[cleanup] Fix minor mistakes (#17083)

Authored by: doe1080

yt_dlp/YoutubeDL.py

@@ -2001,7 +2001,7 @@ class YoutubeDL:
             if webpage_url and webpage_url in self._playlist_urls:
                 self.to_screen(
                     '[download] Skipping already downloaded playlist: {}'.format(
-                        ie_result.get('title')) or ie_result.get('id'))
+                        ie_result.get('title') or ie_result.get('id')))
                 return
 
             self._playlist_level += 1

yt_dlp/extractor/allocine.py

@@ -99,7 +99,7 @@ class AllocineIE(InfoExtractor):
             video_id = display_id
             media_data = self._download_json(
                 f'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media={video_id}', display_id)
-            title = remove_end(strip_or_none(self._html_extract_title(webpage), ' - AlloCiné'))
+            title = remove_end(strip_or_none(self._html_extract_title(webpage)), ' - AlloCiné')
             for key, value in media_data['video'].items():
                 if not key.endswith('Path'):
                     continue

yt_dlp/extractor/amp.py

@@ -87,7 +87,7 @@ class AMPIE(InfoExtractor):  # XXX: Conventionally, base classes should end with
                     'ext': ext,
                 })
 
-        timestamp = unified_timestamp(item.get('pubDate'), ' ') or parse_iso8601(item.get('dc-date'))
+        timestamp = unified_timestamp(item.get('pubDate')) or parse_iso8601(item.get('dc-date'))
 
         return {
             'id': video_id,

yt_dlp/extractor/bbc.py

@@ -514,7 +514,10 @@ class BBCCoUkIE(InfoExtractor):
                         value = item.get(p)
                         if value and re.match(r'^[pb][\da-z]{7}$', value):
                             return value
-                get_from_attributes(item)
+
+                if programme_id := get_from_attributes(item):
+                    return programme_id
+
                 mediator = item.find(f'./{{{self._EMP_PLAYLIST_NS}}}mediator')
                 if mediator is not None:
                     return get_from_attributes(mediator)

yt_dlp/extractor/brainpop.py

@@ -76,9 +76,9 @@ class BrainPOPBaseIE(InfoExtractor):
             }, note='Logging in', errnote='Unable to log in', expected_status=400)
         status_code = int_or_none(login_res['status_code'])
         if status_code != 1505:
+            message = self._LOGIN_ERRORS.get(status_code) or login_res.get('message')
             self.report_warning(
-                f'Unable to login: {self._LOGIN_ERRORS.get(status_code) or login_res.get("message")}'
+                f'Unable to login: {message}' if message else f'Got status code {status_code}')
-                or f'Got status code {status_code}')
 
 
 class BrainPOPIE(BrainPOPBaseIE):

yt_dlp/extractor/byutv.py

@@ -88,7 +88,7 @@ class BYUtvIE(InfoExtractor):
                     'url': video_url,
                     'format_id': format_id,
                 })
-            merge_dicts(info, {
+            info = merge_dicts(info, {
                 'title': ep.get('title'),
                 'description': ep.get('description'),
                 'thumbnail': ep.get('imageThumbnail'),

yt_dlp/extractor/common.py

@@ -3070,8 +3070,8 @@ class InfoExtractor:
                         # %(...) counterparts to be used with % operator
                         t = re.sub(r'\$({})\$'.format('|'.join(identifiers)), r'%(\1)d', t)
                         t = re.sub(r'\$({})%([^$]+)\$'.format('|'.join(identifiers)), r'%(\1)\2', t)
-                        t.replace('$$', '$')
+
-                        return t
+                        return t.replace('$$', '$')
 
                     # @initialization is a regular template like @media one
                     # so it should be handled just the same way (see

yt_dlp/extractor/hrti.py

@@ -74,7 +74,7 @@ class HRTiBaseIE(InfoExtractor):
                 data=json.dumps(auth_data).encode())
         except ExtractorError as e:
             if isinstance(e.cause, HTTPError) and e.cause.status == 406:
-                auth_info = self._parse_json(e.cause.response.read().encode(), None)
+                auth_info = self._parse_json(e.cause.response.read().decode(), None)
             else:
                 raise
 

yt_dlp/extractor/iqiyi.py

@@ -457,12 +457,12 @@ class IqIE(InfoExtractor):
             if video_format.get('m3u8Url'):
                 extracted_formats.extend(self._extract_m3u8_formats(
                     urljoin(format_data.get('dm3u8', 'https://cache-m.iq.com/dc/dt/'), video_format['m3u8Url']),
-                    'mp4', m3u8_id=bid, fatal=False))
+                    video_id, 'mp4', m3u8_id=bid, fatal=False))
             if video_format.get('mpdUrl'):
                 # TODO: Properly extract mpd hostname
                 extracted_formats.extend(self._extract_mpd_formats(
                     urljoin(format_data.get('dm3u8', 'https://cache-m.iq.com/dc/dt/'), video_format['mpdUrl']),
-                    mpd_id=bid, fatal=False))
+                    video_id, mpd_id=bid, fatal=False))
             if video_format.get('m3u8'):
                 ff = video_format.get('ff', 'ts')
                 if ff == 'ts':

yt_dlp/extractor/libsyn.py

@@ -69,7 +69,7 @@ class LibsynIE(InfoExtractor):
 
         episode_title = data.get('item_title') or get_element_by_class('episode-title', webpage)
         if not episode_title:
-            self._search_regex(
+            episode_title = self._search_regex(
                 [r'data-title="([^"]+)"', r'<title>(.+?)</title>'],
                 webpage, 'episode title')
         episode_title = episode_title.strip()

yt_dlp/extractor/mirrativ.py

@@ -59,7 +59,7 @@ class MirrativIE(MirrativBaseIE):
         return {
             'id': video_id,
             'title': self._og_search_title(webpage, default=None) or self._search_regex(
-                r'<title>\s*(.+?) - Mirrativ\s*</title>', webpage) or live_response.get('title'),
+                r'<title>\s*(.+?) - Mirrativ\s*</title>', webpage, 'title', default=None) or live_response.get('title'),
             'is_live': is_live,
             'description': live_response.get('description'),
             'formats': formats,

yt_dlp/extractor/nova.py

@@ -110,7 +110,7 @@ class NovaEmbedIE(InfoExtractor):
 
         title = self._og_search_title(
             webpage, default=None) or self._search_regex(
-            (r'<value>(?P<title>[^<]+)',
+            (r'<value>(?P<value>[^<]+)',
              r'videoTitle\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1'), webpage,
             'title', group='value')
         thumbnail = self._og_search_thumbnail(

yt_dlp/extractor/pandatv.py

@@ -74,7 +74,7 @@ class PandaTvIE(InfoExtractor):
             'http_headers': http_headers,
             **traverse_obj(video_meta, ('media', {
                 'title': ('title', {str}),
-                'release_timestamp': ('startTime', {parse_iso8601(delim=' ')}),
+                'release_timestamp': ('startTime', {parse_iso8601(delimiter=' ')}),
                 'thumbnail': ('ivsThumbnail', {url_or_none}),
                 'channel': ('userNick', {str}),
                 'concurrent_view_count': ('user', {int_or_none}),

yt_dlp/extractor/periscope.py

@@ -107,11 +107,6 @@ class PeriscopeIE(PeriscopeBaseIE):
         width = int_or_none(broadcast.get('width'))
         height = int_or_none(broadcast.get('height'))
 
-        def add_width_and_height(f):
-            for key, val in (('width', width), ('height', height)):
-                if not f.get(key):
-                    f[key] = val
-
         video_urls = set()
         formats = []
         for format_id in ('replay', 'rtmp', 'hls', 'https_hls', 'lhls', 'lhlsweb'):
@@ -128,7 +123,7 @@ class PeriscopeIE(PeriscopeBaseIE):
                 'url': video_url,
                 'ext': 'flv' if format_id == 'rtmp' else 'mp4',
             }
-            self._add_width_and_height(rtmp_format)
+            self._add_width_and_height(rtmp_format, width, height)
             formats.append(rtmp_format)
 
         info['formats'] = formats

yt_dlp/extractor/radiocanada.py

@@ -129,8 +129,8 @@ class RadioCanadaIE(InfoExtractor):
             'thumbnail': get_meta('imageHR') or get_meta('imageMR') or get_meta('imageBR'),
             'duration': int_or_none(get_meta('length')),
             'series': get_meta('Emission'),
-            'season_number': int_or_none('SrcSaison'),
+            'season_number': int_or_none(get_meta('SrcSaison')),
-            'episode_number': int_or_none('SrcEpisode'),
+            'episode_number': int_or_none(get_meta('SrcEpisode')),
             'upload_date': unified_strdate(get_meta('Date')),
             'subtitles': subtitles,
             'formats': formats,

yt_dlp/extractor/rcti.py

@@ -298,7 +298,7 @@ class RCTIPlusSeriesIE(RCTIPlusBaseIE):
                 }
 
     def _series_entries(self, series_id, display_id=None, video_type=None, metadata={}):
-        if not video_type or video_type in 'episodes':
+        if not video_type or video_type == 'episodes':
             try:
                 seasons_list = self._call_api(
                     f'https://api.rctiplus.com/api/v1/program/{series_id}/season',
@@ -311,11 +311,11 @@ class RCTIPlusSeriesIE(RCTIPlusBaseIE):
                 yield from self._entries(
                     f'https://api.rctiplus.com/api/v2/program/{series_id}/episode?season={season["season"]}',
                     display_id, f'Downloading season {season["season"]} episode entries', metadata)
-        if not video_type or video_type in 'extras':
+        if not video_type or video_type == 'extras':
             yield from self._entries(
                 f'https://api.rctiplus.com/api/v2/program/{series_id}/extra?content_id=0',
                 display_id, 'Downloading extra entries', metadata)
-        if not video_type or video_type in 'clips':
+        if not video_type or video_type == 'clips':
             yield from self._entries(
                 f'https://api.rctiplus.com/api/v2/program/{series_id}/clip?content_id=0',
                 display_id, 'Downloading clip entries', metadata)

yt_dlp/extractor/saitosan.py

@@ -48,7 +48,7 @@ class SaitosanIE(InfoExtractor):
 
         self._download_webpage(base, b_id, note='Polling socket')
         payload = f'420["room_start_join",{{"room_id":"{b_id}"}}]'
-        payload = f'{len(payload)}:{payload}'
+        payload = f'{len(payload)}:{payload}'.encode()
 
         self._download_webpage(base, b_id, data=payload, note='Polling socket with payload')
         response = self._download_socket_json(base, b_id, note='Polling socket')
@@ -59,11 +59,11 @@ class SaitosanIE(InfoExtractor):
                 else 'The socket reported that the broadcast could not be joined. Maybe it\'s offline or the URL is incorrect',
                 expected=True, video_id=b_id)
 
-        self._download_webpage(base, b_id, data='26:421["room_finish_join",{}]', note='Polling socket')
+        self._download_webpage(base, b_id, data=b'26:421["room_finish_join",{}]', note='Polling socket')
         b_data = self._download_socket_json(base, b_id, note='Getting broadcast metadata from socket')
         m3u8_url = b_data.get('url')
 
-        self._download_webpage(base, b_id, data='1:1', note='Closing socket', fatal=False)
+        self._download_webpage(base, b_id, data=b'1:1', note='Closing socket', fatal=False)
 
         return {
             'id': b_id,

yt_dlp/extractor/sonyliv.py

@@ -94,7 +94,7 @@ class SonyLIVIE(InfoExtractor):
                 'mobileNumber': username,
                 'channelPartnerID': 'MSMIND',
                 'country': 'IN',
-                'timestamp': dt.datetime.now().strftime('%Y-%m-%dT%H:%M:%S.%MZ'),
+                'timestamp': dt.datetime.now(dt.timezone.utc).strftime('%Y-%m-%dT%H:%M:%S.%fZ'),
                 'otpSize': 6,
                 'loginType': 'REGISTERORSIGNIN',
                 'isMobileMandatory': True,
@@ -111,7 +111,7 @@ class SonyLIVIE(InfoExtractor):
                 'otp': self._get_tfa_info('OTP'),
                 'dmaId': 'IN',
                 'ageConfirmation': True,
-                'timestamp': dt.datetime.now().strftime('%Y-%m-%dT%H:%M:%S.%MZ'),
+                'timestamp': dt.datetime.now(dt.timezone.utc).strftime('%Y-%m-%dT%H:%M:%S.%fZ'),
                 'isMobileMandatory': True,
             }).encode())
         if otp_verify_json['resultCode'] == 'KO':

yt_dlp/extractor/spankbang.py

@@ -109,7 +109,7 @@ class SpankBangIE(InfoExtractor):
 
         for mobj in re.finditer(
                 rf'{STREAM_URL_PREFIX}(?P<id>[^\s=]+)\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2', webpage):
-            extract_format(mobj.group('id', 'url'))
+            extract_format(*mobj.group('id', 'url'))
 
         if not formats:
             stream_key = self._search_regex(

yt_dlp/extractor/tvp.py

@@ -290,7 +290,7 @@ class TVPStreamIE(InfoExtractor):
 
     def _real_extract(self, url):
         channel_id = self._match_id(url)
-        channel_url = self._proto_relative_url(f'//stream.tvp.pl/?channel_id={channel_id}' or 'default')
+        channel_url = self._proto_relative_url(f'//stream.tvp.pl/?channel_id={channel_id}')
         webpage = self._download_webpage(channel_url, channel_id or 'default', 'Downloading channel webpage')
         channels = self._search_json(
             r'window\.__channels\s*=', webpage, 'channel list', channel_id,

yt_dlp/extractor/wdr.py

@@ -88,7 +88,7 @@ class WDRIE(InfoExtractor):
                         manifest_url, video_id, f4m_id='hds', fatal=False))
                 elif ext == 'smil':
                     formats.extend(self._extract_smil_formats(
-                        medium_url, 'stream', fatal=False))
+                        medium_url, video_id, fatal=False))
                 else:
                     a_format = {
                         'url': medium_url,

yt_dlp/extractor/yandexmusic.py

@@ -121,7 +121,7 @@ class YandexMusicTrackIE(YandexMusicBaseIE):
             'Downloading track location JSON',
             query={'format': 'json'})
         key = hashlib.md5(('XGRlBW9FXlekgbPrRHuSiA' + fd_data['path'][1:] + fd_data['s']).encode()).hexdigest()
-        f_url = 'http://{}/get-mp3/{}/{}?track-id={} '.format(fd_data['host'], key, fd_data['ts'] + fd_data['path'], track['id'])
+        f_url = 'http://{}/get-mp3/{}/{}?track-id={}'.format(fd_data['host'], key, fd_data['ts'] + fd_data['path'], track['id'])
 
         thumbnail = None
         cover_uri = track.get('albums', [{}])[0].get('coverUri')