Merge branch 'polskie-radio-programme' of https://github.com/JakubAdamWieczorek/youtu...

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

diff --git a/youtube_dl/extractor/ard.py b/youtube_dl/extractor/ard.py
index 55f940d57f523eab6fd84240b3cc2c1f7c4d4dab..3a806a69b837a02d430d9e8f131acc116dbbe004 100644 (file)
--- a/youtube_dl/extractor/ard.py
+++ b/youtube_dl/extractor/ard.py
@@ -13,26 +13,67 @@ from ..utils import (
     parse_duration,
     unified_strdate,
     xpath_text,
-    parse_xml,
+    update_url_query,
 )
+from ..compat import compat_etree_fromstring
 
 
 class ARDMediathekIE(InfoExtractor):
     IE_NAME = 'ARD:mediathek'
-    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.daserste\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
+    _VALID_URL = r'^https?://(?:(?:www\.)?ardmediathek\.de|mediathek\.(?:daserste|rbb-online)\.de)/(?:.*/)(?P<video_id>[0-9]+|[^0-9][^/\?]+)[^/\?]*(?:\?.*)?'
 
     _TESTS = [{
+        'url': 'http://www.ardmediathek.de/tv/Dokumentation-und-Reportage/Ich-liebe-das-Leben-trotzdem/rbb-Fernsehen/Video?documentId=29582122&bcastId=3822114',
+        'info_dict': {
+            'id': '29582122',
+            'ext': 'mp4',
+            'title': 'Ich liebe das Leben trotzdem',
+            'description': 'md5:45e4c225c72b27993314b31a84a5261c',
+            'duration': 4557,
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        },
+        'skip': 'HTTP Error 404: Not Found',
+    }, {
+        'url': 'http://www.ardmediathek.de/tv/Tatort/Tatort-Scheinwelten-H%C3%B6rfassung-Video/Das-Erste/Video?documentId=29522730&bcastId=602916',
+        'md5': 'f4d98b10759ac06c0072bbcd1f0b9e3e',
+        'info_dict': {
+            'id': '29522730',
+            'ext': 'mp4',
+            'title': 'Tatort: Scheinwelten - Hörfassung (Video tgl. ab 20 Uhr)',
+            'description': 'md5:196392e79876d0ac94c94e8cdb2875f1',
+            'duration': 5252,
+        },
+        'skip': 'HTTP Error 404: Not Found',
+    }, {
+        # audio
+        'url': 'http://www.ardmediathek.de/tv/WDR-H%C3%B6rspiel-Speicher/Tod-eines-Fu%C3%9Fballers/WDR-3/Audio-Podcast?documentId=28488308&bcastId=23074086',
+        'md5': '219d94d8980b4f538c7fcb0865eb7f2c',
+        'info_dict': {
+            'id': '28488308',
+            'ext': 'mp3',
+            'title': 'Tod eines Fußballers',
+            'description': 'md5:f6e39f3461f0e1f54bfa48c8875c86ef',
+            'duration': 3240,
+        },
+        'skip': 'HTTP Error 404: Not Found',
+    }, {
         'url': 'http://mediathek.daserste.de/sendungen_a-z/328454_anne-will/22429276_vertrauen-ist-gut-spionieren-ist-besser-geht',
         'only_matching': True,
     }, {
-        'url': 'http://www.ardmediathek.de/tv/Tatort/Das-Wunder-von-Wolbeck-Video-tgl-ab-20/Das-Erste/Video?documentId=22490580&bcastId=602916',
+        # audio
+        'url': 'http://mediathek.rbb-online.de/radio/Hörspiel/Vor-dem-Fest/kulturradio/Audio?documentId=30796318&topRessort=radio&bcastId=9839158',
+        'md5': '4e8f00631aac0395fee17368ac0e9867',
         'info_dict': {
-            'id': '22490580',
-            'ext': 'mp4',
-            'title': 'Das Wunder von Wolbeck (Video tgl. ab 20 Uhr)',
-            'description': 'Auf einem restaurierten Hof bei Wolbeck wird der Heilpraktiker Raffael Lembeck eines morgens von seiner Frau Stella tot aufgefunden. Das Opfer war offensichtlich in seiner Praxis zu Fall gekommen und ist dann verblutet, erklärt Prof. Boerne am Tatort.',
+            'id': '30796318',
+            'ext': 'mp3',
+            'title': 'Vor dem Fest',
+            'description': 'md5:c0c1c8048514deaed2a73b3a60eecacb',
+            'duration': 3287,
         },
-        'skip': 'Blocked outside of Germany',
+        'skip': 'Video is no longer available',
     }]
 
     def _extract_media_info(self, media_info_url, webpage, video_id):
@@ -57,7 +98,7 @@ class ARDMediathekIE(InfoExtractor):
         subtitle_url = media_info.get('_subtitleUrl')
         if subtitle_url:
             subtitles['de'] = [{
-                'ext': 'srt',
+                'ext': 'ttml',
                 'url': subtitle_url,
             }]
 
@@ -84,13 +125,18 @@ class ARDMediathekIE(InfoExtractor):
                 server = stream.get('_server')
                 for stream_url in stream_urls:
                     ext = determine_ext(stream_url)
+                    if quality != 'auto' and ext in ('f4m', 'm3u8'):
+                        continue
                     if ext == 'f4m':
                         formats.extend(self._extract_f4m_formats(
-                            stream_url + '?hdcore=3.1.1&plugin=aasp-3.1.1.69.124',
-                            video_id, preference=-1, f4m_id='hds'))
+                            update_url_query(stream_url, {
+                                'hdcore': '3.1.1',
+                                'plugin': 'aasp-3.1.1.69.124'
+                            }),
+                            video_id, f4m_id='hds', fatal=False))
                     elif ext == 'm3u8':
                         formats.extend(self._extract_m3u8_formats(
-                            stream_url, video_id, 'mp4', preference=1, m3u8_id='hls'))
+                            stream_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
                     else:
                         if server and server.startswith('rtmp'):
                             f = {
@@ -135,7 +181,7 @@ class ARDMediathekIE(InfoExtractor):
             raise ExtractorError('This program is only suitable for those aged 12 and older. Video %s is therefore only available between 20 pm and 6 am.' % video_id, expected=True)
 
         if re.search(r'[\?&]rss($|[=&])', url):
-            doc = parse_xml(webpage)
+            doc = compat_etree_fromstring(webpage.encode('utf-8'))
             if doc.tag == 'rss':
                 return GenericIE()._extract_rss(url, video_id, doc)
 
@@ -192,7 +238,7 @@ class ARDMediathekIE(InfoExtractor):
 
 
 class ARDIE(InfoExtractor):
-    _VALID_URL = '(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
+    _VALID_URL = r'(?P<mainurl>https?://(www\.)?daserste\.de/[^?#]+/videos/(?P<display_id>[^/?#]+)-(?P<id>[0-9]+))\.html'
     _TEST = {
         'url': 'http://www.daserste.de/information/reportage-dokumentation/dokus/videos/die-story-im-ersten-mission-unter-falscher-flagge-100.html',
         'md5': 'd216c3a86493f9322545e045ddc3eb35',
@@ -204,7 +250,8 @@ class ARDIE(InfoExtractor):
             'title': 'Die Story im Ersten: Mission unter falscher Flagge',
             'upload_date': '20140804',
             'thumbnail': 're:^https?://.*\.jpg$',
-        }
+        },
+        'skip': 'HTTP Error 404: Not Found',
     }
 
     def _real_extract(self, url):