[extractor] Improve _generic_title

This commit is contained in:
pukkandan 2022-10-31 17:35:20 +05:30
parent 682b4524bf
commit 62b8dac490
No known key found for this signature in database
GPG Key ID: 7EEE9E1E817D0A39
16 changed files with 21 additions and 34 deletions

View File

@ -303,9 +303,7 @@ def _real_extract(self, url):
if any(ie.suitable(video) for ie in (ArteTVIE, ArteTVPlaylistIE, )):
items.append(video)
title = (self._og_search_title(webpage, default=None)
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title>', default=None))
title = strip_or_none(title.rsplit('|', 1)[0]) or self._generic_title(url)
title = strip_or_none(self._generic_title('', webpage, default='').rsplit('|', 1)[0]) or None
return self.playlist_from_matches(items, playlist_id=playlist_id, playlist_title=title,
description=self._og_search_description(webpage, default=None))

View File

@ -898,12 +898,8 @@ def _real_extract(self, url):
json_ld_info = self._search_json_ld(webpage, playlist_id, default={})
timestamp = json_ld_info.get('timestamp')
playlist_title = json_ld_info.get('title')
if not playlist_title:
playlist_title = (self._og_search_title(webpage, default=None)
or self._html_extract_title(webpage, 'playlist title', default=None))
if playlist_title:
playlist_title = re.sub(r'(.+)\s*-\s*BBC.*?$', r'\1', playlist_title).strip()
playlist_title = json_ld_info.get('title') or re.sub(
r'(.+)\s*-\s*BBC.*?$', r'\1', self._generic_title('', webpage, default='')).strip() or None
playlist_description = json_ld_info.get(
'description') or self._og_search_description(webpage, default=None)

View File

@ -27,8 +27,7 @@ def _real_extract(self, url):
self._sort_formats(formats)
return {
'id': video_id,
'title': (self._og_search_title(webpage, default=None)
or self._html_extract_title(webpage, 'video title')),
'title': self._generic_title('', webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'age_limit': self._rta_search(webpage),

View File

@ -51,9 +51,7 @@ def _real_extract(self, url):
episode = next_data['props']['pageProps']['episode']
id = episode['id']
title = (episode.get('title')
or self._og_search_title(webpage, fatal=False)
or self._html_extract_title(webpage))
title = episode.get('title') or self._generic_title('', webpage)
url = episode['m3u8']
formats = self._extract_m3u8_formats(url, display_id, ext='ts')
self._sort_formats(formats)

View File

@ -3820,9 +3820,11 @@ def geo_verification_headers(self):
def _generic_id(url):
return urllib.parse.unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
@staticmethod
def _generic_title(url):
return urllib.parse.unquote(os.path.splitext(url_basename(url))[0])
def _generic_title(self, url='', webpage='', *, default=None):
return (self._og_search_title(webpage, default=None)
or self._html_extract_title(webpage, default=None)
or urllib.parse.unquote(os.path.splitext(url_basename(url))[0])
or default)
@staticmethod
def _availability(is_private=None, needs_premium=None, needs_subscription=None, needs_auth=None, is_unlisted=None):

View File

@ -275,8 +275,7 @@ def _real_extract(self, url):
self._search_regex(r'jwsetup\s*=\s*({(?:.|\n)[^;]+});', webpage, 'player config'),
video_id, transform_source=js_to_json)
title = (self._og_search_title(webpage, default=None)
or self._html_extract_title(webpage, 'video title'))
title = self._generic_title('', webpage)
description = (self._og_search_description(webpage, default=None)
or self._html_search_meta('description', webpage, 'description', default=None))

View File

@ -71,7 +71,7 @@ def _real_extract(self, url):
r'<a[^>]+?href="([^"]+)"[^>]+?class="videoplayer"'],
webpage, 'video url')
title = self._og_search_title(webpage, default=None) or self._html_extract_title(webpage)
title = self._generic_title('', webpage)
duration = int_or_none(self._og_search_property(
'video:duration', webpage, 'duration', default=None))

View File

@ -2740,8 +2740,7 @@ def _real_extract(self, url):
# Site Name | Video Title
# Video Title - Tagline | Site Name
# and so on and so forth; it's just not practical
'title': (self._og_search_title(webpage, default=None)
or self._html_extract_title(webpage, 'video title', default='video')),
'title': self._generic_title('', webpage, default='video'),
'description': self._og_search_description(webpage, default=None),
'thumbnail': self._og_search_thumbnail(webpage, default=None),
'age_limit': self._rta_search(webpage),

View File

@ -20,7 +20,7 @@ class HTML5MediaEmbedIE(InfoExtractor):
]
def _extract_from_webpage(self, url, webpage):
video_id, title = self._generic_id(url), self._generic_title(url)
video_id, title = self._generic_id(url), self._generic_title(url, webpage)
entries = self._parse_html5_media_entries(url, webpage, video_id, m3u8_id='hls') or []
for num, entry in enumerate(entries, start=1):
entry.update({

View File

@ -20,7 +20,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(url, video_id)
title = self._html_extract_title(webpage, default=None) or self._og_search_title(webpage)
title = self._generic_title('', webpage)
video_url = self._proto_relative_url(self._search_regex(
r'<source[^>]+src=(["\'])(?P<url>.+?)\1',
webpage, 'video URL', default=None,

View File

@ -48,9 +48,7 @@ def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(
webpage, default=None) or self._html_search_regex(
r'<title[^>]*>([^<]+)</title>', webpage, 'title')
title = self._generic_title('', webpage)
formats = []

View File

@ -321,8 +321,7 @@ def _real_extract(self, url):
webpage = self._download_webpage(f'https://www.nhk.or.jp/school/{program_id}/', program_id)
title = (self._og_search_title(webpage)
or self._html_extract_title(webpage)
title = (self._generic_title('', webpage)
or self._html_search_regex(r'<h3>([^<]+?)とは?\s*</h3>', webpage, 'title', fatal=False))
title = re.sub(r'\s*\|\s*NHK\s+for\s+School\s*$', '', title) if title else None
description = self._html_search_regex(

View File

@ -106,7 +106,6 @@ def _real_extract(self, url):
playlist_title = (
traverse_obj(fusion_metadata, ('headlines', 'basic'))
or self._og_search_title(webpage)
or self._html_extract_title(webpage)
or self._generic_title('', webpage)
)
return self.playlist_result(entries, display_id, playlist_title)

View File

@ -166,7 +166,7 @@ def _real_extract(self, url):
self._sort_formats(formats)
return {
'id': video_id,
'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
'title': self._generic_title('', webpage),
'formats': formats,
'live_status': 'is_live',
'view_count': json_data.get('num_view'),

View File

@ -142,7 +142,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
'title': self._generic_title('', webpage),
'description': self._html_search_regex(
(r'<span itemprop="description" content=["\']([^"\']+)["\']>', *self._og_regexes('description')),
webpage, 'description', fatal=False),

View File

@ -74,6 +74,6 @@ def _real_extract(self, url):
'formats': formats,
'subtitles': subtitles,
'thumbnail': thumbnail or self._og_search_thumbnail(webpage),
'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
'title': self._generic_title('', webpage),
'description': self._og_search_description(webpage, default=None),
}