init__.py

@@ -29,7 +29,10 @@ from .escapist import EscapistIE
 from .exfm import ExfmIE
 from .facebook import FacebookIE
 from .flickr import FlickrIE
-from .francetv import PluzzIE
+from .francetv import (
+    PluzzIE,
+    FranceTvInfoIE,
+)
 from .freesound import FreesoundIE
 from .funnyordie import FunnyOrDieIE
 from .gamespot import GameSpotIE

youtube_dl/extractor/francetv.py

@@ -8,7 +8,29 @@ from ..utils import (
 )
 
 
-class PluzzIE(InfoExtractor):
+class FranceTVBaseInfoExtractor(InfoExtractor):
+    def _extract_video(self, video_id):
+        xml_desc = self._download_webpage(
+            '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')
+        video_url = video_url.replace('/z/', '/i/')
+        thumbnail_path = info.find('image').text
+
+        return {'id': video_id,
+                'ext': 'mp4',
+                'url': video_url,
+                'title': info.find('titre').text,
+                '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'
 
@@ -29,22 +51,27 @@ class PluzzIE(InfoExtractor):
         webpage = self._download_webpage(url, title)
         video_id = self._search_regex(
             r'data-diffusion="(\d+)"', webpage, 'ID')
+        return self._extract_video(video_id)
 
-        xml_desc = self._download_webpage(
-            'http://www.pluzz.fr/appftv/webservices/video/'
-            'getInfosOeuvre.php?id-diffusion='
-            + video_id, title, 'Downloading XML config')
-        info = xml.etree.ElementTree.fromstring(xml_desc.encode('utf-8'))
 
-        manifest_url = info.find('videos/video/url').text
+class FranceTvInfoIE(FranceTVBaseInfoExtractor):
-        video_url = manifest_url.replace('manifest.f4m', 'index_2_av.m3u8')
+    IE_NAME = u'francetvinfo.fr'
-        video_url = video_url.replace('/z/', '/i/')
+    _VALID_URL = r'https?://www\.francetvinfo\.fr/replay.*/(?P<title>.+).html'
-        thumbnail_path = info.find('image').text
 
-        return {'id': video_id,
+    _TEST = {
-                'ext': 'mp4',
+        u'url': u'http://www.francetvinfo.fr/replay-jt/france-3/soir-3/jt-grand-soir-3-lundi-26-aout-2013_393427.html',
-                'url': video_url,
+        u'file': u'84981923.mp4',
-                'title': info.find('titre').text,
+        u'info_dict': {
-                'thumbnail': compat_urlparse.urljoin(url, thumbnail_path),
+            u'title': u'Soir 3',
-                'description': info.find('synopsis').text,
+        },
-                }
+        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)