[extractor/tempo] Add extractor (#4463)

Authored by: HobbyistDev

yt_dlp/YoutubeDL.py

@@ -1713,7 +1713,7 @@ class YoutubeDL:
         assert ie_result['_type'] in ('playlist', 'multi_video')
 
         common_info = self._playlist_infodict(ie_result, strict=True)
-        title = common_info.get('title') or '<Untitled>'
+        title = common_info.get('playlist') or '<Untitled>'
         if self._match_entry(common_info, incomplete=True) is not None:
             return
         self.to_screen(f'[download] Downloading {ie_result["_type"]}: {title}')
@@ -1733,8 +1733,8 @@ class YoutubeDL:
             # Better to do this after potentially exhausting entries
             ie_result['playlist_count'] = all_entries.get_full_count()
 
-        common_info = self._playlist_infodict(ie_result, n_entries=int_or_none(n_entries))
-        ie_copy = collections.ChainMap(ie_result, common_info)
+        ie_copy = collections.ChainMap(
+            ie_result, self._playlist_infodict(ie_result, n_entries=int_or_none(n_entries)))
 
         _infojson_written = False
         write_playlist_files = self.params.get('allow_playlist_files', True)
@@ -1782,6 +1782,7 @@ class YoutubeDL:
 
             extra = {
                 **common_info,
+                'n_entries': int_or_none(n_entries),
                 'playlist_index': playlist_index,
                 'playlist_autonumber': i + 1,
             }

yt_dlp/extractor/_extractors.py

@@ -1727,6 +1727,7 @@ from .telequebec import (
 )
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
+from .tempo import TempoIE
 from .tennistv import TennisTVIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE

yt_dlp/extractor/crunchyroll.py

@@ -649,7 +649,7 @@ Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text
 
 class CrunchyrollShowPlaylistIE(CrunchyrollBaseIE):
     IE_NAME = 'crunchyroll:playlist'
-    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{1,2}/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
+    _VALID_URL = r'https?://(?:(?P<prefix>www|m)\.)?(?P<url>crunchyroll\.com/(?:\w{2}(?:-\w{2})?/)?(?!(?:news|anime-news|library|forum|launchcalendar|lineup|store|comics|freetrial|login|media-\d+))(?P<id>[\w\-]+))/?(?:\?|$)'
 
     _TESTS = [{
         'url': 'https://www.crunchyroll.com/a-bridge-to-the-starry-skies-hoshizora-e-kakaru-hashi',
@@ -757,7 +757,7 @@ class CrunchyrollBetaBaseIE(CrunchyrollBaseIE):
 
 class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
     IE_NAME = 'crunchyroll:beta'
-    _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)watch/(?P<id>\w+)/(?P<display_id>[\w\-]*)/?(?:\?|$)'
+    _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{2}(?:-\w{2})?/)?)watch/(?P<id>\w+)/(?P<display_id>[\w\-]*)/?(?:\?|$)'
     _TESTS = [{
         'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y/to-the-future',
         'info_dict': {
@@ -801,6 +801,9 @@ class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
     }, {
         'url': 'https://beta.crunchyroll.com/watch/GY2P1Q98Y/',
         'only_matching': True,
+    }, {
+        'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -880,7 +883,7 @@ class CrunchyrollBetaIE(CrunchyrollBetaBaseIE):
 
 class CrunchyrollBetaShowIE(CrunchyrollBetaBaseIE):
     IE_NAME = 'crunchyroll:playlist:beta'
-    _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{1,2}/)?)series/(?P<id>\w+)/(?P<display_id>[\w\-]*)/?(?:\?|$)'
+    _VALID_URL = r'https?://beta\.crunchyroll\.com/(?P<lang>(?:\w{2}(?:-\w{2})?/)?)series/(?P<id>\w+)/(?P<display_id>[\w\-]*)/?(?:\?|$)'
     _TESTS = [{
         'url': 'https://beta.crunchyroll.com/series/GY19NQ2QR/Girl-Friend-BETA',
         'info_dict': {

yt_dlp/extractor/tempo.py

@@ -0,0 +1,53 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, parse_iso8601, str_or_none, traverse_obj
+
+
+class TempoIE(InfoExtractor):
+    _VALID_URL = r'https?://video\.tempo\.co/\w+/\d+/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://video.tempo.co/read/30058/anies-baswedan-ajukan-banding-putusan-ptun-batalkan-ump-dki',
+        'info_dict': {
+            'id': '2144438',
+            'ext': 'mp4',
+            'title': 'Anies Baswedan Ajukan Banding Putusan PTUN Batalkan UMP DKI',
+            'display_id': 'anies-baswedan-ajukan-banding-putusan-ptun-batalkan-ump-dki',
+            'duration': 84,
+            'description': 'md5:a6822b7c4c874fa7e5bd63e96a387b66',
+            'thumbnail': 'https://statik.tempo.co/data/2022/07/27/id_1128287/1128287_720.jpg',
+            'timestamp': 1658911277,
+            'upload_date': '20220727',
+            'tags': ['Anies Baswedan', ' PTUN', ' PTUN | Pengadilan Tata Usaha Negara', ' PTUN Batalkan UMP DKI', ' UMP DKI'],
+        }
+    }]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        player_key, widget_id = self._search_regex(
+            r'<ivs-player\s*[^>]+data-ivs-key\s*=\s*"(?P<player_key>[\w]+)[^>]+\bdata-ivs-wid="(?P<widget_id>[\w-]+)',
+            webpage, 'player_key, widget_id', group=('player_key', 'widget_id'))
+
+        json_ld_data = self._search_json_ld(webpage, display_id)
+
+        json_data = self._download_json(
+            f'https://ivxplayer.ivideosmart.com/prod/widget/{widget_id}',
+            display_id, query={'key': player_key})
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            json_data['player']['video_url'], display_id, ext='mp4')
+
+        return {
+            'id': str(json_data['ivx']['id']),
+            'display_id': display_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'title': (self._html_search_meta('twitter:title', webpage) or self._og_search_title(webpage)
+                      or traverse_obj(json_data, ('ivx', 'name'))),
+            'duration': int_or_none(traverse_obj(json_data, ('ivx', 'duration'))),
+            'thumbnail': (self._html_search_meta('twitter:image:src', webpage) or self._og_search_thumbnail(webpage)
+                          or traverse_obj(json_data, ('ivx', 'thumbnail_url'))),
+            'description': (json_ld_data.get('description') or self._html_search_meta(['description', 'twitter:description'], webpage)
+                            or self._og_search_description(webpage)),
+            'timestamp': parse_iso8601(traverse_obj(json_data, ('ivx', 'created_at'))),
+            'tags': str_or_none(self._html_search_meta('keywords', webpage), '').split(','),
+        }