Merge d5de6295cf294cc5f93b07dad4f868b4d12b380a into 3eb8d22ddb8982ca4fb56bb7a8d6517538bf14c6

* thx seproDev, yt-dlp/yt-dlp/pull/12694/commits/ae69e3c
* also add documenting comment in `InfoExtractor`

youtube_dl/extractor/bokecc.py

@@ -32,7 +32,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

youtube_dl/extractor/cloudy.py

@@ -9,7 +9,7 @@ from ..utils import (
 
 
 class CloudyIE(InfoExtractor):
-    _IE_DESC = 'cloudy.ec'
+    IE_DESC = 'cloudy.ec'
     _VALID_URL = r'https?://(?:www\.)?cloudy\.ec/(?:v/|embed\.php\?.*?\bid=)(?P<id>[A-Za-z0-9]+)'
     _TESTS = [{
         'url': 'https://www.cloudy.ec/v/af511e2527aac',

youtube_dl/extractor/common.py

@@ -422,6 +422,8 @@ class InfoExtractor(object):
     _GEO_COUNTRIES = None
     _GEO_IP_BLOCKS = None
     _WORKING = True
+    # supply this in public subclasses: used in supported sites list, etc
+    # IE_DESC = 'short description of IE'
 
     def __init__(self, downloader=None):
         """Constructor. Receives an optional downloader."""

youtube_dl/extractor/itv.py

@@ -35,15 +35,6 @@ from ..utils import (
 
 class ITVBaseIE(InfoExtractor):
 
-    def _search_nextjs_data(self, webpage, video_id, **kw):
-        transform_source = kw.pop('transform_source', None)
-        fatal = kw.pop('fatal', True)
-        return self._parse_json(
-            self._search_regex(
-                r'''<script\b[^>]+\bid=('|")__NEXT_DATA__\1[^>]*>(?P<js>[^<]+)</script>''',
-                webpage, 'next.js data', group='js', fatal=fatal, **kw),
-            video_id, transform_source=transform_source, fatal=fatal)
-
     def __handle_request_webpage_error(self, err, video_id=None, errnote=None, fatal=True):
         if errnote is False:
             return False
@@ -109,7 +100,9 @@ class ITVBaseIE(InfoExtractor):
 
 class ITVIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?:(?P<w>watch)|hub)/[^/]+/(?(w)[\w-]+/)(?P<id>\w+)'
-    _IE_DESC = 'ITVX'
+    IE_DESC = 'ITVX'
+    _WORKING = False
+
     _TESTS = [{
         'note': 'Hub URLs redirect to ITVX',
         'url': 'https://www.itv.com/hub/liar/2a4547a0012',
@@ -270,7 +263,7 @@ class ITVIE(ITVBaseIE):
                 'ext': determine_ext(href, 'vtt'),
             })
 
-        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default='{}')
+        next_data = self._search_nextjs_data(webpage, video_id, fatal=False, default={})
         video_data.update(traverse_obj(next_data, ('props', 'pageProps', ('title', 'episode')), expected_type=dict)[0] or {})
         title = traverse_obj(video_data, 'headerTitle', 'episodeTitle')
         info = self._og_extract(webpage, require_title=not title)
@@ -323,7 +316,7 @@ class ITVIE(ITVBaseIE):
 
 class ITVBTCCIE(ITVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?itv\.com/(?!(?:watch|hub)/)(?:[^/]+/)+(?P<id>[^/?#&]+)'
-    _IE_DESC = 'ITV articles: News, British Touring Car Championship'
+    IE_DESC = 'ITV articles: News, British Touring Car Championship'
     _TESTS = [{
         'note': 'British Touring Car Championship',
         'url': 'https://www.itv.com/btcc/articles/btcc-2018-all-the-action-from-brands-hatch',

youtube_dl/extractor/senateisvp.py

@@ -47,7 +47,7 @@ class SenateISVPIE(InfoExtractor):
         ['vetaff', '76462', 'http://vetaff-f.akamaihd.net'],
         ['arch', '', 'http://ussenate-f.akamaihd.net/']
     ]
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _TESTS = [{
         'url': 'http://www.senate.gov/isvp/?comm=judiciary&type=live&stt=&filename=judiciary031715&auto_play=false&wmode=transparent&poster=http%3A%2F%2Fwww.judiciary.senate.gov%2Fthemes%2Fjudiciary%2Fimages%2Fvideo-poster-flash-fit.png',

youtube_dl/extractor/toggle.py

@@ -1,13 +1,9 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
 import json
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
-    ExtractorError,
     float_or_none,
     int_or_none,
     parse_iso8601,
@@ -16,219 +12,292 @@ from ..utils import (
 
 
 class ToggleIE(InfoExtractor):
-    IE_NAME = 'toggle'
-    _VALID_URL = r'(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:en|zh)/(?:[^/]+/){2,}|toggle:)(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
-        'info_dict': {
-            'id': '343115',
-            'ext': 'mp4',
-            'title': 'Lion Moms Premiere',
-            'description': 'md5:aea1149404bff4d7f7b6da11fafd8e6b',
-            'upload_date': '20150910',
-            'timestamp': 1441858274,
+    IE_NAME = "toggle"
+    _VALID_URL = r"(?:https?://(?:(?:www\.)?mewatch|video\.toggle)\.sg/(?:[^/]+/){1,}|toggle:)[^/]+-(?P<id>[0-9]+)"
+    _TESTS = [
+        {
+            ### to be updated
+            ### deprecated
+            # 'url': 'http://www.mewatch.sg/en/series/lion-moms-tif/trailers/lion-moms-premier/343115',
+            "info_dict": {
+                "id": "343115",
+                "ext": "mp4",
+                "title": "Lion Moms Premiere",
+                "description": "md5:aea1149404bff4d7f7b6da11fafd8e6b",
+                "upload_date": "20150910",
+                "timestamp": 1441858274,
+            },
+            "params": {
+                "skip_download": "m3u8 download",
+            },
         },
-        'params': {
-            'skip_download': 'm3u8 download',
-        }
-    }, {
-        'note': 'DRM-protected video',
-        'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
-        'info_dict': {
-            'id': '341413',
-            'ext': 'wvm',
-            'title': 'Dug\'s Special Mission',
-            'description': 'md5:e86c6f4458214905c1772398fabc93e0',
-            'upload_date': '20150827',
-            'timestamp': 1440644006,
+        {
+            "note": "DRM-protected video",
+            ### url deprecated
+            # 'url': 'http://www.mewatch.sg/en/movies/dug-s-special-mission/341413',
+            "info_dict": {
+                "id": "341413",
+                "ext": "wvm",
+                "title": "Dug's Special Mission",
+                "description": "md5:e86c6f4458214905c1772398fabc93e0",
+                "upload_date": "20150827",
+                "timestamp": 1440644006,
+            },
+            "params": {
+                "skip_download": "DRM-protected wvm download",
+            },
         },
-        'params': {
-            'skip_download': 'DRM-protected wvm download',
-        }
-    }, {
-        # this also tests correct video id extraction
-        'note': 'm3u8 links are geo-restricted, but Android/mp4 is okay',
-        'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
-        'info_dict': {
-            'id': '332861',
-            'ext': 'mp4',
-            'title': '28th SEA Games (5 Show) -  Episode  11',
-            'description': 'md5:3cd4f5f56c7c3b1340c50a863f896faa',
-            'upload_date': '20150605',
-            'timestamp': 1433480166,
+        {
+            # this also tests correct video id extraction
+            "note": "m3u8 links are geo-restricted, but Android/mp4 is okay",
+            ### url deprecated
+            # 'url': 'http://www.mewatch.sg/en/series/28th-sea-games-5-show/28th-sea-games-5-show-ep11/332861',
+            "info_dict": {
+                "id": "332861",
+                "ext": "mp4",
+                "title": "28th SEA Games (5 Show) -  Episode  11",
+                "description": "md5:3cd4f5f56c7c3b1340c50a863f896faa",
+                "upload_date": "20150605",
+                "timestamp": 1433480166,
+            },
+            "params": {
+                "skip_download": "DRM-protected wvm download",
+            },
+            "skip": "m3u8 links are geo-restricted",
         },
-        'params': {
-            'skip_download': 'DRM-protected wvm download',
+        {
+            ### video.toggle.sg seems deprecated
+            # 'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
+            "only_matching": True,
         },
-        'skip': 'm3u8 links are geo-restricted'
-    }, {
-        'url': 'http://video.toggle.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/clips/seraph-sun-aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set/343331',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/zh/series/zero-calling-s2-hd/ep13/336367',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/movies/seven-days/321936',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
-        'only_matching': True,
-    }]
+        {
+            "url": "https://www.mewatch.sg/clips/Seraph-Sun-Aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set-84901",
+            "only_matching": True,
+        },
+        {
+            "url": "https://www.mewatch.sg/episode/Zero-Calling-S2-E13-The-End-of-The-Beginning-55137",
+            "only_matching": True,
+        },
+        {
+            ### webisodes no longer used
+            "url": "https://www.mewatch.sg/clips/Jeeva-is-an-orphan-Vetri-S2-Webisode-7-84944",
+            # 'url': 'http://www.mewatch.sg/en/series/vetri-s2/webisodes/jeeva-is-an-orphan-vetri-s2-webisode-7/342302',
+            "only_matching": True,
+        },
+        {
+            ### only available in Singapore 403 forbidden
+            "url": "https://www.mewatch.sg/movie/Seven-Days-79641",
+            "only_matching": True,
+        },
+        {
+            ### not working for this list, but not a big issue since old path deprecated
+            "url": "https://www.mewatch.sg/list/CNA-Singapore-Tonight-154904",
+            # 'url': 'https://www.mewatch.sg/en/tv-show/news/may-2017-cna-singapore-tonight/fri-19-may-2017/512456',
+            "only_matching": True,
+        },
+        {
+            ### not working. seems deprecated
+            # 'url': 'http://www.mewatch.sg/en/channels/eleven-plus/401585',
+            "only_matching": True,
+        },
+        {
+            ### [20230507:shouldsee] working
+            "url": "https://www.mewatch.sg/watch/Seraph-Sun-Aloysius-will-suddenly-sing-some-old-songs-in-high-pitch-on-set-84901",
+            "only_matching": True,
+        },
+    ]
 
-    _API_USER = 'tvpapi_147'
-    _API_PASS = '11111'
+    _API_USER = "tvpapi_147"
+    _API_PASS = "11111"
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
+        lang = "en"
         params = {
-            'initObj': {
-                'Locale': {
-                    'LocaleLanguage': '',
-                    'LocaleCountry': '',
-                    'LocaleDevice': '',
-                    'LocaleUserState': 0
-                },
-                'Platform': 0,
-                'SiteGuid': 0,
-                'DomainID': '0',
-                'UDID': '',
-                'ApiUser': self._API_USER,
-                'ApiPass': self._API_PASS
-            },
-            'MediaID': video_id,
-            'mediaType': 0,
+            "delivery": "stream,progressive",
+            "resolution": "External",
+            "segments": "all",
+            "lang": lang,
+            "ff": "idp,ldp,rpt,cd",
         }
+        video_info = self._download_json(
+            "https://cdn.mewatch.sg/api/items/" + video_id + "/videos",
+            video_id,
+            "Downloading video info json",
+            query=params,
+        )
 
-        info = self._download_json(
-            'http://tvpapi.as.tvinci.com/v2_9/gateways/jsonpostgw.aspx?m=GetMediaInfo',
-            video_id, 'Downloading video info json', data=json.dumps(params).encode('utf-8'))
+        params = {
+            # 'delivery':'stream,progressive',
+            # 'resolution':'External',
+            "segments": "all",
+            "lang": lang,
+            "ff": "idp,ldp,rpt,cd",
+        }
+        meta_info = self._download_json(
+            "https://cdn.mewatch.sg/api/items/" + video_id,
+            video_id,
+            "Downloading video info json",
+            query=params,
+        )
 
-        title = info['MediaName']
+        # urls = info
+        info = {"Files": video_info}
+        info.update(meta_info)
 
+        title = info["path"].rsplit("/", 1)[-1]
         formats = []
-        for video_file in info.get('Files', []):
-            video_url, vid_format = video_file.get('URL'), video_file.get('Format')
-            if not video_url or video_url == 'NA' or not vid_format:
+
+        for video_file in info.get("Files", []):
+            video_url, vid_format = video_file.get("url"), video_file.get("format")
+            if not video_url or video_url == "NA" or not vid_format:
                 continue
             ext = determine_ext(video_url)
-            vid_format = vid_format.replace(' ', '')
+            vid_format = vid_format.replace(" ", "")
             # if geo-restricted, m3u8 is inaccessible, but mp4 is okay
-            if ext == 'm3u8':
+            if ext == "m3u8":
                 m3u8_formats = self._extract_m3u8_formats(
-                    video_url, video_id, ext='mp4', m3u8_id=vid_format,
-                    note='Downloading %s m3u8 information' % vid_format,
-                    errnote='Failed to download %s m3u8 information' % vid_format,
-                    fatal=False)
+                    video_url,
+                    video_id,
+                    ext="mp4",
+                    m3u8_id=vid_format,
+                    note="Downloading %s m3u8 information" % vid_format,
+                    errnote="Failed to download %s m3u8 information" % vid_format,
+                    fatal=False,
+                )
                 for f in m3u8_formats:
                     # Apple FairPlay Streaming
-                    if '/fpshls/' in f['url']:
+                    if "/fpshls/" in f["url"]:
                         continue
                     formats.append(f)
-            elif ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(
-                    video_url, video_id, mpd_id=vid_format,
-                    note='Downloading %s MPD manifest' % vid_format,
-                    errnote='Failed to download %s MPD manifest' % vid_format,
-                    fatal=False))
-            elif ext == 'ism':
-                formats.extend(self._extract_ism_formats(
-                    video_url, video_id, ism_id=vid_format,
-                    note='Downloading %s ISM manifest' % vid_format,
-                    errnote='Failed to download %s ISM manifest' % vid_format,
-                    fatal=False))
-            elif ext == 'mp4':
-                formats.append({
-                    'ext': ext,
-                    'url': video_url,
-                    'format_id': vid_format,
-                })
+            elif ext == "mpd":
+                formats.extend(
+                    self._extract_mpd_formats(
+                        video_url,
+                        video_id,
+                        mpd_id=vid_format,
+                        note="Downloading %s MPD manifest" % vid_format,
+                        errnote="Failed to download %s MPD manifest" % vid_format,
+                        fatal=False,
+                    )
+                )
+            elif ext == "ism":
+                formats.extend(
+                    self._extract_ism_formats(
+                        video_url,
+                        video_id,
+                        ism_id=vid_format,
+                        note="Downloading %s ISM manifest" % vid_format,
+                        errnote="Failed to download %s ISM manifest" % vid_format,
+                        fatal=False,
+                    )
+                )
+            elif ext == "mp4":
+                formats.append(
+                    {
+                        "ext": ext,
+                        "url": video_url,
+                        "format_id": vid_format,
+                    }
+                )
         if not formats:
-            for meta in (info.get('Metas') or []):
-                if meta.get('Key') == 'Encryption' and meta.get('Value') == '1':
-                    raise ExtractorError(
-                        'This video is DRM protected.', expected=True)
-            # Most likely because geo-blocked
-            raise ExtractorError('No downloadable videos found', expected=True)
-        self._sort_formats(formats)
+            for meta in info.get("Metas") or []:
+                if (
+                    not self.get_param("allow_unplayable_formats")
+                    and meta.get("Key") == "Encryption"
+                    and meta.get("Value") == "1"
+                ):
+                    self.report_drm(video_id)
+            # Most likely because geo-blocked if no formats and no DRM
 
         thumbnails = []
-        for picture in info.get('Pictures', []):
+        for picture in info.get("images", []):
             if not isinstance(picture, dict):
                 continue
-            pic_url = picture.get('URL')
+            pic_url = picture.get("tile")
             if not pic_url:
                 continue
             thumbnail = {
-                'url': pic_url,
+                "url": pic_url,
             }
-            pic_size = picture.get('PicSize', '')
-            m = re.search(r'(?P<width>\d+)[xX](?P<height>\d+)', pic_size)
+            pic_size = picture.get("PicSize", "")
+            m = re.search(r"(?P<width>\d+)[xX](?P<height>\d+)", pic_size)
             if m:
-                thumbnail.update({
-                    'width': int(m.group('width')),
-                    'height': int(m.group('height')),
-                })
+                thumbnail.update(
+                    {
+                        "width": int(m.group("width")),
+                        "height": int(m.group("height")),
+                    }
+                )
             thumbnails.append(thumbnail)
 
         def counter(prefix):
             return int_or_none(
-                info.get(prefix + 'Counter') or info.get(prefix.lower() + '_counter'))
+                info.get(prefix + "Counter") or info.get(prefix.lower() + "_counter")
+            )
 
         return {
-            'id': video_id,
-            'title': title,
-            'description': strip_or_none(info.get('Description')),
-            'duration': int_or_none(info.get('Duration')),
-            'timestamp': parse_iso8601(info.get('CreationDate') or None),
-            'average_rating': float_or_none(info.get('Rating')),
-            'view_count': counter('View'),
-            'like_count': counter('Like'),
-            'thumbnails': thumbnails,
-            'formats': formats,
+            "id": video_id,
+            "title": title,
+            "description": strip_or_none(info.get("Description")),
+            "duration": int_or_none(info.get("Duration")),
+            "timestamp": parse_iso8601(info.get("CreationDate") or None),
+            "average_rating": float_or_none(info.get("Rating")),
+            "view_count": counter("View"),
+            "like_count": counter("Like"),
+            "thumbnails": thumbnails,
+            "formats": formats,
         }
 
 
 class MeWatchIE(InfoExtractor):
-    IE_NAME = 'mewatch'
-    _VALID_URL = r'https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)'
-    _TESTS = [{
-        'url': 'https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371',
-        'info_dict': {
-            'id': '1008625',
-            'ext': 'mp4',
-            'title': 'Recipe Of Life 味之道',
-            'timestamp': 1603306526,
-            'description': 'md5:6e88cde8af2068444fc8e1bc3ebf257c',
-            'upload_date': '20201021',
+    IE_NAME = "mewatch"
+    _VALID_URL = (
+        r"https?://(?:(?:www|live)\.)?mewatch\.sg/watch/[^/?#&]+-(?P<id>[0-9]+)"
+    )
+    _TESTS = [
+        {
+            "url": "https://www.mewatch.sg/watch/Recipe-Of-Life-E1-179371",
+            "info_dict": {
+                "id": "1008625",
+                "ext": "mp4",
+                "title": "Recipe Of Life 味之道",
+                "timestamp": 1603306526,
+                "description": "md5:6e88cde8af2068444fc8e1bc3ebf257c",
+                "upload_date": "20201021",
+            },
+            "params": {
+                "skip_download": "m3u8 download",
+            },
         },
-        'params': {
-            'skip_download': 'm3u8 download',
+        {
+            "url": "https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232",
+            "only_matching": True,
         },
-    }, {
-        'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-搜密。打卡。小红点-S2-E1-176232',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232',
-        'only_matching': True,
-    }, {
-        'url': 'https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759',
-        'only_matching': True,
-    }]
+        {
+            "url": "https://www.mewatch.sg/watch/Little-Red-Dot-Detectives-S2-%E6%90%9C%E5%AF%86%E3%80%82%E6%89%93%E5%8D%A1%E3%80%82%E5%B0%8F%E7%BA%A2%E7%82%B9-S2-E1-176232",
+            "only_matching": True,
+        },
+        {
+            "url": "https://live.mewatch.sg/watch/Recipe-Of-Life-E41-189759",
+            "only_matching": True,
+        },
+    ]
 
     def _real_extract(self, url):
         item_id = self._match_id(url)
-        custom_id = self._download_json(
-            'https://cdn.mewatch.sg/api/items/' + item_id,
-            item_id, query={'segments': 'all'})['customId']
-        return self.url_result(
-            'toggle:' + custom_id, ToggleIE.ie_key(), custom_id)
+        return self.url_result("toggle:" + item_id, ToggleIE.ie_key(), item_id)
+
+        print(f"[debug]{item_id}")
+        xdata = self._download_json(
+            "https://cdn.mewatch.sg/api/items/" + item_id,
+            item_id,
+            query={"segments": "all", "lang": "en", "ff": "idp,ldp,rpt,cd"},
+        )
+        from pprint import pprint
+
+        pprint(xdata)
+        custom_id = xdata["customId"]
+        print(f"[debug]{custom_id}")
+        return self.url_result("toggle:" + custom_id, ToggleIE.ie_key(), custom_id)

youtube_dl/jsinterp.py

@@ -686,6 +686,8 @@ class JSInterpreter(object):
             raise self.Exception('Cannot get index {idx!r:.100}'.format(**locals()), expr=repr(obj), cause=e)
 
     def _dump(self, obj, namespace):
+        if obj is JS_Undefined:
+            return 'undefined'
         try:
             return json.dumps(obj)
         except TypeError: