yt-dlp/youtube_dl/extractor/vgtv.py

236 lines
8.1 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2015-05-30 09:15:42 +00:00
from ..utils import (
ExtractorError,
float_or_none,
)
class VGTVIE(InfoExtractor):
IE_DESC = 'VGTV, BTTV, FTV, Aftenposten, Aftonbladet'
_VALID_URL = r'''(?x)
(?:
vgtv:|
http://(?:www\.)?
)
(?P<host>vgtv.no|(?:bt.no|aftenbladet.no)/tv|fvn.no/fvntv|aftenposten.no/webtv)
(?:
:|
/\#!/(?:video|live)/|
/embed?id=
)
(?P<id>[0-9]+)
'''
_TESTS = [
{
# streamType: vod
'url': 'http://www.vgtv.no/#!/video/84196/hevnen-er-soet-episode-10-abu',
'md5': 'b8be7a234cebb840c0d512c78013e02f',
'info_dict': {
'id': '84196',
'ext': 'mp4',
2014-12-03 18:07:09 +00:00
'title': 'Hevnen er søt: Episode 10 - Abu',
'description': 'md5:e25e4badb5f544b04341e14abdc72234',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 648.000,
'timestamp': 1404626400,
2014-09-08 14:33:03 +00:00
'upload_date': '20140706',
'view_count': int,
},
},
{
# streamType: wasLive
'url': 'http://www.vgtv.no/#!/live/100764/opptak-vgtv-foelger-em-kvalifiseringen',
'info_dict': {
'id': '100764',
2014-09-30 12:50:14 +00:00
'ext': 'flv',
'title': 'OPPTAK: VGTV følger EM-kvalifiseringen',
'description': 'md5:3772d9c0dc2dff92a886b60039a7d4d3',
'thumbnail': 're:^https?://.*\.jpg',
2014-12-03 18:07:09 +00:00
'duration': 9103.0,
'timestamp': 1410113864,
2014-09-08 14:33:03 +00:00
'upload_date': '20140907',
'view_count': int,
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'Video is no longer available',
},
{
# streamType: wasLive
2015-05-30 10:12:07 +00:00
'url': 'http://www.vgtv.no/#!/live/113063/direkte-v75-fra-solvalla',
'info_dict': {
2015-05-30 10:12:07 +00:00
'id': '113063',
'ext': 'mp4',
'title': 'V75 fra Solvalla 30.05.15',
2015-05-30 10:12:07 +00:00
'description': 'md5:b3743425765355855f88e096acc93231',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 25966,
2015-05-30 10:12:07 +00:00
'timestamp': 1432975582,
'upload_date': '20150530',
2014-09-08 14:33:03 +00:00
'view_count': int,
},
'params': {
# m3u8 download
'skip_download': True,
},
},{
'url': 'http://www.aftenposten.no/webtv/#!/video/21039/trailer-sweatshop-i-can-t-take-any-more',
'md5': '7fbc265a3ca4933a423c7a66aa879a67',
'info_dict': {
'id': '21039',
'ext': 'mp4',
'title': 'TRAILER: «SWEATSHOP» - I can´t take any more',
'description': 'md5:21891f2b0dd7ec2f78d84a50e54f8238',
'duration': 66,
'timestamp': 1417002452,
'upload_date': '20141126',
'view_count': int,
}
},
{
'url': 'http://www.bt.no/tv/#!/video/100250/norling-dette-er-forskjellen-paa-1-divisjon-og-eliteserien',
'only_matching': True,
},
]
_HOST_WEBSITES = {
'vgtv.no': {
'vendor': 'vgtv',
'appname': 'vgtv',
},
'bt.no/tv': {
'vendor': 'bt',
'appname': 'bttv',
},
'aftenbladet.no/tv': {
'vendor': 'sa',
'appname': 'satv',
},
'fvn.no/fvntv': {
'vendor': 'fvn',
'appname': 'fvntv',
},
'aftenposten.no/webtv': {
'vendor': 'ap',
'appname': 'aptv',
},
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
host = mobj.group('host')
data = self._download_json(
'http://svp.vg.no/svp/api/v1/%s/assets/%s?appName=%s-website'
% (self._HOST_WEBSITES[host]['vendor'], video_id, self._HOST_WEBSITES[host]['appname']),
video_id, 'Downloading media JSON')
2015-05-30 09:15:42 +00:00
if data.get('status') == 'inactive':
raise ExtractorError(
'Video %s is no longer available' % video_id, expected=True)
streams = data['streamUrls']
2015-05-30 10:12:07 +00:00
stream_type = data.get('streamType')
formats = []
hls_url = streams.get('hls')
if hls_url:
2015-05-09 15:23:09 +00:00
formats.extend(self._extract_m3u8_formats(
hls_url, video_id, 'mp4', m3u8_id='hls'))
hds_url = streams.get('hds')
2015-05-30 09:14:10 +00:00
# wasLive hds are always 404
2015-05-30 10:12:07 +00:00
if hds_url and stream_type != 'wasLive':
2015-05-09 15:23:09 +00:00
formats.extend(self._extract_f4m_formats(
hds_url + '?hdcore=3.2.0&plugin=aasp-3.2.0.77.18',
video_id, f4m_id='hds'))
mp4_url = streams.get('mp4')
if mp4_url:
_url = hls_url or hds_url
MP4_URL_TEMPLATE = '%s/%%s.%s' % (mp4_url.rpartition('/')[0], mp4_url.rpartition('.')[-1])
for mp4_format in _url.split(','):
m = re.search('(?P<width>\d+)_(?P<height>\d+)_(?P<vbr>\d+)', mp4_format)
if not m:
continue
width = int(m.group('width'))
height = int(m.group('height'))
vbr = int(m.group('vbr'))
formats.append({
'url': MP4_URL_TEMPLATE % mp4_format,
'format_id': 'mp4-%s' % vbr,
'width': width,
'height': height,
'vbr': vbr,
'preference': 1,
})
self._sort_formats(formats)
return {
'id': video_id,
'title': self._live_title(data['title']) if stream_type == 'live' else data['title'],
'description': data['description'],
'thumbnail': data['images']['main'] + '?t[]=900x506q80',
'timestamp': data['published'],
'duration': float_or_none(data['duration'], 1000),
'view_count': data['displays'],
'formats': formats,
2015-05-30 10:12:07 +00:00
'is_live': True if stream_type == 'live' else False,
2014-11-23 19:41:03 +00:00
}
class BTArticleIE(InfoExtractor):
IE_NAME = 'bt:article'
IE_DESC = 'Bergens Tidende Articles'
_VALID_URL = 'http://(?:www\.)?bt\.no/(?:[^/]+/)+(?P<id>[^/]+)-\d+\.html'
_TEST = {
'url': 'http://www.bt.no/nyheter/lokalt/Kjemper-for-internatet-1788214.html',
'md5': 'd055e8ee918ef2844745fcfd1a4175fb',
'info_dict': {
'id': '23199',
'ext': 'mp4',
'title': 'Alrekstad internat',
'description': 'md5:dc81a9056c874fedb62fc48a300dac58',
'thumbnail': 're:^https?://.*\.jpg',
'duration': 191,
'timestamp': 1289991323,
'upload_date': '20101117',
'view_count': int,
},
}
def _real_extract(self, url):
webpage = self._download_webpage(url, self._match_id(url))
video_id = self._search_regex(
r'SVP\.Player\.load\(\s*(\d+)', webpage, 'video id')
return self.url_result('vgtv:bt:%s' % video_id, 'VGTV')
class BTVestlendingenIE(InfoExtractor):
IE_NAME = 'bt:vestlendingen'
IE_DESC = 'Bergens Tidende - Vestlendingen'
_VALID_URL = 'http://(?:www\.)?bt\.no/spesial/vestlendingen/#!/(?P<id>\d+)'
_TEST = {
'url': 'http://www.bt.no/spesial/vestlendingen/#!/86588',
'md5': 'd7d17e3337dc80de6d3a540aefbe441b',
'info_dict': {
'id': '86588',
'ext': 'mov',
'title': 'Otto Wollertsen',
'description': 'Vestlendingen Otto Fredrik Wollertsen',
'timestamp': 1430473209,
'upload_date': '20150501',
},
}
def _real_extract(self, url):
return self.url_result('xstream:btno:%s' % self._match_id(url), 'Xstream')