Import Upstream version 2020.01.24

[youtubedl] / youtube_dl / extractor / rtlnl.py

diff --git a/youtube_dl/extractor/rtlnl.py b/youtube_dl/extractor/rtlnl.py
index cfce4550ada568cfe13fae859a2bb745671074b5..fadca8c175475e9b2bf7cb4c9bc0a7e2ed163fcc 100644 (file)
--- a/youtube_dl/extractor/rtlnl.py
+++ b/youtube_dl/extractor/rtlnl.py
@@ -12,26 +12,27 @@ class RtlNlIE(InfoExtractor):
     IE_NAME = 'rtl.nl'
     IE_DESC = 'rtl.nl and rtlxl.nl'
     _VALID_URL = r'''(?x)
-        https?://(www\.)?
+        https?://(?:(?:www|static)\.)?
         (?:
-            rtlxl\.nl/\#!/[^/]+/|
-            rtl\.nl/system/videoplayer/[^?#]+?/video_embed\.html\#uuid=
+            rtlxl\.nl/[^\#]*\#!/[^/]+/|
+            rtl\.nl/(?:(?:system/videoplayer/(?:[^/]+/)+(?:video_)?embed\.html|embed)\b.+?\buuid=|video/)
         )
         (?P<id>[0-9a-f-]+)'''
 
     _TESTS = [{
-        'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/6e4203a6-0a5e-3596-8424-c599a59e0677',
-        'md5': 'cc16baa36a6c169391f0764fa6b16654',
+        'url': 'http://www.rtlxl.nl/#!/rtl-nieuws-132237/82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
+        'md5': '473d1946c1fdd050b2c0161a4b13c373',
         'info_dict': {
-            'id': '6e4203a6-0a5e-3596-8424-c599a59e0677',
+            'id': '82b1aad1-4a14-3d7b-b554-b0aed1b2c416',
             'ext': 'mp4',
-            'title': 'RTL Nieuws - Laat',
-            'description': 'md5:6b61f66510c8889923b11f2778c72dc5',
-            'timestamp': 1408051800,
-            'upload_date': '20140814',
-            'duration': 576.880,
+            'title': 'RTL Nieuws',
+            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+            'timestamp': 1461951000,
+            'upload_date': '20160429',
+            'duration': 1167.96,
         },
     }, {
+        # best format available a3t
         'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed/autoplay=false',
         'md5': 'dea7474214af1271d91ef332fb8be7ea',
         'info_dict': {
@@ -39,47 +40,68 @@ class RtlNlIE(InfoExtractor):
             'ext': 'mp4',
             'timestamp': 1424039400,
             'title': 'RTL Nieuws - Nieuwe beelden Kopenhagen: chaos direct na aanslag',
-            'thumbnail': 're:^https?://screenshots\.rtl\.nl/system/thumb/sz=[0-9]+x[0-9]+/uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed$',
+            'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=84ae5571-ac25-4225-ae0c-ef8d9efb2aed$',
             'upload_date': '20150215',
             'description': 'Er zijn nieuwe beelden vrijgegeven die vlak na de aanslag in Kopenhagen zijn gemaakt. Op de video is goed te zien hoe omstanders zich bekommeren om één van de slachtoffers, terwijl de eerste agenten ter plaatse komen.',
         }
+    }, {
+        # empty synopsis and missing episodes (see https://github.com/ytdl-org/youtube-dl/issues/6275)
+        # best format available nettv
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/rtlnieuws/video_embed.html#uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a/autoplay=false',
+        'info_dict': {
+            'id': 'f536aac0-1dc3-4314-920e-3bd1c5b3811a',
+            'ext': 'mp4',
+            'title': 'RTL Nieuws - Meer beelden van overval juwelier',
+            'thumbnail': r're:^https?://screenshots\.rtl\.nl/(?:[^/]+/)*sz=[0-9]+x[0-9]+/uuid=f536aac0-1dc3-4314-920e-3bd1c5b3811a$',
+            'timestamp': 1437233400,
+            'upload_date': '20150718',
+            'duration': 30.474,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # encrypted m3u8 streams, georestricted
+        'url': 'http://www.rtlxl.nl/#!/afl-2-257632/52a74543-c504-4cde-8aa8-ec66fe8d68a7',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.rtl.nl/system/videoplayer/derden/embed.html#!/uuid=bb0353b0-d6a4-1dad-90e9-18fe75b8d1f0',
+        'only_matching': True,
+    }, {
+        'url': 'http://rtlxl.nl/?_ga=1.204735956.572365465.1466978370#!/rtl-nieuws-132237/3c487912-023b-49ac-903e-2c5d79f8410f',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.rtl.nl/video/c603c9c2-601d-4b5e-8175-64f1e942dc7d/',
+        'only_matching': True,
+    }, {
+        'url': 'https://static.rtl.nl/embed/?uuid=1a2970fc-5c0b-43ff-9fdc-927e39e6d1bc&autoplay=false&publicatiepunt=rtlnieuwsnl',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
         uuid = self._match_id(url)
         info = self._download_json(
-            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=flash/' % uuid,
+            'http://www.rtl.nl/system/s4m/vfd/version=2/uuid=%s/fmt=adaptive/' % uuid,
             uuid)
 
         material = info['material'][0]
-        progname = info['abstracts'][0]['name']
-        subtitle = material['title'] or info['episodes'][0]['name']
-        description = material.get('synopsis') or info['episodes'][0]['synopsis']
-
-        # Use unencrypted m3u8 streams (See https://github.com/rg3/youtube-dl/issues/4118)
-        videopath = material['videopath'].replace('.f4m', '.m3u8')
-        m3u8_url = 'http://manifest.us.rtl.nl' + videopath
+        title = info['abstracts'][0]['name']
+        subtitle = material.get('title')
+        if subtitle:
+            title += ' - %s' % subtitle
+        description = material.get('synopsis')
 
-        formats = self._extract_m3u8_formats(m3u8_url, uuid, ext='mp4')
+        meta = info.get('meta', {})
 
-        video_urlpart = videopath.split('/flash/')[1][:-5]
-        PG_URL_TEMPLATE = 'http://pg.us.rtl.nl/rtlxl/network/%s/progressive/%s.mp4'
+        videopath = material['videopath']
+        m3u8_url = meta.get('videohost', 'http://manifest.us.rtl.nl') + videopath
 
-        formats.extend([
-            {
-                'url': PG_URL_TEMPLATE % ('a2m', video_urlpart),
-                'format_id': 'pg-sd',
-            },
-            {
-                'url': PG_URL_TEMPLATE % ('a3m', video_urlpart),
-                'format_id': 'pg-hd',
-                'quality': 0,
-            }
-        ])
+        formats = self._extract_m3u8_formats(
+            m3u8_url, uuid, 'mp4', m3u8_id='hls', fatal=False)
         self._sort_formats(formats)
 
         thumbnails = []
-        meta = info.get('meta', {})
+
         for p in ('poster_base_url', '"thumb_base_url"'):
             if not meta.get(p):
                 continue
@@ -95,7 +117,7 @@ class RtlNlIE(InfoExtractor):
 
         return {
             'id': uuid,
-            'title': '%s - %s' % (progname, subtitle),
+            'title': title,
             'formats': formats,
             'timestamp': material['original_date'],
             'description': description,