]> Raphaël G. Git Repositories - youtubedl/blobdiff - youtube_dl/extractor/rtve.py
Rapsys Git / youtubedl / blobdiff
? search:
summary | shortlog | log | commit | commitdiff | tree
raw | inline | side by side
Initiate new release.
[youtubedl] / youtube_dl / extractor / rtve.py
diff --git a/youtube_dl/extractor/rtve.py b/youtube_dl/extractor/rtve.py
index f11e3588b0796718e2ecbe316b53b968a08df98c..d9edf9da2f71cf6fbcf3c8bfd310c4818eced62c 100644 (file)
--- a/youtube_dl/extractor/rtve.py
+++ b/youtube_dl/extractor/rtve.py
@@ -1,4 +1,4 @@
-# encoding: utf-8
+# coding: utf-8
 from __future__ import unicode_literals
 
 import base64
 from __future__ import unicode_literals
 
 import base64
@@ -10,6 +10,7 @@ from ..compat import (
     compat_struct_unpack,
 )
 from ..utils import (
     compat_struct_unpack,
 )
 from ..utils import (
+    determine_ext,
     ExtractorError,
     float_or_none,
     remove_end,
     ExtractorError,
     float_or_none,
     remove_end,
@@ -64,7 +65,7 @@ def _decrypt_url(png):
 class RTVEALaCartaIE(InfoExtractor):
     IE_NAME = 'rtve.es:alacarta'
     IE_DESC = 'RTVE a la carta'
 class RTVEALaCartaIE(InfoExtractor):
     IE_NAME = 'rtve.es:alacarta'
     IE_DESC = 'RTVE a la carta'
-    _VALID_URL = r'https?://www\.rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
 
     _TESTS = [{
         'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
@@ -84,6 +85,18 @@ class RTVEALaCartaIE(InfoExtractor):
             'title': 'TODO',
         },
         'skip': 'The f4m manifest can\'t be used yet',
             'title': 'TODO',
         },
         'skip': 'The f4m manifest can\'t be used yet',
+    }, {
+        'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
+        'md5': 'e55e162379ad587e9640eda4f7353c0f',
+        'info_dict': {
+            'id': '4236788',
+            'ext': 'mp4',
+            'title': 'Servir y proteger - Capítulo 104 ',
+            'duration': 3222.0,
+        },
+        'params': {
+            'skip_download': True,  # requires ffmpeg
+        },
     }, {
         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
         'only_matching': True,
     }, {
         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
         'only_matching': True,
@@ -107,15 +120,32 @@ class RTVEALaCartaIE(InfoExtractor):
             video_id)['page']['items'][0]
         if info['state'] == 'DESPU':
             raise ExtractorError('The video is no longer available', expected=True)
             video_id)['page']['items'][0]
         if info['state'] == 'DESPU':
             raise ExtractorError('The video is no longer available', expected=True)
+        title = info['title']
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
         png_request = sanitized_Request(png_url)
         png_request.add_header('Referer', url)
         png = self._download_webpage(png_request, video_id, 'Downloading url information')
         video_url = _decrypt_url(png)
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
         png_request = sanitized_Request(png_url)
         png_request.add_header('Referer', url)
         png = self._download_webpage(png_request, video_id, 'Downloading url information')
         video_url = _decrypt_url(png)
-        if not video_url.endswith('.f4m'):
-            video_url = video_url.replace(
-                'resources/', 'auth/resources/'
-            ).replace('.net.rtve', '.multimedia.cdn.rtve')
+        ext = determine_ext(video_url)
+
+        formats = []
+        if not video_url.endswith('.f4m') and ext != 'm3u8':
+            if '?' not in video_url:
+                video_url = video_url.replace('resources/', 'auth/resources/')
+            video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
+
+        if ext == 'm3u8':
+            formats.extend(self._extract_m3u8_formats(
+                video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+                m3u8_id='hls', fatal=False))
+        elif ext == 'f4m':
+            formats.extend(self._extract_f4m_formats(
+                video_url, video_id, f4m_id='hds', fatal=False))
+        else:
+            formats.append({
+                'url': video_url,
+            })
+        self._sort_formats(formats)
 
         subtitles = None
         if info.get('sbtFile') is not None:
 
         subtitles = None
         if info.get('sbtFile') is not None:
@@ -123,8 +153,8 @@ class RTVEALaCartaIE(InfoExtractor):
 
         return {
             'id': video_id,
 
         return {
             'id': video_id,
-            'title': info['title'],
-            'url': video_url,
+            'title': title,
+            'formats': formats,
             'thumbnail': info.get('image'),
             'page_url': url,
             'subtitles': subtitles,
             'thumbnail': info.get('image'),
             'page_url': url,
             'subtitles': subtitles,
@@ -184,7 +214,7 @@ class RTVEInfantilIE(InfoExtractor):
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'
 class RTVELiveIE(InfoExtractor):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'
-    _VALID_URL = r'https?://www\.rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/directo/la-1/',
 
     _TESTS = [{
         'url': 'http://www.rtve.es/directo/la-1/',
@@ -209,7 +239,10 @@ class RTVELiveIE(InfoExtractor):
         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         vidplayer_id = self._search_regex(
         title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         vidplayer_id = self._search_regex(
-            r'playerId=player([0-9]+)', webpage, 'internal video ID')
+            (r'playerId=player([0-9]+)',
+             r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
+             r'data-id=["\'](\d+)'),
+            webpage, 'internal video ID')
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
         m3u8_url = _decrypt_url(png)
         png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
         png = self._download_webpage(png_url, video_id, 'Downloading url information')
         m3u8_url = _decrypt_url(png)
@@ -222,3 +255,34 @@ 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())
Backup clone of https://github.com/ytdl-org unavailable since RIAA fucking raid...