[franceculture] Add extractor for '/emission-*' urls (closes #3777, closes #8022)

diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index 971047ad4d27bdbde1c7f92cace36339da3c4177..68c9c12886583941c3b43063953f7dfe7b744ede 100644 (file)
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -203,7 +203,10 @@ from .fourtube import FourTubeIE
 from .foxgay import FoxgayIE
 from .foxnews import FoxNewsIE
 from .foxsports import FoxSportsIE
-from .franceculture import FranceCultureIE
+from .franceculture import (
+    FranceCultureIE,
+    FranceCultureEmissionIE,
+)
 from .franceinter import FranceInterIE
 from .francetv import (
     PluzzIE,

diff --git a/youtube_dl/extractor/franceculture.py b/youtube_dl/extractor/franceculture.py
index 2ac6157cdecd2a0ea565f6d9528d8552aca22164..e2ca962838932f682f0ac833bd64169ccaba8fc5 100644 (file)
--- a/youtube_dl/extractor/franceculture.py
+++ b/youtube_dl/extractor/franceculture.py
@@ -8,6 +8,7 @@ from ..compat import (
 from ..utils import (
     determine_ext,
     int_or_none,
+    ExtractorError,
 )
 
 
@@ -28,8 +29,7 @@ class FranceCultureIE(InfoExtractor):
         }
     }
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
+    def _extract_from_player(self, url, video_id):
         webpage = self._download_webpage(url, video_id)
 
         video_path = self._search_regex(
@@ -42,6 +42,9 @@ class FranceCultureIE(InfoExtractor):
             r'<a id="player".*?>\s+<img src="([^"]+)"',
             webpage, 'thumbnail', fatal=False)
 
+        display_id = self._search_regex(
+            r'<span class="path-diffusion">emission-(.*?)</span>', webpage, 'display_id')
+
         title = self._html_search_regex(
             r'<span class="title-diffusion">(.*?)</span>', webpage, 'title')
         alt_title = self._html_search_regex(
@@ -66,4 +69,37 @@ class FranceCultureIE(InfoExtractor):
             'alt_title': alt_title,
             'thumbnail': thumbnail,
             'description': description,
+            'display_id': display_id,
         }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        return self._extract_from_player(url, video_id)
+
+
+class FranceCultureEmissionIE(FranceCultureIE):
+    _VALID_URL = r'https?://(?:www\.)?franceculture\.fr/emission-(?P<id>[^?#]+)'
+    _TEST = {
+        'url': 'http://www.franceculture.fr/emission-les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
+        'info_dict': {
+            'title': 'Jean-Gabriel Périot, cinéaste',
+            'alt_title': 'Les Carnets de la création',
+            'id': '5093239',
+            'display_id': 'les-carnets-de-la-creation-jean-gabriel-periot-cineaste-2015-10-13',
+            'ext': 'mp3',
+            'timestamp': 1444762500,
+            'upload_date': '20151013',
+            'description': 'startswith:Aujourd\'hui dans "Les carnets de la création", le cinéaste',
+        },
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        video_path = self._html_search_regex(
+            r'<a class="rf-player-open".*?href="([^"]+)"', webpage, 'video path', 'no_path_player')
+        if video_path == 'no_path_player':
+            raise ExtractorError('no player : no sound in this page.', expected=True)
+        new_id = self._search_regex('play=(?P<id>[0-9]+)', video_path, 'new_id', group='id')
+        video_url = compat_urlparse.urljoin(url, video_path)
+        return self._extract_from_player(video_url, new_id)