Madeorsk/youtube-dl
1
0
Fork 0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-11-22 08:34:32 +01:00
Code Issues Releases Wiki Activity

[svt] Add timestamp and thumbnail in more cases

Browse Source 
Add timestamp, set to "valid from" which i think could been seen as publish time.
Add thumbnail in more cases, seems to was only done in the embedded data case for some reason.
Update API URL (current one redirects to it).
Switch svtplay test url to an existing video and also one with no expire date.
Also add an additional thumbnail url test regex.
This commit is contained in:
Mattias Wadman 2020-05-07 23:51:16 +02:00
parent d51e23d9fc
commit ca058603e5
1 changed files with 22 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
youtube_dl/extractor/svt.py
View File

@ -9,6 +9,7 @@ from ..utils import (
determine_ext, determine_ext,
dict_get, dict_get,
int_or_none, int_or_none,
parse_iso8601,
str_or_none, str_or_none,
strip_or_none, strip_or_none,
try_get, try_get,
@ -44,7 +45,8 @@ class SVTBaseIE(InfoExtractor):
'format_id': player_type, 'format_id': player_type,
'url': vurl, 'url': vurl,
}) })
if not formats and video_info.get('rights', {}).get('geoBlockedSweden'): rights = video_info.get('rights', {})
if not formats and rights.get('geoBlockedSweden'):
self.raise_geo_restricted( self.raise_geo_restricted(
'This video is only available in Sweden', 'This video is only available in Sweden',
countries=self._GEO_COUNTRIES) countries=self._GEO_COUNTRIES)
@ -70,6 +72,8 @@ class SVTBaseIE(InfoExtractor):
episode = video_info.get('episodeTitle') episode = video_info.get('episodeTitle')
episode_number = int_or_none(video_info.get('episodeNumber')) episode_number = int_or_none(video_info.get('episodeNumber'))
timestamp = parse_iso8601(rights.get('validFrom'))
duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration'))) duration = int_or_none(dict_get(video_info, ('materialLength', 'contentDuration')))
age_limit = None age_limit = None
adult = dict_get( adult = dict_get(
@ -84,6 +88,7 @@ class SVTBaseIE(InfoExtractor):
'formats': formats, 'formats': formats,
'subtitles': subtitles, 'subtitles': subtitles,
'duration': duration, 'duration': duration,
'timestamp': timestamp,
'age_limit': age_limit, 'age_limit': age_limit,
'series': series, 'series': series,
'season_number': season_number, 'season_number': season_number,
@ -141,21 +146,26 @@ class SVTPlayIE(SVTPlayBaseIE):
) )
''' '''
_TESTS = [{ _TESTS = [{
'url': 'http://www.svtplay.se/video/5996901/flygplan-till-haile-selassie/flygplan-till-haile-selassie-2', 'url': 'https://www.svtplay.se/video/13906852/en-liten-film-om/en-liten-film-torsk-pa-tallinn-en-liten-film-om-ensamhet',
'md5': '2b6704fe4a28801e1a098bbf3c5ac611', 'md5': '2382036fd6f8c994856c323fe51c426e',
'info_dict': { 'info_dict': {
'id': '5996901', 'id': 'jvR32zj',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Flygplan till Haile Selassie', 'title': 'Torsk på Tallinn - en liten film om ensamhet',
'duration': 3527, 'timestamp': 1366063200,
'thumbnail': r're:^https?://.*[\.-]jpg$', 'upload_date': '20130415',
'duration': 3510,
'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
'age_limit': 0, 'age_limit': 0,
'subtitles': { 'subtitles': {
'sv': [{ 'sv': [{
'ext': 'wsrt', 'ext': 'vtt',
}] }]
}, },
}, },
'params': {
'format': 'bestvideo',
},
}, { }, {
# geo restricted to Sweden # geo restricted to Sweden
'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten', 'url': 'http://www.oppetarkiv.se/video/5219710/trollflojten',
@ -180,7 +190,7 @@ class SVTPlayIE(SVTPlayBaseIE):
def _extract_by_video_id(self, video_id, webpage=None): def _extract_by_video_id(self, video_id, webpage=None):
data = self._download_json( data = self._download_json(
'https://api.svt.se/videoplayer-api/video/%s' % video_id, 'https://api.svt.se/video/%s' % video_id,
video_id, headers=self.geo_verification_headers()) video_id, headers=self.geo_verification_headers())
info_dict = self._extract_video(data, video_id) info_dict = self._extract_video(data, video_id)
if not info_dict.get('title'): if not info_dict.get('title'):
@ -234,8 +244,10 @@ class SVTPlayIE(SVTPlayBaseIE):
r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"'), r'"content"\s*:\s*{.*?"id"\s*:\s*"([\da-zA-Z-]+)"'),
webpage, 'video id') webpage, 'video id')
return self._extract_by_video_id(svt_id, webpage) info_dict = self._extract_by_video_id(svt_id, webpage)
info_dict.update({'thumbnail': thumbnail})
return info_dict
class SVTSeriesIE(SVTPlayBaseIE): class SVTSeriesIE(SVTPlayBaseIE):
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?' _VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?'