mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-08-17 12:50:40 +02:00
70 lines
2.6 KiB
Python
70 lines
2.6 KiB
Python
# encoding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
import datetime
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
class AftonbladetIE(InfoExtractor):
|
|
_VALID_URL = r'^http://tv\.aftonbladet\.se/webbtv.+?(?P<video_id>article[0-9]+)\.ab(?:$|[?#])'
|
|
_TEST = {
|
|
'url': 'http://tv.aftonbladet.se/webbtv/nyheter/vetenskap/rymden/article36015.ab',
|
|
'info_dict': {
|
|
'id': 'article36015',
|
|
'ext': 'mp4',
|
|
'title': 'Vulkanutbrott i rymden - nu släpper NASA bilderna',
|
|
'description': 'Jupiters måne mest aktiv av alla himlakroppar',
|
|
'upload_date': '20140306',
|
|
},
|
|
}
|
|
|
|
def _real_extract(self, url):
|
|
mobj = re.search(self._VALID_URL, url)
|
|
|
|
video_id = mobj.group('video_id')
|
|
webpage = self._download_webpage(url, video_id)
|
|
|
|
# find internal video meta data
|
|
META_URL = 'http://aftonbladet-play.drlib.aptoma.no/video/%s.json'
|
|
internal_meta_id = self._html_search_regex(
|
|
r'data-aptomaId="([\w\d]+)"', webpage, 'internal_meta_id')
|
|
internal_meta_url = META_URL % internal_meta_id
|
|
internal_meta_json = self._download_json(
|
|
internal_meta_url, video_id, 'Downloading video meta data')
|
|
|
|
# find internal video formats
|
|
FORMATS_URL = 'http://aftonbladet-play.videodata.drvideo.aptoma.no/actions/video/?id=%s'
|
|
internal_video_id = internal_meta_json['videoId']
|
|
internal_formats_url = FORMATS_URL % internal_video_id
|
|
internal_formats_json = self._download_json(
|
|
internal_formats_url, video_id, 'Downloading video formats')
|
|
|
|
formats = []
|
|
for fmt in internal_formats_json['formats']['http']['pseudostreaming']['mp4']:
|
|
p = fmt['paths'][0]
|
|
formats.append({
|
|
'url': 'http://%s:%d/%s/%s' % (p['address'], p['port'], p['path'], p['filename']),
|
|
'ext': 'mp4',
|
|
'width': fmt['width'],
|
|
'height': fmt['height'],
|
|
'tbr': fmt['bitrate'],
|
|
'protocol': 'http',
|
|
})
|
|
self._sort_formats(formats)
|
|
|
|
timestamp = datetime.datetime.fromtimestamp(internal_meta_json['timePublished'])
|
|
upload_date = timestamp.strftime('%Y%m%d')
|
|
|
|
return {
|
|
'id': video_id,
|
|
'title': internal_meta_json['title'],
|
|
'formats': formats,
|
|
'thumbnail': internal_meta_json['imageUrl'],
|
|
'description': internal_meta_json['shortPreamble'],
|
|
'upload_date': upload_date,
|
|
'duration': internal_meta_json['duration'],
|
|
'view_count': internal_meta_json['views'],
|
|
}
|