github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-07 20:30:41 -05:00
Code Issues Projects Releases Packages Wiki Activity

[ie/orf:on] Improve extraction (#9677)

Browse source 
Closes #9652
Authored by: TuxCoder
This commit is contained in:
TuxCoder 2024-05-23 06:25:16 +02:00 committed by GitHub
parent be7db1a5a8
commit 0dd53faeca
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 33 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

42
yt_dlp/extractor/orf.py
View file

@ -14,6 +14,7 @@
make_archive_id, make_archive_id,
mimetype2ext, mimetype2ext,
orderedSet, orderedSet,
parse_age_limit,
remove_end, remove_end,
smuggle_url, smuggle_url,
strip_jsonp, strip_jsonp,
@ -569,7 +570,7 @@ def _real_extract(self, url):
class ORFONIE(InfoExtractor): class ORFONIE(InfoExtractor):
IE_NAME = 'orf:on' IE_NAME = 'orf:on'
_VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d{8})/(?P<slug>[\w-]+)' _VALID_URL = r'https?://on\.orf\.at/video/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'https://on.orf.at/video/14210000/school-of-champions-48', 'url': 'https://on.orf.at/video/14210000/school-of-champions-48',
'info_dict': { 'info_dict': {
@ -583,32 +584,55 @@ class ORFONIE(InfoExtractor):
'timestamp': 1706472362, 'timestamp': 1706472362,
'upload_date': '20240128', 'upload_date': '20240128',
} }
}, {
'url': 'https://on.orf.at/video/3220355',
'md5': 'f94d98e667cf9a3851317efb4e136662',
'info_dict': {
'id': '3220355',
'ext': 'mp4',
'duration': 445.04,
'thumbnail': 'https://api-tvthek.orf.at/assets/segments/0002/60/thumb_159573_segments_highlight_teaser.png',
'title': '50 Jahre Burgenland: Der Festumzug',
'description': 'md5:1560bf855119544ee8c4fa5376a2a6b0',
'media_type': 'episode',
'timestamp': 52916400,
'upload_date': '19710905',
}
}] }]
def _extract_video(self, video_id, display_id): def _extract_video(self, video_id):
encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode() encrypted_id = base64.b64encode(f'3dSlfek03nsLKdj4Jsd{video_id}'.encode()).decode()
api_json = self._download_json( api_json = self._download_json(
f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', display_id) f'https://api-tvthek.orf.at/api/v4.3/public/episode/encrypted/{encrypted_id}', video_id)
if traverse_obj(api_json, 'is_drm_protected'):
self.report_drm(video_id)
formats, subtitles = [], {} formats, subtitles = [], {}
for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)): for manifest_type in traverse_obj(api_json, ('sources', {dict.keys}, ...)):
for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})): for manifest_url in traverse_obj(api_json, ('sources', manifest_type, ..., 'src', {url_or_none})):
if manifest_type == 'hls': if manifest_type == 'hls':
fmts, subs = self._extract_m3u8_formats_and_subtitles( fmts, subs = self._extract_m3u8_formats_and_subtitles(
manifest_url, display_id, fatal=False, m3u8_id='hls') manifest_url, video_id, fatal=False, m3u8_id='hls')
elif manifest_type == 'dash': elif manifest_type == 'dash':
fmts, subs = self._extract_mpd_formats_and_subtitles( fmts, subs = self._extract_mpd_formats_and_subtitles(
manifest_url, display_id, fatal=False, mpd_id='dash') manifest_url, video_id, fatal=False, mpd_id='dash')
else: else:
continue continue
formats.extend(fmts) formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles) self._merge_subtitles(subs, target=subtitles)
for sub_url in traverse_obj(api_json, (
'_embedded', 'subtitle',
('xml_url', 'sami_url', 'stl_url', 'ttml_url', 'srt_url', 'vtt_url'), {url_or_none})):
self._merge_subtitles({'de': [{'url': sub_url}]}, target=subtitles)
return { return {
'id': video_id, 'id': video_id,
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
**traverse_obj(api_json, { **traverse_obj(api_json, {
'age_limit': ('age_classification', {parse_age_limit}),
'duration': ('duration_second', {float_or_none}), 'duration': ('duration_second', {float_or_none}),
'title': (('title', 'headline'), {str}), 'title': (('title', 'headline'), {str}),
'description': (('description', 'teaser_text'), {str}), 'description': (('description', 'teaser_text'), {str}),
@ -617,14 +641,14 @@ def _extract_video(self, video_id, display_id):
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id, display_id = self._match_valid_url(url).group('id', 'slug') video_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, video_id)
return { return {
'id': video_id, 'id': video_id,
'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None), 'title': self._html_search_meta(['og:title', 'twitter:title'], webpage, default=None),
'description': self._html_search_meta( 'description': self._html_search_meta(
['description', 'og:description', 'twitter:description'], webpage, default=None), ['description', 'og:description', 'twitter:description'], webpage, default=None),
**self._search_json_ld(webpage, display_id, fatal=False), **self._search_json_ld(webpage, video_id, fatal=False),
**self._extract_video(video_id, display_id), **self._extract_video(video_id),
} }