Merge branch 'yt-dlp:master' into trial

.github/workflows/build.yml

@@ -107,6 +107,8 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Needed for changelog
       - uses: actions/setup-python@v5
         with:
           python-version: "3.10"
@@ -133,6 +135,7 @@ jobs:
       - name: Prepare
         run: |
           python devscripts/update-version.py -c "${{ inputs.channel }}" -r "${{ needs.process.outputs.origin }}" "${{ inputs.version }}"
+          python devscripts/update_changelog.py -vv
           python devscripts/make_lazy_extractors.py
       - name: Build Unix platform-independent binary
         run: |

.github/workflows/release.yml

@@ -189,13 +189,8 @@ jobs:
         if: |
           !inputs.prerelease && env.target_repo == github.repository
         run: |
+          python devscripts/update_changelog.py -vv
           make doc
-          sed '/### /Q' Changelog.md >> ./CHANGELOG
-          echo '### ${{ env.version }}' >> ./CHANGELOG
-          python ./devscripts/make_changelog.py -vv -c >> ./CHANGELOG
-          echo >> ./CHANGELOG
-          grep -Poz '(?s)### \d+\.\d+\.\d+.+' 'Changelog.md' | head -n -1 >> ./CHANGELOG
-          cat ./CHANGELOG > Changelog.md
 
       - name: Push to release
         id: push_release
@@ -266,6 +261,7 @@ jobs:
           pypi_project: ${{ needs.prepare.outputs.pypi_project }}
         run: |
           python devscripts/update-version.py -c "${{ env.channel }}" -r "${{ env.target_repo }}" -s "${{ env.suffix }}" "${{ env.version }}"
+          python devscripts/update_changelog.py -vv
           python devscripts/make_lazy_extractors.py
           sed -i -E '0,/(name = ")[^"]+(")/s//\1${{ env.pypi_project }}\2/' pyproject.toml
 

Makefile

@@ -2,7 +2,7 @@ all: lazy-extractors yt-dlp doc pypi-files
 clean: clean-test clean-dist
 clean-all: clean clean-cache
 completions: completion-bash completion-fish completion-zsh
-doc: README.md CONTRIBUTING.md issuetemplates supportedsites
+doc: README.md CONTRIBUTING.md CONTRIBUTORS issuetemplates supportedsites
 ot: offlinetest
 tar: yt-dlp.tar.gz
 
@@ -156,5 +156,14 @@ yt-dlp.tar.gz: all
 		Makefile yt-dlp.1 README.txt completions .gitignore \
 		setup.cfg yt-dlp yt_dlp pyproject.toml devscripts test
 
-AUTHORS:
-	git shortlog -s -n HEAD | cut -f2 | sort > AUTHORS
+AUTHORS: Changelog.md
+	@if [ -d '.git' ] && command -v git > /dev/null ; then \
+	  echo 'Generating $@ from git commit history' ; \
+	  git shortlog -s -n HEAD | cut -f2 | sort > $@ ; \
+	fi
+
+CONTRIBUTORS: Changelog.md
+	@if [ -d '.git' ] && command -v git > /dev/null ; then \
+	  echo 'Updating $@ from git commit history' ; \
+	  $(PYTHON) devscripts/make_changelog.py -v -c > /dev/null ; \
+	fi

devscripts/make_changelog.py

@@ -445,7 +445,32 @@ def get_new_contributors(contributors_path, commits):
     return sorted(new_contributors, key=str.casefold)
 
 
-if __name__ == '__main__':
+def create_changelog(args):
+    logging.basicConfig(
+        datefmt='%Y-%m-%d %H-%M-%S', format='{asctime} | {levelname:<8} | {message}',
+        level=logging.WARNING - 10 * args.verbosity, style='{', stream=sys.stderr)
+
+    commits = CommitRange(None, args.commitish, args.default_author)
+
+    if not args.no_override:
+        if args.override_path.exists():
+            overrides = json.loads(read_file(args.override_path))
+            commits.apply_overrides(overrides)
+        else:
+            logger.warning(f'File {args.override_path.as_posix()} does not exist')
+
+    logger.info(f'Loaded {len(commits)} commits')
+
+    new_contributors = get_new_contributors(args.contributors_path, commits)
+    if new_contributors:
+        if args.contributors:
+            write_file(args.contributors_path, '\n'.join(new_contributors) + '\n', mode='a')
+        logger.info(f'New contributors: {", ".join(new_contributors)}')
+
+    return Changelog(commits.groups(), args.repo, args.collapsible)
+
+
+def create_parser():
     import argparse
 
     parser = argparse.ArgumentParser(
@@ -477,27 +502,9 @@ def get_new_contributors(contributors_path, commits):
     parser.add_argument(
         '--collapsible', action='store_true',
         help='make changelog collapsible (default: %(default)s)')
-    args = parser.parse_args()
-
-    logging.basicConfig(
-        datefmt='%Y-%m-%d %H-%M-%S', format='{asctime} | {levelname:<8} | {message}',
-        level=logging.WARNING - 10 * args.verbosity, style='{', stream=sys.stderr)
-
-    commits = CommitRange(None, args.commitish, args.default_author)
-
-    if not args.no_override:
-        if args.override_path.exists():
-            overrides = json.loads(read_file(args.override_path))
-            commits.apply_overrides(overrides)
-        else:
-            logger.warning(f'File {args.override_path.as_posix()} does not exist')
 
-    logger.info(f'Loaded {len(commits)} commits')
+    return parser
 
-    new_contributors = get_new_contributors(args.contributors_path, commits)
-    if new_contributors:
-        if args.contributors:
-            write_file(args.contributors_path, '\n'.join(new_contributors) + '\n', mode='a')
-        logger.info(f'New contributors: {", ".join(new_contributors)}')
 
-    print(Changelog(commits.groups(), args.repo, args.collapsible))
+if __name__ == '__main__':
+    print(create_changelog(create_parser().parse_args()))

devscripts/update_changelog.py

@@ -0,0 +1,26 @@
+#!/usr/bin/env python3
+
+# Allow direct execution
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+from pathlib import Path
+
+from devscripts.make_changelog import create_changelog, create_parser
+from devscripts.utils import read_file, read_version, write_file
+
+# Always run after devscripts/update-version.py, and run before `make doc|pypi-files|tar|all`
+
+if __name__ == '__main__':
+    parser = create_parser()
+    parser.description = 'Update an existing changelog file with an entry for a new release'
+    parser.add_argument(
+        '--changelog-path', type=Path, default=Path(__file__).parent.parent / 'Changelog.md',
+        help='path to the Changelog file')
+    args = parser.parse_args()
+    new_entry = create_changelog(args)
+
+    header, sep, changelog = read_file(args.changelog_path).partition('\n### ')
+    write_file(args.changelog_path, f'{header}{sep}{read_version()}\n{new_entry}\n{sep}{changelog}')

yt_dlp/extractor/crunchyroll.py

@@ -136,7 +136,7 @@ def _call_api(self, path, internal_id, lang, note='api', query={}):
         return result
 
     def _extract_formats(self, stream_response, display_id=None):
-        requested_formats = self._configuration_arg('format') or ['adaptive_hls']
+        requested_formats = self._configuration_arg('format') or ['vo_adaptive_hls']
         available_formats = {}
         for stream_type, streams in traverse_obj(
                 stream_response, (('streams', ('data', 0)), {dict.items}, ...)):

yt_dlp/extractor/gofile.py

@@ -58,21 +58,18 @@ def _real_initialize(self):
             return
 
         account_data = self._download_json(
-            'https://api.gofile.io/createAccount', None, note='Getting a new guest account')
+            'https://api.gofile.io/accounts', None, 'Getting a new guest account', data=b'{}')
         self._TOKEN = account_data['data']['token']
         self._set_cookie('.gofile.io', 'accountToken', self._TOKEN)
 
     def _entries(self, file_id):
-        query_params = {
-            'contentId': file_id,
-            'token': self._TOKEN,
-            'wt': '4fd6sg89d7s6',  # From https://gofile.io/dist/js/alljs.js
-        }
+        query_params = {'wt': '4fd6sg89d7s6'}  # From https://gofile.io/dist/js/alljs.js
         password = self.get_param('videopassword')
         if password:
             query_params['password'] = hashlib.sha256(password.encode('utf-8')).hexdigest()
         files = self._download_json(
-            'https://api.gofile.io/getContent', file_id, note='Getting filelist', query=query_params)
+            f'https://api.gofile.io/contents/{file_id}', file_id, 'Getting filelist',
+            query=query_params, headers={'Authorization': f'Bearer {self._TOKEN}'})
 
         status = files['status']
         if status == 'error-passwordRequired':
@@ -82,7 +79,7 @@ def _entries(self, file_id):
             raise ExtractorError(f'{self.IE_NAME} said: status {status}', expected=True)
 
         found_files = False
-        for file in (try_get(files, lambda x: x['data']['contents'], dict) or {}).values():
+        for file in (try_get(files, lambda x: x['data']['children'], dict) or {}).values():
             file_type, file_format = file.get('mimetype').split('/', 1)
             if file_type not in ('video', 'audio') and file_format != 'vnd.mts':
                 continue

yt_dlp/extractor/sonyliv.py

@@ -1,4 +1,5 @@
 import datetime
+import itertools
 import json
 import math
 import random
@@ -12,8 +13,8 @@
     int_or_none,
     jwt_decode_hs256,
     try_call,
-    try_get,
 )
+from ..utils.traversal import traverse_obj
 
 
 class SonyLIVIE(InfoExtractor):
@@ -183,37 +184,56 @@ def _real_extract(self, url):
 
 
 class SonyLIVSeriesIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?sonyliv\.com/shows/[^/?#&]+-(?P<id>\d{10})$'
+    _VALID_URL = r'https?://(?:www\.)?sonyliv\.com/shows/[^/?#&]+-(?P<id>\d{10})/?(?:$|[?#])'
     _TESTS = [{
         'url': 'https://www.sonyliv.com/shows/adaalat-1700000091',
-        'playlist_mincount': 456,
+        'playlist_mincount': 452,
         'info_dict': {
             'id': '1700000091',
         },
+    }, {
+        'url': 'https://www.sonyliv.com/shows/beyhadh-1700000007/',
+        'playlist_mincount': 358,
+        'info_dict': {
+            'id': '1700000007',
+        },
     }]
-    _API_SHOW_URL = "https://apiv2.sonyliv.com/AGL/1.9/R/ENG/WEB/IN/DL/DETAIL/{}?kids_safe=false&from=0&to=49"
-    _API_EPISODES_URL = "https://apiv2.sonyliv.com/AGL/1.4/R/ENG/WEB/IN/CONTENT/DETAIL/BUNDLE/{}?from=0&to=1000&orderBy=episodeNumber&sortOrder=asc"
-    _API_SECURITY_URL = 'https://apiv2.sonyliv.com/AGL/1.4/A/ENG/WEB/ALL/GETTOKEN'
+    _API_BASE = 'https://apiv2.sonyliv.com/AGL'
 
     def _entries(self, show_id):
         headers = {
             'Accept': 'application/json, text/plain, */*',
             'Referer': 'https://www.sonyliv.com',
         }
         headers['security_token'] = self._download_json(
-            self._API_SECURITY_URL, video_id=show_id, headers=headers,
-            note='Downloading security token')['resultObj']
-        seasons = try_get(
-            self._download_json(self._API_SHOW_URL.format(show_id), video_id=show_id, headers=headers),
-            lambda x: x['resultObj']['containers'][0]['containers'], list)
-        for season in seasons or []:
-            season_id = season['id']
-            episodes = try_get(
-                self._download_json(self._API_EPISODES_URL.format(season_id), video_id=season_id, headers=headers),
-                lambda x: x['resultObj']['containers'][0]['containers'], list)
-            for episode in episodes or []:
-                video_id = episode.get('id')
-                yield self.url_result('sonyliv:%s' % video_id, ie=SonyLIVIE.ie_key(), video_id=video_id)
+            f'{self._API_BASE}/1.4/A/ENG/WEB/ALL/GETTOKEN', show_id,
+            'Downloading security token', headers=headers)['resultObj']
+        seasons = traverse_obj(self._download_json(
+            f'{self._API_BASE}/1.9/R/ENG/WEB/IN/DL/DETAIL/{show_id}', show_id,
+            'Downloading series JSON', headers=headers, query={
+                'kids_safe': 'false',
+                'from': '0',
+                'to': '49',
+            }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
+        for season in seasons:
+            season_id = str(season['id'])
+            note = traverse_obj(season, ('metadata', 'title', {str})) or 'season'
+            cursor = 0
+            for page_num in itertools.count(1):
+                episodes = traverse_obj(self._download_json(
+                    f'{self._API_BASE}/1.4/R/ENG/WEB/IN/CONTENT/DETAIL/BUNDLE/{season_id}',
+                    season_id, f'Downloading {note} page {page_num} JSON', headers=headers, query={
+                        'from': str(cursor),
+                        'to': str(cursor + 99),
+                        'orderBy': 'episodeNumber',
+                        'sortOrder': 'asc',
+                    }), ('resultObj', 'containers', 0, 'containers', lambda _, v: int_or_none(v['id'])))
+                if not episodes:
+                    break
+                for episode in episodes:
+                    video_id = str(episode['id'])
+                    yield self.url_result(f'sonyliv:{video_id}', SonyLIVIE, video_id)
+                cursor += 100
 
     def _real_extract(self, url):
         show_id = self._match_id(url)

yt_dlp/extractor/tiktok.py

@@ -41,7 +41,7 @@ class TikTokBaseIE(InfoExtractor):
     @property
     def _API_HOSTNAME(self):
         return self._configuration_arg(
-            'api_hostname', ['api16-normal-c-useast1a.tiktokv.com'], ie_key=TikTokIE)[0]
+            'api_hostname', ['api22-normal-c-useast2a.tiktokv.com'], ie_key=TikTokIE)[0]
 
     @staticmethod
     def _create_url(user_id, video_id):