1
mirror of https://github.com/yt-dlp/yt-dlp synced 2024-12-24 10:33:45 +01:00
yt-dlp/youtube_dl/extractor/nfb.py
Sergey M? 5c2266df4b 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
2015-11-23 21:56:23 +06:00

94 lines
3.7 KiB
Python

from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import compat_urllib_parse
from ..utils import sanitized_Request
class NFBIE(InfoExtractor):
IE_NAME = 'nfb'
IE_DESC = 'National Film Board of Canada'
_VALID_URL = r'https?://(?:www\.)?(?:nfb|onf)\.ca/film/(?P<id>[\da-z_-]+)'
_TEST = {
'url': 'https://www.nfb.ca/film/qallunaat_why_white_people_are_funny',
'info_dict': {
'id': 'qallunaat_why_white_people_are_funny',
'ext': 'mp4',
'title': 'Qallunaat! Why White People Are Funny ',
'description': 'md5:836d8aff55e087d04d9f6df554d4e038',
'duration': 3128,
'uploader': 'Mark Sandiford',
'uploader_id': 'mark-sandiford',
},
'params': {
# rtmp download
'skip_download': True,
}
}
def _real_extract(self, url):
video_id = self._match_id(url)
page = self._download_webpage(
'https://www.nfb.ca/film/%s' % video_id, video_id,
'Downloading film page')
uploader_id = self._html_search_regex(r'<a class="director-link" href="/explore-all-directors/([^/]+)/"',
page, 'director id', fatal=False)
uploader = self._html_search_regex(r'<em class="director-name" itemprop="name">([^<]+)</em>',
page, 'director name', fatal=False)
request = sanitized_Request(
'https://www.nfb.ca/film/%s/player_config' % video_id,
compat_urllib_parse.urlencode({'getConfig': 'true'}).encode('ascii'))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
request.add_header('X-NFB-Referer', 'http://www.nfb.ca/medias/flash/NFBVideoPlayer.swf')
config = self._download_xml(request, video_id, 'Downloading player config XML')
title = None
description = None
thumbnail = None
duration = None
formats = []
def extract_thumbnail(media):
thumbnails = {}
for asset in media.findall('assets/asset'):
thumbnails[asset.get('quality')] = asset.find('default/url').text
if not thumbnails:
return None
if 'high' in thumbnails:
return thumbnails['high']
return list(thumbnails.values())[0]
for media in config.findall('./player/stream/media'):
if media.get('type') == 'posterImage':
thumbnail = extract_thumbnail(media)
elif media.get('type') == 'video':
duration = int(media.get('duration'))
title = media.find('title').text
description = media.find('description').text
# It seems assets always go from lower to better quality, so no need to sort
for asset in media.findall('assets/asset'):
for x in asset:
formats.append({
'url': x.find('streamerURI').text,
'app': x.find('streamerURI').text.split('/', 3)[3],
'play_path': x.find('url').text,
'rtmp_live': False,
'ext': 'mp4',
'format_id': '%s-%s' % (x.tag, asset.get('quality')),
})
return {
'id': video_id,
'title': title,
'description': description,
'thumbnail': thumbnail,
'duration': duration,
'uploader': uploader,
'uploader_id': uploader_id,
'formats': formats,
}