[cleanup] Misc (#5044)

Authored by: gamer191, pukkandan

yt_dlp/extractor/acfun.py

@@ -84,7 +84,7 @@ class AcFunVideoIE(AcFunVideoBaseIE):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
-        json_all = self._search_json(r'window.videoInfo\s*=\s*', webpage, 'videoInfo', video_id)
+        json_all = self._search_json(r'window.videoInfo\s*=', webpage, 'videoInfo', video_id)
 
         title = json_all.get('title')
         video_list = json_all.get('videoList') or []
@@ -164,7 +164,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
         video_id = f'{video_id}{format_field(ac_idx, template="__%s")}'
 
         webpage = self._download_webpage(url, video_id)
-        json_bangumi_data = self._search_json(r'window.bangumiData\s*=\s*', webpage, 'bangumiData', video_id)
+        json_bangumi_data = self._search_json(r'window.bangumiData\s*=', webpage, 'bangumiData', video_id)
 
         if ac_idx:
             video_info = json_bangumi_data['hlVideoInfo']
@@ -181,7 +181,7 @@ class AcFunBangumiIE(AcFunVideoBaseIE):
             if v.get('id') == season_id), 1)
 
         json_bangumi_list = self._search_json(
-            r'window\.bangumiList\s*=\s*', webpage, 'bangumiList', video_id, fatal=False)
+            r'window\.bangumiList\s*=', webpage, 'bangumiList', video_id, fatal=False)
         video_internal_id = int_or_none(traverse_obj(json_bangumi_data, ('currentVideoInfo', 'id')))
         episode_number = video_internal_id and next((
             idx for idx, v in enumerate(json_bangumi_list.get('items') or [], 1)

yt_dlp/extractor/anvato.py

@@ -10,11 +10,11 @@ from ..aes import aes_encrypt
 from ..utils import (
     bytes_to_intlist,
     determine_ext,
-    intlist_to_bytes,
     int_or_none,
+    intlist_to_bytes,
     join_nonempty,
-    strip_jsonp,
     smuggle_url,
+    strip_jsonp,
     traverse_obj,
     unescapeHTML,
     unsmuggle_url,

yt_dlp/extractor/audioboom.py

@@ -1,10 +1,5 @@
 from .common import InfoExtractor
-from ..utils import (
-    clean_html,
-    float_or_none,
-    unescapeHTML,
-    traverse_obj,
-)
+from ..utils import clean_html, float_or_none, traverse_obj, unescapeHTML
 
 
 class AudioBoomIE(InfoExtractor):

yt_dlp/extractor/bandcamp.py

@@ -5,16 +5,16 @@ import time
 from .common import InfoExtractor
 from ..compat import compat_str
 from ..utils import (
+    KNOWN_EXTENSIONS,
     ExtractorError,
     float_or_none,
     int_or_none,
-    KNOWN_EXTENSIONS,
     parse_filesize,
     str_or_none,
     try_get,
-    update_url_query,
     unified_strdate,
     unified_timestamp,
+    update_url_query,
     url_or_none,
     urljoin,
 )

yt_dlp/extractor/hrfensehen.py

@@ -1,6 +1,7 @@
 import json
 import re
 
+from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     traverse_obj,
@@ -8,7 +9,6 @@ from ..utils import (
     unescapeHTML,
     unified_timestamp,
 )
-from .common import InfoExtractor
 
 
 class HRFernsehenIE(InfoExtractor):

yt_dlp/extractor/huya.py

@@ -54,7 +54,7 @@ class HuyaLiveIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id=video_id)
-        stream_data = self._search_json(r'stream:\s+', webpage, 'stream', video_id=video_id, default=None)
+        stream_data = self._search_json(r'stream:\s', webpage, 'stream', video_id=video_id, default=None)
         room_info = try_get(stream_data, lambda x: x['data'][0]['gameLiveInfo'])
         if not room_info:
             raise ExtractorError('Can not extract the room info', expected=True)

yt_dlp/extractor/iltalehti.py

@@ -41,7 +41,7 @@ class IltalehtiIE(InfoExtractor):
         article_id = self._match_id(url)
         webpage = self._download_webpage(url, article_id)
         info = self._search_json(
-            r'<script>\s*window.App\s*=\s*', webpage, 'json', article_id,
+            r'<script>\s*window.App\s*=', webpage, 'json', article_id,
             transform_source=js_to_json)
         props = traverse_obj(info, (
             'state', 'articles', ..., 'items', (('main_media', 'properties'), ('body', ..., 'properties'))))

yt_dlp/extractor/instagram.py

@@ -452,7 +452,7 @@ class InstagramIE(InstagramBaseIE):
                 webpage = self._download_webpage(
                     f'{url}/embed/', video_id, note='Downloading embed webpage', fatal=False)
                 additional_data = self._search_json(
-                    r'window\.__additionalDataLoaded\s*\(\s*[^,]+,\s*', webpage, 'additional data', video_id, fatal=False)
+                    r'window\.__additionalDataLoaded\s*\(\s*[^,]+,', webpage, 'additional data', video_id, fatal=False)
                 if not additional_data and not media:
                     self.raise_login_required('Requested content is not available, rate-limit reached or login required')
 

yt_dlp/extractor/liputan6.py

@@ -57,7 +57,7 @@ class Liputan6IE(InfoExtractor):
         webpage = self._download_webpage(url, display_id)
 
         json_data = self._search_json(
-            r'window.kmklabs.gtm\s*=\s*', webpage, 'json_data', display_id)
+            r'window.kmklabs.gtm\s*=', webpage, 'json_data', display_id)
         video_id = json_data['videos']['video_1']['video_id']
 
         return self.url_result(

yt_dlp/extractor/microsoftembed.py

@@ -1,9 +1,5 @@
 from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    traverse_obj,
-    unified_timestamp,
-)
+from ..utils import int_or_none, traverse_obj, unified_timestamp
 
 
 class MicrosoftEmbedIE(InfoExtractor):

yt_dlp/extractor/nbc.py

@@ -643,7 +643,7 @@ class NBCStationsIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         nbc_data = self._search_json(
-            r'<script>var\s*nbc\s*=\s*', webpage, 'NBC JSON data', video_id)
+            r'<script>var\s*nbc\s*=', webpage, 'NBC JSON data', video_id)
         pdk_acct = nbc_data.get('pdkAcct') or 'Yh1nAC'
         fw_ssid = traverse_obj(nbc_data, ('video', 'fwSSID'))
         fw_network_id = traverse_obj(nbc_data, ('video', 'fwNetworkID'), default='382114')

yt_dlp/extractor/rcs.py

@@ -2,10 +2,10 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
-    clean_html,
     ExtractorError,
-    js_to_json,
     base_url,
+    clean_html,
+    js_to_json,
     url_basename,
     urljoin,
 )

yt_dlp/extractor/trovo.py

@@ -7,9 +7,9 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     format_field,
-    traverse_obj,
     int_or_none,
     str_or_none,
+    traverse_obj,
     try_get,
 )
 

yt_dlp/extractor/tviplayer.py

@@ -62,7 +62,7 @@ class TVIPlayerIE(InfoExtractor):
         webpage = self._download_webpage(url, video_id)
 
         json_data = self._search_json(
-            r'<script>\s*jsonData\s*=\s*', webpage, 'json_data', video_id)
+            r'<script>\s*jsonData\s*=', webpage, 'json_data', video_id)
 
         formats, subtitles = self._extract_m3u8_formats_and_subtitles(
             f'{json_data["videoUrl"]}?wmsAuthSign={self.wms_auth_sign_token}',

yt_dlp/extractor/yandexvideo.py

@@ -6,9 +6,9 @@ from ..utils import (
     determine_ext,
     extract_attributes,
     int_or_none,
+    lowercase_escape,
     try_get,
     url_or_none,
-    lowercase_escape,
 )