New upstream version 2020.05.08

[youtubedl] / youtube_dl / extractor / rts.py

diff --git a/youtube_dl/extractor/rts.py b/youtube_dl/extractor/rts.py
index 5e84c109802e34ce8f57496ee3b7e2cd409c0788..48f17b828c1a8c6b0494ad1edb2bc3f914b3417a 100644 (file)
--- a/youtube_dl/extractor/rts.py
+++ b/youtube_dl/extractor/rts.py
@@ -3,26 +3,25 @@ from __future__ import unicode_literals
 
 import re
 
 
 import re
 

-from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-)
+from .srgssr import SRGSSRIE
+from ..compat import compat_str

 from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
 from ..utils import (
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,

+    determine_ext,

 )
 
 
 )
 
 

-class RTSIE(InfoExtractor):
+class RTSIE(SRGSSRIE):

     IE_DESC = 'RTS.ch'
     IE_DESC = 'RTS.ch'

-    _VALID_URL = r'https?://(?:www\.)?rts\.ch/(?:(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html|play/tv/[^/]+/video/(?P<display_id_new>.+?)\?id=(?P<id_new>[0-9]+))'
+    _VALID_URL = r'rts:(?P<rts_id>\d+)|https?://(?:.+?\.)?rts\.ch/(?:[^/]+/){2,}(?P<id>[0-9]+)-(?P<display_id>.+?)\.html'

 
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
 
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',

-            'md5': '753b877968ad8afaeddccc374d4256a5',
+            'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',

             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',
             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',


@@ -33,30 +32,20 @@ class RTSIE(InfoExtractor):
                 'uploader': 'Divers',
                 'upload_date': '19680921',
                 'timestamp': -40280400,
                 'uploader': 'Divers',
                 'upload_date': '19680921',
                 'timestamp': -40280400,

-                'thumbnail': 're:^https?://.*\.image',
+                'thumbnail': r're:^https?://.*\.image',

                 'view_count': int,
             },
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
                 'view_count': int,
             },
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',

-            'md5': 'c148457a27bdc9e5b1ffe081a7a8337b',

             'info_dict': {
             'info_dict': {

-                'id': '5624067',
-                'display_id': 'entre-ciel-et-mer',
-                'ext': 'mp4',
-                'duration': 3720,
-                'title': 'Les yeux dans les cieux - Mon homard au Canada',
-                'description': 'md5:d22ee46f5cc5bac0912e5a0c6d44a9f7',
-                'uploader': 'Passe-moi les jumelles',
-                'upload_date': '20140404',
-                'timestamp': 1396635300,
-                'thumbnail': 're:^https?://.*\.image',
-                'view_count': int,
+                'id': '5624065',
+                'title': 'Passe-moi les jumelles',

             },
             },

+            'playlist_mincount': 4,

         },
         {
             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',
         },
         {
             'url': 'http://www.rts.ch/video/sport/hockey/5745975-1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski.html',

-            'md5': 'b4326fecd3eb64a458ba73c73e91299d',

             'info_dict': {
                 'id': '5745975',
                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',
             'info_dict': {
                 'id': '5745975',
                 'display_id': '1-2-kloten-fribourg-5-2-second-but-pour-gotteron-par-kwiatowski',


@@ -67,14 +56,18 @@ class RTSIE(InfoExtractor):
                 'uploader': 'Hockey',
                 'upload_date': '20140403',
                 'timestamp': 1396556882,
                 'uploader': 'Hockey',
                 'upload_date': '20140403',
                 'timestamp': 1396556882,

-                'thumbnail': 're:^https?://.*\.image',
+                'thumbnail': r're:^https?://.*\.image',

                 'view_count': int,
             },
                 'view_count': int,
             },

+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },

             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',

-            'md5': '9bb06503773c07ce83d3cbd793cebb91',
+            'md5': '1bae984fe7b1f78e94abc74e802ed99f',

             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',
             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',


@@ -82,10 +75,10 @@ class RTSIE(InfoExtractor):
                 'duration': 33,
                 'title': 'Londres cachée par un épais smog',
                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',
                 'duration': 33,
                 'title': 'Londres cachée par un épais smog',
                 'description': 'Un important voile de smog recouvre Londres depuis mercredi, provoqué par la pollution et du sable du Sahara.',

-                'uploader': 'Le Journal en continu',
+                'uploader': 'L\'actu en vidéo',

                 'upload_date': '20140403',
                 'timestamp': 1396537322,
                 'upload_date': '20140403',
                 'timestamp': 1396537322,

-                'thumbnail': 're:^https?://.*\.image',
+                'thumbnail': r're:^https?://.*\.image',

                 'view_count': int,
             },
         },
                 'view_count': int,
             },
         },


@@ -104,85 +97,134 @@ class RTSIE(InfoExtractor):
             },
         },
         {
             },
         },
         {

-            'url': 'http://www.rts.ch/play/tv/-/video/le-19h30?id=6348260',
-            'md5': '968777c8779e5aa2434be96c54e19743',
+            # article with videos on rhs
+            'url': 'http://www.rts.ch/sport/hockey/6693917-hockey-davos-decroche-son-31e-titre-de-champion-de-suisse.html',

             'info_dict': {
             'info_dict': {

-                'id': '6348260',
-                'display_id': 'le-19h30',
-                'ext': 'mp4',
-                'duration': 1796,
-                'title': 'Le 19h30',
-                'description': '',
-                'uploader': 'Le 19h30',
-                'upload_date': '20141201',
-                'timestamp': 1417458600,
-                'thumbnail': 're:^https?://.*\.image',
-                'view_count': int,
+                'id': '6693917',
+                'title': 'Hockey: Davos décroche son 31e titre de champion de Suisse',

             },
             },

+            'playlist_mincount': 5,

         },
         {
         },
         {

-            'url': 'http://www.rts.ch/play/tv/le-19h30/video/le-chantier-du-nouveau-parlement-vaudois-a-permis-une-trouvaille-historique?id=6348280',
+            'url': 'http://pages.rts.ch/emissions/passe-moi-les-jumelles/5624065-entre-ciel-et-mer.html',

             'only_matching': True,
         }
     ]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)
             'only_matching': True,
         }
     ]
 
     def _real_extract(self, url):
         m = re.match(self._VALID_URL, url)

-        video_id = m.group('id') or m.group('id_new')
-        display_id = m.group('display_id') or m.group('display_id_new')
+        media_id = m.group('rts_id') or m.group('id')
+        display_id = m.group('display_id') or media_id

 
         def download_json(internal_id):
             return self._download_json(
                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
                 display_id)
 
 
         def download_json(internal_id):
             return self._download_json(
                 'http://www.rts.ch/a/%s.html?f=json/article' % internal_id,
                 display_id)
 

-        all_info = download_json(video_id)
+        all_info = download_json(media_id)

 
 

-        # video_id extracted out of URL is not always a real id
+        # media_id extracted out of URL is not always a real id

         if 'video' not in all_info and 'audio' not in all_info:
         if 'video' not in all_info and 'audio' not in all_info:

-            page = self._download_webpage(url, display_id)
+            entries = []
+
+            for item in all_info.get('items', []):
+                item_url = item.get('url')
+                if not item_url:
+                    continue
+                entries.append(self.url_result(item_url, 'RTS'))
+
+            if not entries:
+                page, urlh = self._download_webpage_handle(url, display_id)
+                if re.match(self._VALID_URL, urlh.geturl()).group('id') != media_id:
+                    return self.url_result(urlh.geturl(), 'RTS')
+
+                # article with videos on rhs
+                videos = re.findall(
+                    r'<article[^>]+class="content-item"[^>]*>\s*<a[^>]+data-video-urn="urn:([^"]+)"',
+                    page)
+                if not videos:
+                    videos = re.findall(
+                        r'(?s)<iframe[^>]+class="srg-player"[^>]+src="[^"]+urn:([^"]+)"',
+                        page)
+                if videos:
+                    entries = [self.url_result('srgssr:%s' % video_urn, 'SRGSSR') for video_urn in videos]
+
+            if entries:
+                return self.playlist_result(entries, media_id, all_info.get('title'))
+

             internal_id = self._html_search_regex(
                 r'<(?:video|audio) data-id="([0-9]+)"', page,
                 'internal video id')
             all_info = download_json(internal_id)
 
             internal_id = self._html_search_regex(
                 r'<(?:video|audio) data-id="([0-9]+)"', page,
                 'internal video id')
             all_info = download_json(internal_id)
 

+        media_type = 'video' if 'video' in all_info else 'audio'
+
+        # check for errors
+        self.get_media_data('rts', media_type, media_id)
+

         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 

-        upload_timestamp = parse_iso8601(info.get('broadcast_date'))
-        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
-        if isinstance(duration, compat_str):
-            duration = parse_duration(duration)
-        view_count = info.get('plays')
-        thumbnail = unescapeHTML(info.get('preview_image_url'))
+        title = info['title']

 
         def extract_bitrate(url):
             return int_or_none(self._search_regex(
                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 
 
         def extract_bitrate(url):
             return int_or_none(self._search_regex(
                 r'-([0-9]+)k\.', url, 'bitrate', default=None))
 

-        formats = [{
-            'format_id': fid,
-            'url': furl,
-            'tbr': extract_bitrate(furl),
-        } for fid, furl in info['streams'].items()]
-
-        if 'media' in info:
-            formats.extend([{
-                'format_id': '%s-%sk' % (media['ext'], media['rate']),
-                'url': 'http://download-video.rts.ch/%s' % media['url'],
-                'tbr': media['rate'] or extract_bitrate(media['url']),
-            } for media in info['media'] if media.get('rate')])
-
+        formats = []
+        streams = info.get('streams', {})
+        for format_id, format_url in streams.items():
+            if format_id == 'hds_sd' and 'hds' in streams:
+                continue
+            if format_id == 'hls_sd' and 'hls' in streams:
+                continue
+            ext = determine_ext(format_url)
+            if ext in ('m3u8', 'f4m'):
+                format_url = self._get_tokenized_src(format_url, media_id, format_id)
+                if ext == 'f4m':
+                    formats.extend(self._extract_f4m_formats(
+                        format_url + ('?' if '?' not in format_url else '&') + 'hdcore=3.4.0',
+                        media_id, f4m_id=format_id, fatal=False))
+                else:
+                    formats.extend(self._extract_m3u8_formats(
+                        format_url, media_id, 'mp4', 'm3u8_native', m3u8_id=format_id, fatal=False))
+            else:
+                formats.append({
+                    'format_id': format_id,
+                    'url': format_url,
+                    'tbr': extract_bitrate(format_url),
+                })
+
+        for media in info.get('media', []):
+            media_url = media.get('url')
+            if not media_url or re.match(r'https?://', media_url):
+                continue
+            rate = media.get('rate')
+            ext = media.get('ext') or determine_ext(media_url, 'mp4')
+            format_id = ext
+            if rate:
+                format_id += '-%dk' % rate
+            formats.append({
+                'format_id': format_id,
+                'url': 'http://download-video.rts.ch/' + media_url,
+                'tbr': rate or extract_bitrate(media_url),
+            })
+
+        self._check_formats(formats, media_id)

         self._sort_formats(formats)
 
         self._sort_formats(formats)
 

+        duration = info.get('duration') or info.get('cutout') or info.get('cutduration')
+        if isinstance(duration, compat_str):
+            duration = parse_duration(duration)
+

         return {
         return {

-            'id': video_id,
+            'id': media_id,

             'display_id': display_id,
             'formats': formats,
             'display_id': display_id,
             'formats': formats,

-            'title': info['title'],
+            'title': title,

             'description': info.get('intro'),
             'duration': duration,
             'description': info.get('intro'),
             'duration': duration,

-            'view_count': view_count,
+            'view_count': int_or_none(info.get('plays')),

             'uploader': info.get('programName'),
             'uploader': info.get('programName'),

-            'timestamp': upload_timestamp,
-            'thumbnail': thumbnail,
+            'timestamp': parse_iso8601(info.get('broadcast_date')),
+            'thumbnail': unescapeHTML(info.get('preview_image_url')),

         }
         }