Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Fork Sync #23

Merged
merged 4 commits into from
Nov 21, 2020
Merged

Fork Sync #23

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0ada1b9
[svt] Extract timestamp and thumbnail in more cases (#27130)
wader Nov 21, 2020
049f224
[svtplay] Add support for svt.se/barnkanalen (closes #24817)
dstftw Nov 21, 2020
1e72660
[svtplay] Fix test title
dstftw Nov 21, 2020
82abc13
[youtube:tab] Comment out test
dstftw Nov 21, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
48 changes: 37 additions & 11 deletions youtube_dl/extractor/svt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
determine_ext,
dict_get,
int_or_none,
unified_timestamp,
str_or_none,
strip_or_none,
try_get,
Expand Down Expand Up @@ -44,7 +45,8 @@ def _extract_video(self, video_info, video_id):
'format_id': player_type,
'url': vurl,
})
if not formats and video_info.get('rights', {}).get('geoBlockedSweden'):
rights = try_get(video_info, lambda x: x['rights'], dict) or {}
if not formats and rights.get('geoBlockedSweden'):
self.raise_geo_restricted(
'This video is only available in Sweden',
countries=self._GEO_COUNTRIES)
Expand All @@ -70,6 +72,7 @@ def _extract_video(self, video_info, video_id):
episode = video_info.get('episodeTitle')
episode_number = int_or_none(video_info.get('episodeNumber'))

timestamp = unified_timestamp(rights.get('validFrom'))
duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
age_limit = None
adult = dict_get(
Expand All @@ -84,6 +87,7 @@ def _extract_video(self, video_info, video_id):
'formats': formats,
'subtitles': subtitles,
'duration': duration,
'timestamp': timestamp,
'age_limit': age_limit,
'series': series,
'season_number': season_number,
Expand Down Expand Up @@ -136,26 +140,39 @@ class SVTPlayIE(SVTPlayBaseIE):
IE_DESC = 'SVT Play and Öppet arkiv'
_VALID_URL = r'''(?x)
(?:
svt:(?P<svt_id>[^/?#&]+)|
(?:
svt:|
https?://(?:www\.)?svt\.se/barnkanalen/barnplay/[^/]+/
)
(?P<svt_id>[^/?#&]+)|
https?://(?:www\.)?(?:svtplay|oppetarkiv)\.se/(?:video|klipp|kanaler)/(?P<id>[^/?#&]+)
)
'''
_TESTS = [{
'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2',
'md5': '2b6704fe4a28801e1a098bbf3c5ac611',
'url': 'https://www.svtplay.se/video/26194546/det-har-ar-himlen',
'md5': '2382036fd6f8c994856c323fe51c426e',
'info_dict': {
'id': '5996901',
'id': 'jNwpV9P',
'ext': 'mp4',
'title': 'Flygplan till Haile Selassie',
'duration': 3527,
'thumbnail': r're:^https?://.*[\.-]jpg$',
'title': 'Det här är himlen',
'timestamp': 1586044800,
'upload_date': '20200405',
'duration': 3515,
'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
'age_limit': 0,
'subtitles': {
'sv': [{
'ext': 'wsrt',
'ext': 'vtt',
}]
},
},
'params': {
'format': 'bestvideo',
# skip for now due to download test asserts that segment is > 10000 bytes and svt uses
# init segments that are smaller
# AssertionError: Expected test_SVTPlay_jNwpV9P.mp4 to be at least 9.77KiB, but it's only 864.00B
'skip_download': True,
},
}, {
# geo restricted to Sweden
'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
Expand All @@ -172,6 +189,12 @@ class SVTPlayIE(SVTPlayBaseIE):
}, {
'url': 'svt:14278044',
'only_matching': True,
}, {
'url': 'https://www.svt.se/barnkanalen/barnplay/kar/eWv5MLX/',
'only_matching': True,
}, {
'url': 'svt:eWv5MLX',
'only_matching': True,
}]

def _adjust_title(self, info):
Expand Down Expand Up @@ -236,7 +259,10 @@ def _real_extract(self, url):
r'["\']svtId["\']\s*:\s*["\']([\da-zA-Z-]+)'),
webpage, 'video id')

return self._extract_by_video_id(svt_id, webpage)
info_dict = self._extract_by_video_id(svt_id, webpage)
info_dict['thumbnail'] = thumbnail

return info_dict


class SVTSeriesIE(SVTPlayBaseIE):
Expand Down Expand Up @@ -360,7 +386,7 @@ class SVTPageIE(InfoExtractor):

@classmethod
def suitable(cls, url):
return False if SVTIE.suitable(url) else super(SVTPageIE, cls).suitable(url)
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super(SVTPageIE, cls).suitable(url)

def _real_extract(self, url):
path, display_id = re.match(self._VALID_URL, url).groups()
Expand Down
11 changes: 7 additions & 4 deletions youtube_dl/extractor/youtube.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2620,10 +2620,13 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
}, {
'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
'only_matching': True,
}, {
'url': 'https://www.youtube.com/TheYoungTurks/live',
'only_matching': True,
}]
},
# TODO
# {
# 'url': 'https://www.youtube.com/TheYoungTurks/live',
# 'only_matching': True,
# }
]

def _extract_channel_id(self, webpage):
channel_id = self._html_search_meta(
Expand Down