1
0
Fork 0
mirror of https://gitlab.com/dstftw/youtube-dl.git synced 2020-11-16 09:42:26 +00:00

[tv4] Add new extractor (Closes #4839) (Closes #2103)

This commit is contained in:
Naglis Jonaitis 2015-02-20 14:13:41 +02:00
parent dd0a58f5f0
commit 50efb383f0
2 changed files with 101 additions and 0 deletions

View file

@ -490,6 +490,7 @@ from .tumblr import TumblrIE
from .tunein import TuneInIE from .tunein import TuneInIE
from .turbo import TurboIE from .turbo import TurboIE
from .tutv import TutvIE from .tutv import TutvIE
from .tv4 import TV4IE
from .tvigle import TvigleIE from .tvigle import TvigleIE
from .tvp import TvpIE, TvpSeriesIE from .tvp import TvpIE, TvpSeriesIE
from .tvplay import TVPlayIE from .tvplay import TVPlayIE

100
youtube_dl/extractor/tv4.py Normal file
View file

@ -0,0 +1,100 @@
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_iso8601,
)
class TV4IE(InfoExtractor):
IE_DESC = 'tv4.se and tv4play.se'
_VALID_URL = r'''(?x)https?://(?:www\.)?
(?:
tv4\.se/(?:[^/]+)/klipp/(?:.*)-|
tv4play\.se/
(?:
(?:program|barn)/(?:[^\?]+)\?video_id=|
iframe/video/|
film/|
sport/|
)
)(?P<id>[0-9]+)'''
_TESTS = [
{
'url': 'http://www.tv4.se/kalla-fakta/klipp/kalla-fakta-5-english-subtitles-2491650',
'md5': '909d6454b87b10a25aa04c4bdd416a9b',
'info_dict': {
'id': '2491650',
'ext': 'mp4',
'title': 'Kalla Fakta 5 (english subtitles)',
'thumbnail': 're:^https?://.*\.jpg$',
'timestamp': int,
'upload_date': '20131125',
},
},
{
'url': 'http://www.tv4play.se/iframe/video/3054113',
'md5': '77f851c55139ffe0ebd41b6a5552489b',
'info_dict': {
'id': '3054113',
'ext': 'mp4',
'title': 'Så här jobbar ficktjuvarna - se avslöjande bilder',
'thumbnail': 're:^https?://.*\.jpg$',
'description': 'Unika bilder avslöjar hur turisternas fickor vittjas mitt på Stockholms central. Två experter på ficktjuvarna avslöjar knepen du ska se upp för.',
'timestamp': int,
'upload_date': '20150130',
},
},
{
'url': 'http://www.tv4play.se/sport/3060959',
'only_matching': True,
},
{
'url': 'http://www.tv4play.se/film/2378136',
'only_matching': True,
},
{
'url': 'http://www.tv4play.se/barn/looney-tunes?video_id=3062412',
'only_matching': True,
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
info = self._download_json(
'http://www.tv4play.se/player/assets/%s.json' % video_id, video_id, 'Downloading video info JSON')
# If is_geo_restricted is true, it doesn't neceserally mean we can't download it
if info['is_geo_restricted']:
self.report_warning('This content might not be available in your country due to licensing restrictions.')
if info['requires_subscription']:
raise ExtractorError('This content requires subscription.', expected=True)
sources_data = self._download_json(
'https://prima.tv4play.se/api/web/asset/%s/play.json?protocol=http&videoFormat=MP4' % video_id, video_id, 'Downloading sources JSON')
sources = sources_data['playback']
formats = []
for item in sources.get('items', {}).get('item', []):
ext, bitrate = item['mediaFormat'], item['bitrate']
formats.append({
'format_id': '%s_%s' % (ext, bitrate),
'tbr': bitrate,
'ext': ext,
'url': item['url'],
})
self._sort_formats(formats)
return {
'id': video_id,
'title': info['title'],
'formats': formats,
'description': info.get('description'),
'timestamp': parse_iso8601(info.get('broadcast_date_time')),
'duration': info.get('duration'),
'thumbnail': info.get('image'),
'is_live': sources.get('live'),
}