[cleanup] Misc (yt-dlp#8968)

Authored by: pukkandan, bashonly, seproDev

.gitignore

@@ -33,20 +33,23 @@ cookies
 *.gif
 *.jpeg
 *.jpg
+*.lrc
 *.m4a
 *.m4v
 *.mhtml
 *.mkv
 *.mov
 *.mp3
 *.mp4
+*.mpg
 *.mpga
 *.oga
 *.ogg
 *.opus
 *.png
 *.sbv
 *.srt
+*.ssa
 *.swf
 *.swp
 *.tt

Makefile

@@ -17,8 +17,8 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
 clean-test:
 	rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
 	*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
-	*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
-	*.mp4 *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
+	*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.lrc *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
+	*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
 clean-dist:
 	rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
 	yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS

bundle/__init__.py

@@ -1 +0,0 @@
-# Empty file

bundle/py2exe.py

@@ -20,7 +20,7 @@ def main():
         'py2exe builds do not support pycryptodomex and needs VC++14 to run. '
         'It is recommended to run "pyinst.py" to build using pyinstaller instead')
 
-    return freeze(
+    freeze(
         console=[{
             'script': './yt_dlp/__main__.py',
             'dest_base': 'yt-dlp',

devscripts/__init__.py

@@ -1 +0,0 @@
-# Empty file needed to make devscripts.utils properly importable from outside

devscripts/changelog_override.json

@@ -120,5 +120,11 @@
         "when": "15f22b4880b6b3f71f350c64d70976ae65b9f1ca",
         "short": "[webvtt] Allow spaces before newlines for CueBlock (#7681)",
         "authors": ["TSRBerry"]
+    },
+    {
+        "action": "change",
+        "when": "4ce57d3b873c2887814cbec03d029533e82f7db5",
+        "short": "[ie] Support multi-period MPD streams (#6654)",
+        "authors": ["alard", "pukkandan"]
     }
 ]

devscripts/make_changelog.py

@@ -253,7 +253,7 @@ class CommitRange:
         ''', re.VERBOSE | re.DOTALL)
     EXTRACTOR_INDICATOR_RE = re.compile(r'(?:Fix|Add)\s+Extractors?', re.IGNORECASE)
     REVERT_RE = re.compile(r'(?:\[[^\]]+\]\s+)?(?i:Revert)\s+([\da-f]{40})')
-    FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert)\s+([\da-f]{40})')
+    FIXES_RE = re.compile(r'(?i:Fix(?:es)?(?:\s+bugs?)?(?:\s+in|\s+for)?|Revert|Improve)\s+([\da-f]{40})')
     UPSTREAM_MERGE_RE = re.compile(r'Update to ytdl-commit-([\da-f]+)')
 
     def __init__(self, start, end, default_author=None):

test/test_networking.py

@@ -69,7 +69,7 @@ def do_GET(self):
             self.send_response(200)
             self.send_header('Content-Type', 'text/plain; charset=utf-8')
             self.end_headers()
-            self.wfile.write('{self.proxy_name}: {self.path}'.format(self=self).encode())
+            self.wfile.write(f'{self.proxy_name}: {self.path}'.encode())
     return HTTPTestRequestHandler
 
 

yt_dlp/YoutubeDL.py

@@ -575,7 +575,7 @@ class YoutubeDL:
         'url', 'manifest_url', 'manifest_stream_number', 'ext', 'format', 'format_id', 'format_note',
         'width', 'height', 'aspect_ratio', 'resolution', 'dynamic_range', 'tbr', 'abr', 'acodec', 'asr', 'audio_channels',
         'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx', 'rows', 'columns',
-        'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start',
+        'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start', 'is_dash_periods', 'request_data',
         'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
         'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'hls_aes', 'downloader_options',
         'page_url', 'app', 'play_path', 'tc_url', 'flash_version', 'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time'

yt_dlp/extractor/altcensored.py

@@ -4,6 +4,7 @@
 from .common import InfoExtractor
 from ..utils import (
     InAdvancePagedList,
+    clean_html,
     int_or_none,
     orderedSet,
     str_to_int,
@@ -32,23 +33,23 @@ class AltCensoredIE(InfoExtractor):
             'duration': 926.09,
             'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
             'view_count': int,
-            'categories': ['News & Politics'],  # FIXME
+            'categories': ['News & Politics'],
         }
     }]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
+        category = clean_html(self._html_search_regex(
+            r'<a href="/category/\d+">([^<]+)</a>', webpage, 'category', default=None))
 
         return {
             '_type': 'url_transparent',
             'url': f'https://archive.org/details/youtube-{video_id}',
             'ie_key': ArchiveOrgIE.ie_key(),
             'view_count': str_to_int(self._html_search_regex(
                 r'YouTube Views:(?:\s|&nbsp;)*([\d,]+)', webpage, 'view count', default=None)),
-            'categories': self._html_search_regex(
-                r'<a href="/category/\d+">\s*\n?\s*([^<]+)</a>',
-                webpage, 'category', default='').split() or None,
+            'categories': [category] if category else None,
         }
 
 

yt_dlp/extractor/arte.py

@@ -142,10 +142,10 @@ class ArteTVIE(ArteTVBaseIE):
     def _fix_accessible_subs_locale(subs):
         updated_subs = {}
         for lang, sub_formats in subs.items():
-            for format in sub_formats:
-                if format.get('url', '').endswith('-MAL.m3u8'):
+            for fmt in sub_formats:
+                if fmt.get('url', '').endswith('-MAL.m3u8'):
                     lang += '-acc'
-                updated_subs.setdefault(lang, []).append(format)
+                updated_subs.setdefault(lang, []).append(fmt)
         return updated_subs
 
     def _real_extract(self, url):

yt_dlp/extractor/getcourseru.py

@@ -160,9 +160,8 @@ def _real_extract(self, url):
             self._login(hostname, username, password)
 
         display_id = self._match_id(url)
-        # NB: 404 is returned due to yt-dlp not properly following redirects #9020
-        webpage, urlh = self._download_webpage_handle(url, display_id, expected_status=404)
-        if self._LOGIN_URL_PATH in urlh.url or urlh.status == 404:
+        webpage, urlh = self._download_webpage_handle(url, display_id)
+        if self._LOGIN_URL_PATH in urlh.url:
             raise ExtractorError(
                 f'This video is only available for registered users. {self._login_hint("any", netrc=hostname)}',
                 expected=True)

yt_dlp/extractor/medaltv.py

@@ -9,7 +9,6 @@
     int_or_none,
     str_or_none,
     traverse_obj,
-    update_url_query,
 )
 
 
@@ -82,7 +81,7 @@ class MedalTVIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
-        webpage = self._download_webpage(update_url_query(url, {'mobilebypass': 'true'}), video_id)
+        webpage = self._download_webpage(url, video_id, query={'mobilebypass': 'true'})
 
         hydration_data = self._search_json(
             r'<script[^>]*>[^<]*\bhydrationData\s*=', webpage,

yt_dlp/extractor/radiko.py

@@ -162,10 +162,8 @@ def _extract_formats(self, video_id, station, is_onair, ft, cursor, auth_token,
         return formats
 
     def _extract_performers(self, prog):
-        performers = traverse_obj(prog, (
-            'pfm/text()', ..., {lambda x: re.split(r'[/／、　,，]', x)}, ..., {str.strip}))
-        # TODO: change 'artist' fields to 'artists' and return traversal list instead of str
-        return ', '.join(performers) or None
+        return traverse_obj(prog, (
+            'pfm/text()', ..., {lambda x: re.split(r'[/／、　,，]', x)}, ..., {str.strip})) or None
 
 
 class RadikoIE(RadikoBaseIE):
@@ -194,7 +192,7 @@ def _real_extract(self, url):
         return {
             'id': video_id,
             'title': try_call(lambda: prog.find('title').text),
-            'artist': self._extract_performers(prog),
+            'cast': self._extract_performers(prog),
             'description': clean_html(try_call(lambda: prog.find('info').text)),
             'uploader': try_call(lambda: station_program.find('.//name').text),
             'uploader_id': station,
@@ -253,7 +251,7 @@ def _real_extract(self, url):
         return {
             'id': station,
             'title': title,
-            'artist': self._extract_performers(prog),
+            'cast': self._extract_performers(prog),
             'description': description,
             'uploader': station_name,
             'uploader_id': station,