import traceback
from .common import InfoExtractor, SearchInfoExtractor
-from ..compat import functools
+from ..compat import functools # isort: split
from ..compat import (
compat_chr,
compat_HTTPError,
if self._LOGIN_REQUIRED and not self._cookies_passed:
self.raise_login_required('Login details are needed to download this content', method='cookies')
- _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*=\s*({.+})\s*;'
- _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+})\s*;'
- _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
+ _YT_INITIAL_DATA_RE = r'(?:window\s*\[\s*["\']ytInitialData["\']\s*\]|ytInitialData)\s*='
+ _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
def _get_default_ytcfg(self, client='web'):
return copy.deepcopy(INNERTUBE_CLIENTS[client])
query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
def extract_yt_initial_data(self, item_id, webpage, fatal=True):
- data = self._search_regex(
- (fr'{self._YT_INITIAL_DATA_RE}\s*{self._YT_INITIAL_BOUNDARY_RE}',
- self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
- if data:
- return self._parse_json(data, item_id, fatal=fatal)
+ return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
@staticmethod
def _extract_session_index(*data):
chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
chapter_title = lambda chapter: self._get_text(chapter, 'title')
- return next((
- filter(None, (
- self._extract_chapters(
- traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
- chapter_time, chapter_title, duration)
- for contents in content_list
- ))), [])
+ return next(filter(None, (
+ self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
+ chapter_time, chapter_title, duration)
+ for contents in content_list)), [])
- @staticmethod
- def _extract_chapters_from_description(description, duration):
- chapters = [{'start_time': 0}]
- for timestamp, title in re.findall(
- r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''):
- start = parse_duration(timestamp)
- if start and title and chapters[-1]['start_time'] < start < duration:
- chapters[-1]['end_time'] = start
- chapters.append({
- 'start_time': start,
- 'title': title,
- })
- chapters[-1]['end_time'] = duration
- return chapters[1:]
-
- def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
- chapters = []
- last_chapter = {'start_time': 0}
- for idx, chapter in enumerate(chapter_list or []):
- title = chapter_title(chapter)
- start_time = chapter_time(chapter)
- if start_time is None:
- continue
- last_chapter['end_time'] = start_time
- if start_time < last_chapter['start_time']:
- if idx == 1:
- chapters.pop()
- self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
- else:
- self.report_warning(f'Invalid start time for chapter "{title}"')
- continue
- last_chapter = {'start_time': start_time, 'title': title}
- chapters.append(last_chapter)
- last_chapter['end_time'] = duration
- return chapters
+ def _extract_chapters_from_description(self, description, duration):
+ return self._extract_chapters(
+ re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
+ chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
+ duration=duration, strict=False)
- def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
- return self._parse_json(self._search_regex(
- (fr'{regex}\s*{self._YT_INITIAL_BOUNDARY_RE}',
- regex), webpage, name, default='{}'), video_id, fatal=False, lenient=True)
+ def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
+ if not duration:
+ return
+ chapter_list = [{
+ 'start_time': chapter_time(chapter),
+ 'title': chapter_title(chapter),
+ } for chapter in chapter_list or []]
+ if not strict:
+ chapter_list.sort(key=lambda c: c['start_time'] or 0)
+
+ chapters = [{'start_time': 0, 'title': '<Untitled>'}]
+ for idx, chapter in enumerate(chapter_list):
+ if chapter['start_time'] is None or not chapter['title']:
+ self.report_warning(f'Incomplete chapter {idx}')
+ elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
+ chapters[-1]['end_time'] = chapter['start_time']
+ chapters.append(chapter)
+ else:
+ self.report_warning(f'Invalid start time for chapter "{chapter["title"]}"')
+ chapters[-1]['end_time'] = duration
+ return chapters if len(chapters) > 1 and chapters[1]['start_time'] else chapters[1:]
def _extract_comment(self, comment_renderer, parent=None):
comment_id = comment_renderer.get('commentId')
def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
initial_pr = None
if webpage:
- initial_pr = self._extract_yt_initial_variable(
- webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
- video_id, 'initial player response')
+ initial_pr = self._search_json(
+ self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
all_clients = set(clients)
clients = clients[::-1]
# Youtube Music Auto-generated description
if video_description:
- mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
+ mobj = re.search(
+ r'''(?xs)
+ (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
+ (?P<album>[^\n]+)
+ (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
+ (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
+ (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
+ .+\nAuto-generated\ by\ YouTube\.\s*$
+ ''', video_description)
if mobj:
release_year = mobj.group('release_year')
release_date = mobj.group('release_date')
initial_data = None
if webpage:
- initial_data = self._extract_yt_initial_variable(
- webpage, self._YT_INITIAL_DATA_RE, video_id,
- 'yt initial data')
+ initial_data = self._search_json(
+ self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', video_id, fatal=False)
if not initial_data:
query = {'videoId': video_id}
query.update(self._get_checkok_params())
channel = traverse_obj(
notification, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
expected_type=str)
+ notification_title = self._get_text(notification, 'shortMessage')
+ if notification_title:
+ notification_title = notification_title.replace('\xad', '') # remove soft hyphens
+ # TODO: handle recommended videos
title = self._search_regex(
- rf'{re.escape(channel)} [^:]+: (.+)', self._get_text(notification, 'shortMessage'),
+ rf'{re.escape(channel or "")}[^:]+: (.+)', notification_title,
'video title', default=None)
- if title:
- title = title.replace('\xad', '') # remove soft hyphens
upload_date = (strftime_or_none(self._extract_time_text(notification, 'sentTimeText')[0], '%Y%m%d')
if self._configuration_arg('approximate_date', ie_key=YoutubeTabIE.ie_key())
else None)
projects / yt-dlp.git / blobdiff