external/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-10 01:02:13 +01:00
Code Issues Projects Releases Packages Wiki Activity

[ie/nfb] Fix extractors (#9650)

Browse source 
Authored by: rrgomes
This commit is contained in:
rrgomes 2024-05-11 12:38:41 -04:00 committed by GitHub
parent 4cc99d7b6c
commit 0a1a8e3005
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 10 additions and 17 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
yt_dlp/extractor/nfb.py
View file

@ -5,7 +5,6 @@
merge_dicts, merge_dicts,
parse_count, parse_count,
url_or_none, url_or_none,
urljoin,
) )
from ..utils.traversal import traverse_obj from ..utils.traversal import traverse_obj
@ -16,8 +15,7 @@ class NFBBaseIE(InfoExtractor):
def _extract_ep_data(self, webpage, video_id, fatal=False): def _extract_ep_data(self, webpage, video_id, fatal=False):
return self._search_json( return self._search_json(
r'const\s+episodesData\s*=', webpage, 'episode data', video_id, r'episodesData\s*:', webpage, 'episode data', video_id, fatal=fatal) or {}
contains_pattern=r'\[\s*{(?s:.+)}\s*\]', fatal=fatal) or []
def _extract_ep_info(self, data, video_id, slug=None): def _extract_ep_info(self, data, video_id, slug=None):
info = traverse_obj(data, (lambda _, v: video_id in v['embed_url'], { info = traverse_obj(data, (lambda _, v: video_id in v['embed_url'], {
@ -224,18 +222,14 @@ def _real_extract(self, url):
# type_ can change from film to serie(s) after redirect; new slug may have episode number # type_ can change from film to serie(s) after redirect; new slug may have episode number
type_, slug = self._match_valid_url(urlh.url).group('type', 'id') type_, slug = self._match_valid_url(urlh.url).group('type', 'id')
embed_url = urljoin(f'https://www.{site}.ca', self._html_search_regex( player_data = self._search_json(
r'<[^>]+\bid=["\']player-iframe["\'][^>]*\bsrc=["\']([^"\']+)', webpage, 'embed url')) r'window\.PLAYER_OPTIONS\[[^\]]+\]\s*=', webpage, 'player data', slug)
video_id = self._match_id(embed_url) # embed url has unique slug video_id = self._match_id(player_data['overlay']['url']) # overlay url always has unique slug
player = self._download_webpage(embed_url, video_id, 'Downloading player page')
if 'MESSAGE_GEOBLOCKED' in player:
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
formats, subtitles = self._extract_m3u8_formats_and_subtitles( formats, subtitles = self._extract_m3u8_formats_and_subtitles(
self._html_search_regex(r'source:\s*\'([^\']+)', player, 'm3u8 url'), player_data['source'], video_id, 'mp4', m3u8_id='hls')
video_id, 'mp4', m3u8_id='hls')
if dv_source := self._html_search_regex(r'dvSource:\s*\'([^\']+)', player, 'dv', default=None): if dv_source := url_or_none(player_data.get('dvSource')):
fmts, subs = self._extract_m3u8_formats_and_subtitles( fmts, subs = self._extract_m3u8_formats_and_subtitles(
dv_source, video_id, 'mp4', m3u8_id='dv', preference=-2, fatal=False) dv_source, video_id, 'mp4', m3u8_id='dv', preference=-2, fatal=False)
for fmt in fmts: for fmt in fmts:
@ -246,17 +240,16 @@ def _real_extract(self, url):
info = { info = {
'id': video_id, 'id': video_id,
'title': self._html_search_regex( 'title': self._html_search_regex(
r'<[^>]+\bid=["\']titleHeader["\'][^>]*>\s*<h1[^>]*>\s*([^<]+?)\s*</h1>', r'["\']nfb_version_title["\']\s*:\s*["\']([^"\']+)',
webpage, 'title', default=None), webpage, 'title', default=None),
'description': self._html_search_regex( 'description': self._html_search_regex(
r'<[^>]+\bid=["\']tabSynopsis["\'][^>]*>\s*<p[^>]*>\s*([^<]+)', r'<[^>]+\bid=["\']tabSynopsis["\'][^>]*>\s*<p[^>]*>\s*([^<]+)',
webpage, 'description', default=None), webpage, 'description', default=None),
'thumbnail': self._html_search_regex( 'thumbnail': url_or_none(player_data.get('poster')),
r'poster:\s*\'([^\']+)', player, 'thumbnail', default=None),
'uploader': self._html_search_regex( 'uploader': self._html_search_regex(
r'<[^>]+\bitemprop=["\']name["\'][^>]*>([^<]+)', webpage, 'uploader', default=None), r'<[^>]+\bitemprop=["\']director["\'][^>]*>([^<]+)', webpage, 'uploader', default=None),
'release_year': int_or_none(self._html_search_regex( 'release_year': int_or_none(self._html_search_regex(
r'<[^>]+\bitemprop=["\']datePublished["\'][^>]*>([^<]+)', r'["\']nfb_version_year["\']\s*:\s*["\']([^"\']+)',
webpage, 'release_year', default=None)), webpage, 'release_year', default=None)),
} if type_ == 'film' else self._extract_ep_info(self._extract_ep_data(webpage, video_id, slug), video_id) } if type_ == 'film' else self._extract_ep_info(self._extract_ep_data(webpage, video_id, slug), video_id)