[toggo] Add extractor (#1961)

Authored by: nyuszika7h

yt_dlp/extractor/brightcove.py

@@ -472,32 +472,22 @@ def _extract_urls(ie, webpage):
     def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
         title = json_data['name'].strip()
 
-        num_drm_sources = 0
         formats, subtitles = [], {}
         sources = json_data.get('sources') or []
         for source in sources:
             container = source.get('container')
             ext = mimetype2ext(source.get('type'))
             src = source.get('src')
-            skip_unplayable = not self.get_param('allow_unplayable_formats')
+            if ext == 'm3u8' or container == 'M2TS':
-            # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
-            if skip_unplayable and (container == 'WVM' or source.get('key_systems')):
-                num_drm_sources += 1
-                continue
-            elif ext == 'ism' and skip_unplayable:
-                continue
-            elif ext == 'm3u8' or container == 'M2TS':
                 if not src:
                     continue
-                f, subs = self._extract_m3u8_formats_and_subtitles(
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
                     src, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False)
-                formats.extend(f)
                 subtitles = self._merge_subtitles(subtitles, subs)
             elif ext == 'mpd':
                 if not src:
                     continue
-                f, subs = self._extract_mpd_formats_and_subtitles(src, video_id, 'dash', fatal=False)
+                fmts, subs = self._extract_mpd_formats_and_subtitles(src, video_id, 'dash', fatal=False)
-                formats.extend(f)
                 subtitles = self._merge_subtitles(subtitles, subs)
             else:
                 streaming_src = source.get('streaming_src')
@@ -544,7 +534,13 @@ def build_format_id(kind):
                         'play_path': stream_name,
                         'format_id': build_format_id('rtmp'),
                     })
-                formats.append(f)
+                fmts = [f]
+
+            # https://support.brightcove.com/playback-api-video-fields-reference#key_systems_object
+            if container == 'WVM' or source.get('key_systems') or ext == 'ism':
+                for f in fmts:
+                    f['has_drm'] = True
+            formats.extend(fmts)
 
         if not formats:
             errors = json_data.get('errors')
@@ -552,9 +548,6 @@ def build_format_id(kind):
                 error = errors[0]
                 self.raise_no_formats(
                     error.get('message') or error.get('error_subcode') or error['error_code'], expected=True)
-            elif (not self.get_param('allow_unplayable_formats')
-                    and sources and num_drm_sources == len(sources)):
-                self.report_drm(video_id)
 
         self._sort_formats(formats)
 

yt_dlp/extractor/extractors.py

@@ -1513,6 +1513,9 @@
     ToggleIE,
     MeWatchIE,
 )
+from .toggo import (
+    ToggoIE,
+)
 from .tokentube import (
     TokentubeIE,
     TokentubeChannelIE

yt_dlp/extractor/toggo.py

@@ -0,0 +1,73 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, parse_qs
+
+
+class ToggoIE(InfoExtractor):
+    IE_NAME = 'toggo'
+    _VALID_URL = r'https?://(?:www\.)?toggo\.de/[\w-]+/folge/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://www.toggo.de/weihnachtsmann--co-kg/folge/ein-geschenk-fuer-zwei',
+        'info_dict': {
+            'id': 'VEP2977',
+            'ext': 'mp4',
+            'title': 'Ein Geschenk für zwei',
+            'display_id': 'ein-geschenk-fuer-zwei',
+            'thumbnail': r're:^https?://.*\.(?:jpg|png)',
+            'description': 'md5:b7715915bfa47824b4e4ad33fb5962f8',
+            'release_timestamp': 1637259179,
+            'series': 'Weihnachtsmann & Co. KG',
+            'season': 'Weihnachtsmann & Co. KG',
+            'season_number': 1,
+            'season_id': 'VST118',
+            'episode': 'Ein Geschenk für zwei',
+            'episode_number': 7,
+            'episode_id': 'VEP2977',
+            'timestamp': 1581935960,
+            'uploader_id': '6057955896001',
+            'upload_date': '20200217',
+        },
+        'params': {'skip_download': True},
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        data = self._download_json(
+            f'https://production-n.toggo.de/api/assetstore/vod/asset/{display_id}', display_id)['data']
+
+        brightcove_id = next(
+            x['value'] for x in data['custom_fields'] if x.get('key') == 'video-cloud-id')
+        info = self._downloader.get_info_extractor('BrightcoveNew').extract(
+            f'http://players.brightcove.net/6057955896001/default_default/index.html?videoId={brightcove_id}')
+
+        for f in info['formats']:
+            if '/dash/live/cenc/' in f.get('fragment_base_url', ''):
+                # Get hidden non-DRM format
+                f['fragment_base_url'] = f['fragment_base_url'].replace('/cenc/', '/clear/')
+                f['has_drm'] = False
+
+            if '/fairplay/' in f.get('manifest_url', ''):
+                f['has_drm'] = True
+
+        thumbnails = [{
+            'id': name,
+            'url': url,
+            'width': int_or_none(next(iter(parse_qs(url).get('width', [])), None)),
+        } for name, url in (data.get('images') or {}).items()]
+
+        return {
+            **info,
+            'id': data.get('id'),
+            'display_id': display_id,
+            'title': data.get('title'),
+            'language': data.get('language'),
+            'thumbnails': thumbnails,
+            'description': data.get('description'),
+            'release_timestamp': data.get('earliest_start_date'),
+            'series': data.get('series_title'),
+            'season': data.get('season_title'),
+            'season_number': data.get('season_no'),
+            'season_id': data.get('season_id'),
+            'episode': data.get('title'),
+            'episode_number': data.get('episode_no'),
+            'episode_id': data.get('id'),
+        }