Merge pull request #5 from ytdl-org/master

02.03.2020 Master merge

youtube_dl/extractor/peertube.py

@@ -8,6 +8,7 @@ from ..compat import compat_str
 from ..utils import (
     int_or_none,
     parse_resolution,
+    str_or_none,
     try_get,
     unified_timestamp,
     url_or_none,
@@ -415,6 +416,7 @@ class PeerTubeIE(InfoExtractor):
                             peertube\.cpy\.re
                         )'''
     _UUID_RE = r'[\da-fA-F]{8}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{4}-[\da-fA-F]{12}'
+    _API_BASE = 'https://%s/api/v1/videos/%s/%s'
     _VALID_URL = r'''(?x)
                     (?:
                         peertube:(?P<host>[^:]+):|
@@ -423,26 +425,30 @@ class PeerTubeIE(InfoExtractor):
                     (?P<id>%s)
                     ''' % (_INSTANCES_RE, _UUID_RE)
     _TESTS = [{
-        'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
+        'url': 'https://framatube.org/videos/watch/9c9de5e8-0a1e-484a-b099-e80766180a6d',
-        'md5': '80f24ff364cc9d333529506a263e7feb',
+        'md5': '9bed8c0137913e17b86334e5885aacff',
         'info_dict': {
-            'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c',
+            'id': '9c9de5e8-0a1e-484a-b099-e80766180a6d',
             'ext': 'mp4',
-            'title': 'wow',
+            'title': 'What is PeerTube?',
-            'description': 'wow such video, so gif',
+            'description': 'md5:3fefb8dde2b189186ce0719fda6f7b10',
             'thumbnail': r're:https?://.*\.(?:jpg|png)',
-            'timestamp': 1519297480,
+            'timestamp': 1538391166,
-            'upload_date': '20180222',
+            'upload_date': '20181001',
-            'uploader': 'Luclu7',
+            'uploader': 'Framasoft',
-            'uploader_id': '7fc42640-efdb-4505-a45d-a15b1a5496f1',
+            'uploader_id': '3',
-            'uploder_url': 'https://peertube.nsa.ovh/accounts/luclu7',
+            'uploader_url': 'https://framatube.org/accounts/framasoft',
-            'license': 'Unknown',
+            'channel': 'Les vidéos de Framasoft',
-            'duration': 3,
+            'channel_id': '2',
+            'channel_url': 'https://framatube.org/video-channels/bf54d359-cfad-4935-9d45-9d6be93f63e8',
+            'language': 'en',
+            'license': 'Attribution - Share Alike',
+            'duration': 113,
             'view_count': int,
             'like_count': int,
             'dislike_count': int,
-            'tags': list,
+            'tags': ['framasoft', 'peertube'],
-            'categories': list,
+            'categories': ['Science & Technology'],
         }
     }, {
         'url': 'https://peertube.tamanoir.foucry.net/videos/watch/0b04f13d-1e18-4f1d-814e-4979aa7c9c44',
@@ -484,13 +490,38 @@ class PeerTubeIE(InfoExtractor):
                 entries = [peertube_url]
         return entries
 
+    def _call_api(self, host, video_id, path, note=None, errnote=None, fatal=True):
+        return self._download_json(
+            self._API_BASE % (host, video_id, path), video_id,
+            note=note, errnote=errnote, fatal=fatal)
+
+    def _get_subtitles(self, host, video_id):
+        captions = self._call_api(
+            host, video_id, 'captions', note='Downloading captions JSON',
+            fatal=False)
+        if not isinstance(captions, dict):
+            return
+        data = captions.get('data')
+        if not isinstance(data, list):
+            return
+        subtitles = {}
+        for e in data:
+            language_id = try_get(e, lambda x: x['language']['id'], compat_str)
+            caption_url = urljoin('https://%s' % host, e.get('captionPath'))
+            if not caption_url:
+                continue
+            subtitles.setdefault(language_id or 'en', []).append({
+                'url': caption_url,
+            })
+        return subtitles
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         host = mobj.group('host') or mobj.group('host_2')
         video_id = mobj.group('id')
 
-        video = self._download_json(
+        video = self._call_api(
-            'https://%s/api/v1/videos/%s' % (host, video_id), video_id)
+            host, video_id, '', note='Downloading video JSON')
 
         title = video['name']
 
@@ -513,10 +544,28 @@ class PeerTubeIE(InfoExtractor):
             formats.append(f)
         self._sort_formats(formats)
 
-        def account_data(field):
+        full_description = self._call_api(
-            return try_get(video, lambda x: x['account'][field], compat_str)
+            host, video_id, 'description', note='Downloading description JSON',
+            fatal=False)
 
-        category = try_get(video, lambda x: x['category']['label'], compat_str)
+        description = None
+        if isinstance(full_description, dict):
+            description = str_or_none(full_description.get('description'))
+        if not description:
+            description = video.get('description')
+
+        subtitles = self.extract_subtitles(host, video_id)
+
+        def data(section, field, type_):
+            return try_get(video, lambda x: x[section][field], type_)
+
+        def account_data(field, type_):
+            return data('account', field, type_)
+
+        def channel_data(field, type_):
+            return data('channel', field, type_)
+
+        category = data('category', 'label', compat_str)
         categories = [category] if category else None
 
         nsfw = video.get('nsfw')
@@ -528,14 +577,17 @@ class PeerTubeIE(InfoExtractor):
         return {
             'id': video_id,
             'title': title,
-            'description': video.get('description'),
+            'description': description,
             'thumbnail': urljoin(url, video.get('thumbnailPath')),
             'timestamp': unified_timestamp(video.get('publishedAt')),
-            'uploader': account_data('displayName'),
+            'uploader': account_data('displayName', compat_str),
-            'uploader_id': account_data('uuid'),
+            'uploader_id': str_or_none(account_data('id', int)),
-            'uploder_url': account_data('url'),
+            'uploader_url': url_or_none(account_data('url', compat_str)),
-            'license': try_get(
+            'channel': channel_data('displayName', compat_str),
-                video, lambda x: x['licence']['label'], compat_str),
+            'channel_id': str_or_none(channel_data('id', int)),
+            'channel_url': url_or_none(channel_data('url', compat_str)),
+            'language': data('language', 'id', compat_str),
+            'license': data('licence', 'label', compat_str),
             'duration': int_or_none(video.get('duration')),
             'view_count': int_or_none(video.get('views')),
             'like_count': int_or_none(video.get('likes')),
@@ -544,4 +596,5 @@ class PeerTubeIE(InfoExtractor):
             'tags': try_get(video, lambda x: x['tags'], list),
             'categories': categories,
             'formats': formats,
+            'subtitles': subtitles
         }

youtube_dl/extractor/servus.py

@@ -7,9 +7,18 @@ from .common import InfoExtractor
 
 
 class ServusIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)/(?P<id>[aA]{2}-\w+|\d+-\d+)'
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            servus\.com/(?:(?:at|de)/p/[^/]+|tv/videos)|
+                            servustv\.com/videos
+                        )
+                        /(?P<id>[aA]{2}-\w+|\d+-\d+)
+                    '''
     _TESTS = [{
-        'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
+        # new URL schema
+        'url': 'https://www.servustv.com/videos/aa-1t6vbu5pw1w12/',
         'md5': '3e1dd16775aa8d5cbef23628cfffc1f4',
         'info_dict': {
             'id': 'AA-1T6VBU5PW1W12',
@@ -18,6 +27,10 @@ class ServusIE(InfoExtractor):
             'description': 'md5:1247204d85783afe3682644398ff2ec4',
             'thumbnail': r're:^https?://.*\.jpg',
         }
+    }, {
+        # old URL schema
+        'url': 'https://www.servus.com/de/p/Die-Gr%C3%BCnen-aus-Sicht-des-Volkes/AA-1T6VBU5PW1W12/',
+        'only_matching': True,
     }, {
         'url': 'https://www.servus.com/at/p/Wie-das-Leben-beginnt/1309984137314-381415152/',
         'only_matching': True,

youtube_dl/extractor/vimeo.py

@@ -33,6 +33,7 @@ from ..utils import (
     unified_timestamp,
     unsmuggle_url,
     urlencode_postdata,
+    urljoin,
     unescapeHTML,
 )
 
@@ -191,7 +192,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             for tt in text_tracks:
                 subtitles[tt['lang']] = [{
                     'ext': 'vtt',
-                    'url': 'https://vimeo.com' + tt['url'],
+                    'url': urljoin('https://vimeo.com', tt['url']),
                 }]
 
         thumbnails = []

youtube_dl/extractor/youtube.py

@@ -2495,20 +2495,23 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
     _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
     IE_NAME = 'youtube:playlist'
     _TESTS = [{
-        'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+        'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
         'info_dict': {
-            'title': 'ytdl test PL',
+            'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
-            'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
+            'uploader': 'Sergey M.',
+            'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
+            'title': 'youtube-dl public playlist',
         },
-        'playlist_count': 3,
+        'playlist_count': 1,
     }, {
-        'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
+        'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
         'info_dict': {
-            'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
+            'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
-            'title': 'YDL_Empty_List',
+            'uploader': 'Sergey M.',
+            'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
+            'title': 'youtube-dl empty playlist',
         },
         'playlist_count': 0,
-        'skip': 'This playlist is private',
     }, {
         'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
         'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
@@ -2518,7 +2521,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             'uploader': 'Christiaan008',
             'uploader_id': 'ChRiStIaAn008',
         },
-        'playlist_count': 95,
+        'playlist_count': 96,
     }, {
         'note': 'issue #673',
         'url': 'PLBB231211A4F62143',