Cleanup Part 1

Currently untested. More to come.

yt_dlp/extractor/drtv.py

@@ -1,26 +1,20 @@
-import binascii
-import hashlib
 import json
-import re
-import uuid
 
 from .common import InfoExtractor
-from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
-from ..compat import compat_etree_fromstring, compat_urllib_parse_unquote
 from ..utils import (
-    ExtractorError,
-    float_or_none,
     int_or_none,
     mimetype2ext,
-    str_or_none,
-    traverse_obj,
-    unified_timestamp,
+    parse_iso8601,
+    random_uuidv4,
+    try_call,
     update_url_query,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 SERIES_API = 'https://production-cdn.dr-massive.com/api/page?device=web_browser&item_detail_expand=all&lang=da&max_list_prefetch=3&path=%s'
 
+
 class DRTVIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
@@ -160,36 +154,73 @@ class DRTVIE(InfoExtractor):
         },
     }]
 
+    _TOKEN = None
+
+    def _real_initialize(self):
+        if self._TOKEN:
+            return
+        token_response = self._download_json(
+            'https://production.dr-massive.com/api/authorization/anonymous-sso', None,
+            note='Downloading anonymous token', headers={
+                'content-type': 'application/json',
+            },
+            query={
+                'device': 'web_browser',
+                'ff': 'idp,ldp,rpt',
+                'lang': 'da',
+                'supportFallbackToken': 'true',
+            },
+            data=json.dumps({
+                'deviceId': random_uuidv4(),
+                'scopes': [
+                    'Catalog',
+                ],
+                'optout': True,
+            }).encode('utf-8'))
+
+        self._TOKEN = traverse_obj(
+            token_response, (lambda _, x: x['type'] == 'UserAccount', 'value'), get_all=False)
+
     def _real_extract(self, url):
-        raw_video_id, is_radio_url = self._match_valid_url(url).group('id', 'radio')
+        raw_video_id = self._match_valid_url(url).group('id')
         webpage = self._download_webpage(url, raw_video_id)
-        if '>Programmet er ikke længere tilgængeligt' in webpage:
-            raise ExtractorError(
-                'Video %s is not available' % raw_video_id, expected=True)
-        json_data = self._search_json(r'window\.__data\s*=', webpage, 'data', raw_video_id)
-        item = traverse_obj(json_data, ('cache', 'page', Ellipsis, (None, ('entries', 0)), 'item'), get_all=False)
-        itemId = item.get('id')
-        videoId = item['customId'].split(':')[-1]
-        deviceId = uuid.uuid1()
-        token = self._download_json('https://isl.dr-massive.com/api/authorization/anonymous-sso?device=web_browser&ff=idp%2Cldp&lang=da', videoId, headers={'Content-Type': 'application/json'}, data=json.dumps({'deviceId': str(deviceId), 'scopes': ['Catalog'], 'optout': True}).encode('utf-8'))[0]['value']
-        data = self._download_json('https://production.dr-massive.com/api/account/items/{0}/videos?delivery=stream&device=web_browser&ff=idp%2Cldp%2Crpt&lang=da&resolution=HD-1080&sub=Anonymous'.format(itemId), videoId, headers={'authorization': 'Bearer {0}'.format(token)})
+
+        json_data = self._search_json(r'window\.__data\s*=\s*', webpage, 'data', raw_video_id)
+        item = traverse_obj(json_data, ('cache', 'page', ..., (None, ('entries', 0)), 'item'), get_all=False) or {}
+        item_id = item.get('id') or raw_video_id.rsplit('_', 1)[-1]
+        video_id = try_call(item['customId'].split(':')[-1]) or item_id
+
+        stream_data = self._download_json(
+            f'https://production.dr-massive.com/api/account/items/{item_id}/videos', video_id, query={
+                'delivery': 'stream',
+                'device': 'web_browser',
+                'ff': 'idp,ldp,rpt',
+                'lang': 'da',
+                'resolution': 'HD-1080',
+                'sub': 'Anonymous',
+            },
+            headers={
+                'authorization': f'Bearer {self._TOKEN}',
+            })
+
         formats = []
         subtitles = {}
-        for fmt in data:
+        for fmt in stream_data:
             format_id = fmt.get('format', 'na')
             access_service = fmt.get('accessService')
             preference = None
-            if accessService in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
+            if access_service in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
                 preference = -1
-                formatId += '-%s' % accessService
-            elif accessService == 'StandardVideo':
+                format_id += '-%s' % access_service
+            elif access_service == 'StandardVideo':
                 preference = 1
-            fmts, subs = self._extract_m3u8_formats_and_subtitles(fmt['url'], videoId, 'mp4', entry_protocol='m3u8_native', preference=preference, m3u8_id=formatId, fatal=False)
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(fmt['url'], video_id, preference=preference, m3u8_id=format_id, fatal=False)
             formats.extend(fmts)
             self._merge_subtitles(subs, target=subtitles)
             LANGS = {
-                'Danish': 'da',
+                'DanishLanguageSubtitles': 'da',
             }
+
             for subs in fmt['subtitles']:
                 if not isinstance(subs, dict):
                     continue
@@ -201,15 +232,28 @@ class DRTVIE(InfoExtractor):
                     'url': sub_uri,
                     'ext': mimetype2ext(subs.get('format')) or 'vtt'
                 })
-            
+
         return {
-            'id': videoId,
-            'title': item.get('episodeName'),
-            'description': item.get('description'),
+            'id': video_id,
             'formats': formats,
             'subtitles': subtitles,
+            **traverse_obj(item, {
+                'title': 'title',
+                'description': 'description',
+                'thumbnail': ('images', 'wallpaper'),
+                'timestamp': ('customFields', 'BroadcastTimeDK', {parse_iso8601}),
+                'duration': 'duration',
+                'series': ('season', 'title'),
+                'season': ('season', 'show', 'title'),
+                'season_number': ('season', 'seasonNumber', {int_or_none}),
+                'season_id': 'seasonId',
+                'episode': 'episodeName',
+                'episode_number': ('episodeNumber', {int_or_none}),
+                'release_year': 'releaseYear',
+            }),
         }
 
+
 class DRTVLiveIE(InfoExtractor):
     IE_NAME = 'drtv:live'
     _VALID_URL = r'https?://(?:www\.)?dr\.dk/(?:tv|TV)/live/(?P<id>[\da-z-]+)'
@@ -264,6 +308,7 @@ class DRTVLiveIE(InfoExtractor):
             'is_live': True,
         }
 
+
 class DRTVSeasonIE(InfoExtractor):
     IE_NAME = 'drtv:season'
     _VALID_URL = r'https?://(?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/saeson/(?P<display_id>[\w-]+)_(?P<id>\d+)'