Add extractor for rtve.es/television (fixes #10076)

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index 916c8bb3ef71cfbeb31d3027555a5192017d8719..71baee90d6ac8f591b29247ddc4b7f6dcf1319f2 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -689,7 +689,7 @@ from .rtlnl import RtlNlIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE
 from .rtl2 import RTL2IE
 from .rtp import RTPIE
 from .rts import RTSIE

-from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE
+from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE

 from .rtvnh import RTVNHIE
 from .rudo import RudoIE
 from .ruhd import RUHDIE
 from .rtvnh import RTVNHIE
 from .rudo import RudoIE
 from .ruhd import RUHDIE

diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py
index de35e07d9e733820d3eb18004de4b7f46924ac71..d33b05f5de1b33441e79363959fd4b40150707de 100644 (file)
--- a/youtube_dl/extractor/rtve.py
+++ b/youtube_dl/extractor/rtve.py
@@ -220,3 +220,34 @@ class RTVELiveIE(InfoExtractor):
             'formats': formats,
             'is_live': True,
         }
             'formats': formats,
             'is_live': True,
         }

+
+
+class RTVETelevisionIE(InfoExtractor):
+    IE_NAME = 'rtve.es:television'
+    _VALID_URL = r'https?://www\.rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml'
+
+    _TEST = {
+        'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml',
+        'info_dict': {
+            'id': '3069778',
+            'ext': 'mp4',
+            'title': 'Documentos TV - La revolución del móvil',
+            'duration': 3496.948,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }
+
+    def _real_extract(self, url):
+        page_id = self._match_id(url)
+        webpage = self._download_webpage(url, page_id)
+
+        alacarta_url = self._search_regex(
+            r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&',
+            webpage, 'alacarta url', default=None)
+        if alacarta_url is None:
+            raise ExtractorError(
+                'The webpage doesn\'t contain any video', expected=True)
+
+        return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key())