Allow extractors to specify section_start/end for clips

This commit is contained in:
pukkandan 2022-06-22 02:32:14 +05:30
parent 230d5c8239
commit 3975b4d2e8
No known key found for this signature in database
GPG Key ID: 7EEE9E1E817D0A39
2 changed files with 17 additions and 5 deletions

View File

@ -1596,9 +1596,13 @@ def process_ie_result(self, ie_result, download=True, extra_info=None):
if not info: if not info:
return info return info
exempted_fields = {'_type', 'url', 'ie_key'}
if not ie_result.get('section_end') and ie_result.get('section_start') is None:
# For video clips, the id etc of the clip extractor should be used
exempted_fields |= {'id', 'extractor', 'extractor_key'}
new_result = info.copy() new_result = info.copy()
new_result.update(filter_dict(ie_result, lambda k, v: ( new_result.update(filter_dict(ie_result, lambda k, v: v is not None and k not in exempted_fields))
v is not None and k not in {'_type', 'url', 'id', 'extractor', 'extractor_key', 'ie_key'})))
# Extracted info may not be a video result (i.e. # Extracted info may not be a video result (i.e.
# info.get('_type', 'video') != video) but rather an url or # info.get('_type', 'video') != video) but rather an url or
@ -2369,6 +2373,8 @@ def sanitize_numeric_fields(info):
sanitize_string_field(info_dict, 'id') sanitize_string_field(info_dict, 'id')
sanitize_numeric_fields(info_dict) sanitize_numeric_fields(info_dict)
if info_dict.get('section_end') and info_dict.get('section_start') is not None:
info_dict['duration'] = round(info_dict['section_end'] - info_dict['section_start'], 3)
if (info_dict.get('duration') or 0) <= 0 and info_dict.pop('duration', None): if (info_dict.get('duration') or 0) <= 0 and info_dict.pop('duration', None):
self.report_warning('"duration" field is negative, there is an error in extractor') self.report_warning('"duration" field is negative, there is an error in extractor')
@ -2604,10 +2610,11 @@ def to_screen(*msg):
for fmt, chapter in itertools.product(formats_to_download, requested_ranges or [{}]): for fmt, chapter in itertools.product(formats_to_download, requested_ranges or [{}]):
new_info = self._copy_infodict(info_dict) new_info = self._copy_infodict(info_dict)
new_info.update(fmt) new_info.update(fmt)
if chapter: offset, duration = info_dict.get('section_start') or 0, info_dict.get('duration') or float('inf')
if chapter or offset:
new_info.update({ new_info.update({
'section_start': chapter.get('start_time'), 'section_start': offset + chapter.get('start_time', 0),
'section_end': chapter.get('end_time', 0), 'section_end': offset + min(chapter.get('end_time', 0), duration),
'section_title': chapter.get('title'), 'section_title': chapter.get('title'),
'section_number': chapter.get('index'), 'section_number': chapter.get('index'),
}) })

View File

@ -385,6 +385,11 @@ class InfoExtractor:
release_year: Year (YYYY) when the album was released. release_year: Year (YYYY) when the album was released.
composer: Composer of the piece composer: Composer of the piece
The following fields should only be set for clips that should be cut from the original video:
section_start: Start time of the section in seconds
section_end: End time of the section in seconds
Unless mentioned otherwise, the fields should be Unicode strings. Unless mentioned otherwise, the fields should be Unicode strings.
Unless mentioned otherwise, None is equivalent to absence of information. Unless mentioned otherwise, None is equivalent to absence of information.