1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-21 23:12:50 +08:00
youtube-dl/youtube_dl/extractor/drtv.py
2015-02-18 17:20:22 +01:00

96 lines
3.3 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor, ExtractorError
from ..utils import parse_iso8601
class DRTVIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?dr\.dk/tv/se/(?:[^/]+/)*(?P<id>[\da-z-]+)(?:[/#?]|$)'
_TEST = {
'url': 'http://www.dr.dk/tv/se/partiets-mand/partiets-mand-7-8',
'md5': '4a7e1dd65cdb2643500a3f753c942f25',
'info_dict': {
'id': 'partiets-mand-7-8',
'ext': 'mp4',
'title': 'Partiets mand (7:8)',
'description': 'md5:a684b90a8f9336cd4aab94b7647d7862',
'timestamp': 1403047940,
'upload_date': '20140617',
'duration': 1299.040,
},
}
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_id = self._search_regex(
r'data-(?:material-identifier|episode-slug)="([^"]+)"',
webpage, 'video id')
programcard = self._download_json(
'http://www.dr.dk/mu/programcard/expanded/%s' % video_id,
video_id, 'Downloading video JSON')
data = programcard['Data'][0]
title = data['Title']
description = data['Description']
timestamp = parse_iso8601(data['CreatedTime'])
thumbnail = None
duration = None
restricted_to_denmark = False
formats = []
subtitles = {}
for asset in data['Assets']:
if asset['Kind'] == 'Image':
thumbnail = asset['Uri']
elif asset['Kind'] == 'VideoResource':
duration = asset['DurationInMilliseconds'] / 1000.0
restricted_to_denmark = asset['RestrictedToDenmark']
spoken_subtitles = asset['Target'] == 'SpokenSubtitles'
for link in asset['Links']:
target = link['Target']
uri = link['Uri']
format_id = target
preference = -1 if target == 'HDS' else -2
if spoken_subtitles:
preference -= 2
format_id += '-spoken-subtitles'
formats.append({
'url': uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43' if target == 'HDS' else uri,
'format_id': format_id,
'ext': link['FileFormat'],
'preference': preference,
})
subtitles_list = asset.get('SubtitlesList')
if isinstance(subtitles_list, list):
LANGS = {
'Danish': 'dk',
}
for subs in subtitles_list:
lang = subs['Language']
subtitles[LANGS.get(lang, lang)] = [{'url': subs['Uri'], 'ext': 'vtt'}]
if not formats and restricted_to_denmark:
raise ExtractorError(
'Unfortunately, DR is not allowed to show this program outside Denmark.', expected=True)
self._sort_formats(formats)
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
'subtitles': subtitles,
}