youtube-dl/youtube_dl/extractor/viewster.py

218 lines
8.8 KiB
Python
Raw Normal View History

# coding: utf-8
2015-03-13 20:12:11 +00:00
from __future__ import unicode_literals
2016-04-24 01:32:56 +00:00
import re
2015-03-13 20:12:11 +00:00
from .common import InfoExtractor
from ..compat import (
compat_HTTPError,
compat_urllib_parse_unquote,
)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
parse_iso8601,
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
sanitized_Request,
HEADRequest,
2016-04-24 01:32:56 +00:00
url_basename,
)
2015-03-13 20:12:11 +00:00
class ViewsterIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?viewster\.com/(?:serie|movie)/(?P<id>\d+-\d+-\d+)'
2015-03-13 21:18:04 +00:00
_TESTS = [{
# movie, Type=Movie
2015-03-13 21:18:04 +00:00
'url': 'http://www.viewster.com/movie/1140-11855-000/the-listening-project/',
2015-09-22 15:49:29 +00:00
'md5': 'e642d1b27fcf3a4ffa79f194f5adde36',
2015-03-13 21:18:04 +00:00
'info_dict': {
'id': '1140-11855-000',
2015-09-22 15:49:29 +00:00
'ext': 'mp4',
'title': 'The listening Project',
'description': 'md5:bac720244afd1a8ea279864e67baa071',
'timestamp': 1214870400,
'upload_date': '20080701',
'duration': 4680,
},
2015-03-13 21:18:04 +00:00
}, {
# series episode, Type=Episode
'url': 'http://www.viewster.com/serie/1284-19427-001/the-world-and-a-wall/',
2015-09-22 15:49:29 +00:00
'md5': '9243079a8531809efe1b089db102c069',
2015-03-13 21:18:04 +00:00
'info_dict': {
'id': '1284-19427-001',
2015-09-22 15:49:29 +00:00
'ext': 'mp4',
'title': 'The World and a Wall',
'description': 'md5:24814cf74d3453fdf5bfef9716d073e3',
'timestamp': 1428192000,
'upload_date': '20150405',
'duration': 1500,
},
}, {
# serie, Type=Serie
'url': 'http://www.viewster.com/serie/1303-19426-000/',
'info_dict': {
'id': '1303-19426-000',
'title': 'Is It Wrong to Try to Pick up Girls in a Dungeon?',
'description': 'md5:eeda9bef25b0d524b3a29a97804c2f11',
},
'playlist_count': 13,
}, {
# unfinished serie, no Type
'url': 'http://www.viewster.com/serie/1284-19427-000/baby-steps-season-2/',
'info_dict': {
'id': '1284-19427-000',
'title': 'Baby Steps—Season 2',
'description': 'md5:e7097a8fc97151e25f085c9eb7a1cdb1',
},
'playlist_mincount': 16,
2015-09-22 15:55:04 +00:00
}, {
# geo restricted series
'url': 'https://www.viewster.com/serie/1280-18794-002/',
'only_matching': True,
}, {
# geo restricted video
'url': 'https://www.viewster.com/serie/1280-18794-002/what-is-extraterritoriality-lawo/',
'only_matching': True,
2015-03-13 21:18:04 +00:00
}]
2015-03-13 20:12:11 +00:00
_ACCEPT_HEADER = 'application/json, text/javascript, */*; q=0.01'
def _download_json(self, url, video_id, note='Downloading JSON metadata', fatal=True, query={}):
Switch codebase to use sanitized_Request instead of compat_urllib_request.Request [downloader/dash] Use sanitized_Request [downloader/http] Use sanitized_Request [atresplayer] Use sanitized_Request [bambuser] Use sanitized_Request [bliptv] Use sanitized_Request [brightcove] Use sanitized_Request [cbs] Use sanitized_Request [ceskatelevize] Use sanitized_Request [collegerama] Use sanitized_Request [extractor/common] Use sanitized_Request [crunchyroll] Use sanitized_Request [dailymotion] Use sanitized_Request [dcn] Use sanitized_Request [dramafever] Use sanitized_Request [dumpert] Use sanitized_Request [eitb] Use sanitized_Request [escapist] Use sanitized_Request [everyonesmixtape] Use sanitized_Request [extremetube] Use sanitized_Request [facebook] Use sanitized_Request [fc2] Use sanitized_Request [flickr] Use sanitized_Request [4tube] Use sanitized_Request [gdcvault] Use sanitized_Request [extractor/generic] Use sanitized_Request [hearthisat] Use sanitized_Request [hotnewhiphop] Use sanitized_Request [hypem] Use sanitized_Request [iprima] Use sanitized_Request [ivi] Use sanitized_Request [keezmovies] Use sanitized_Request [letv] Use sanitized_Request [lynda] Use sanitized_Request [metacafe] Use sanitized_Request [minhateca] Use sanitized_Request [miomio] Use sanitized_Request [meovideo] Use sanitized_Request [mofosex] Use sanitized_Request [moniker] Use sanitized_Request [mooshare] Use sanitized_Request [movieclips] Use sanitized_Request [mtv] Use sanitized_Request [myvideo] Use sanitized_Request [neteasemusic] Use sanitized_Request [nfb] Use sanitized_Request [niconico] Use sanitized_Request [noco] Use sanitized_Request [nosvideo] Use sanitized_Request [novamov] Use sanitized_Request [nowness] Use sanitized_Request [nuvid] Use sanitized_Request [played] Use sanitized_Request [pluralsight] Use sanitized_Request [pornhub] Use sanitized_Request [pornotube] Use sanitized_Request [primesharetv] Use sanitized_Request [promptfile] Use sanitized_Request [qqmusic] Use sanitized_Request [rtve] Use sanitized_Request [safari] Use sanitized_Request [sandia] Use sanitized_Request [shared] Use sanitized_Request [sharesix] Use sanitized_Request [sina] Use sanitized_Request [smotri] Use sanitized_Request [sohu] Use sanitized_Request [spankwire] Use sanitized_Request [sportdeutschland] Use sanitized_Request [streamcloud] Use sanitized_Request [streamcz] Use sanitized_Request [tapely] Use sanitized_Request [tube8] Use sanitized_Request [tubitv] Use sanitized_Request [twitch] Use sanitized_Request [twitter] Use sanitized_Request [udemy] Use sanitized_Request [vbox7] Use sanitized_Request [veoh] Use sanitized_Request [vessel] Use sanitized_Request [vevo] Use sanitized_Request [viddler] Use sanitized_Request [videomega] Use sanitized_Request [viewvster] Use sanitized_Request [viki] Use sanitized_Request [vk] Use sanitized_Request [vodlocker] Use sanitized_Request [voicerepublic] Use sanitized_Request [wistia] Use sanitized_Request [xfileshare] Use sanitized_Request [xtube] Use sanitized_Request [xvideos] Use sanitized_Request [yandexmusic] Use sanitized_Request [youku] Use sanitized_Request [youporn] Use sanitized_Request [youtube] Use sanitized_Request [patreon] Use sanitized_Request [extractor/common] Remove unused import [nfb] PEP 8
2015-11-21 16:18:17 +00:00
request = sanitized_Request(url)
2015-03-13 20:12:11 +00:00
request.add_header('Accept', self._ACCEPT_HEADER)
request.add_header('Auth-token', self._AUTH_TOKEN)
return super(ViewsterIE, self)._download_json(request, video_id, note, fatal=fatal, query=query)
2015-03-13 20:12:11 +00:00
def _real_extract(self, url):
video_id = self._match_id(url)
# Get 'api_token' cookie
2017-02-21 18:36:39 +00:00
self._request_webpage(
HEADRequest('http://www.viewster.com/'),
video_id, headers=self.geo_verification_headers())
cookies = self._get_cookies('http://www.viewster.com/')
self._AUTH_TOKEN = compat_urllib_parse_unquote(cookies['api_token'].value)
2015-03-13 21:18:04 +00:00
info = self._download_json(
'https://public-api.viewster.com/search/%s' % video_id,
video_id, 'Downloading entry JSON')
2015-03-13 21:18:04 +00:00
entry_id = info.get('Id') or info['id']
2015-03-13 21:18:04 +00:00
# unfinished serie has no Type
2015-09-22 16:00:50 +00:00
if info.get('Type') in ('Serie', None):
try:
episodes = self._download_json(
'https://public-api.viewster.com/series/%s/episodes' % entry_id,
video_id, 'Downloading series JSON')
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
self.raise_geo_restricted()
else:
raise
entries = [
self.url_result(
'http://www.viewster.com/movie/%s' % episode['OriginId'], 'Viewster')
for episode in episodes]
2015-07-21 20:08:25 +00:00
title = (info.get('Title') or info['Synopsis']['Title']).strip()
description = info.get('Synopsis', {}).get('Detailed')
return self.playlist_result(entries, video_id, title, description)
2015-03-13 21:18:04 +00:00
formats = []
for language_set in info.get('LanguageSets', []):
manifest_url = None
m3u8_formats = []
audio = language_set.get('Audio') or ''
subtitle = language_set.get('Subtitle') or ''
base_format_id = audio
if subtitle:
base_format_id += '-%s' % subtitle
def concat(suffix, sep='-'):
return (base_format_id + '%s%s' % (sep, suffix)) if base_format_id else suffix
2018-10-26 04:40:49 +00:00
medias = self._download_json(
'https://public-api.viewster.com/movies/%s/videos' % entry_id,
video_id, fatal=False, query={
'mediaTypes': ['application/f4m+xml', 'application/x-mpegURL', 'video/mp4'],
'language': audio,
'subtitle': subtitle,
})
if not medias:
continue
for media in medias:
video_url = media.get('Uri')
if not video_url:
continue
ext = determine_ext(video_url)
if ext == 'f4m':
manifest_url = video_url
video_url += '&' if '?' in video_url else '?'
video_url += 'hdcore=3.2.0&plugin=flowplayer-3.2.0.1'
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id=concat('hds')))
elif ext == 'm3u8':
manifest_url = video_url
m3u8_formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id=concat('hls'),
fatal=False) # m3u8 sometimes fail
if m3u8_formats:
formats.extend(m3u8_formats)
else:
qualities_basename = self._search_regex(
r'/([^/]+)\.csmil/',
manifest_url, 'qualities basename', default=None)
if not qualities_basename:
continue
QUALITIES_RE = r'((,\d+k)+,?)'
qualities = self._search_regex(
QUALITIES_RE, qualities_basename,
'qualities', default=None)
if not qualities:
continue
qualities = list(map(lambda q: int(q[:-1]), qualities.strip(',').split(',')))
qualities.sort()
http_template = re.sub(QUALITIES_RE, r'%dk', qualities_basename)
http_url_basename = url_basename(video_url)
if m3u8_formats:
self._sort_formats(m3u8_formats)
m3u8_formats = list(filter(
lambda f: f.get('vcodec') != 'none', m3u8_formats))
if len(qualities) == len(m3u8_formats):
for q, m3u8_format in zip(qualities, m3u8_formats):
f = m3u8_format.copy()
f.update({
'url': video_url.replace(http_url_basename, http_template % q),
'format_id': f['format_id'].replace('hls', 'http'),
'protocol': 'http',
})
formats.append(f)
else:
for q in qualities:
formats.append({
'url': video_url.replace(http_url_basename, http_template % q),
'ext': 'mp4',
'format_id': 'http-%d' % q,
'tbr': q,
})
if not formats and not info.get('VODSettings'):
self.raise_geo_restricted()
self._sort_formats(formats)
2015-03-13 21:18:04 +00:00
synopsis = info.get('Synopsis') or {}
# Prefer title outside synopsis since it's less messy
2015-07-21 20:08:25 +00:00
title = (info.get('Title') or synopsis['Title']).strip()
description = synopsis.get('Detailed') or (info.get('Synopsis') or {}).get('Short')
duration = int_or_none(info.get('Duration'))
timestamp = parse_iso8601(info.get('ReleaseDate'))
return {
'id': video_id,
'title': title,
'description': description,
'timestamp': timestamp,
'duration': duration,
'formats': formats,
}