yt-dlp/youtube_dl/extractor/viddler.py

147 lines
5.1 KiB
Python
Raw Normal View History

2014-10-25 00:10:11 +02:00
from __future__ import unicode_literals
from .common import InfoExtractor
from ..compat import (
compat_urllib_parse,
compat_urlparse,
)
2014-10-25 00:10:11 +02:00
from ..utils import (
float_or_none,
int_or_none,
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 17:18:17 +01:00
sanitized_Request,
)
class ViddlerIE(InfoExtractor):
2014-10-25 00:10:11 +02:00
_VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)'
_TESTS = [{
2015-01-28 17:49:42 +01:00
'url': 'http://www.viddler.com/v/43903784',
2016-02-09 20:12:47 +01:00
'md5': '9eee21161d2c7f5b39690c3e325fab2f',
2014-10-25 00:10:11 +02:00
'info_dict': {
'id': '43903784',
2016-02-09 20:12:47 +01:00
'ext': 'mov',
2015-01-28 17:49:42 +01:00
'title': 'Video Made Easy',
'description': 'md5:6a697ebd844ff3093bd2e82c37b409cd',
'uploader': 'viddler',
2014-10-25 00:10:11 +02:00
'timestamp': 1335371429,
'upload_date': '20120425',
2015-01-28 17:49:42 +01:00
'duration': 100.89,
2014-10-25 00:10:11 +02:00
'thumbnail': 're:^https?://.*\.jpg$',
'view_count': int,
2015-01-28 18:21:17 +01:00
'comment_count': int,
2014-10-25 00:10:11 +02:00
'categories': ['video content', 'high quality video', 'video made easy', 'how to produce video with limited resources', 'viddler'],
}
}, {
2015-01-28 17:49:42 +01:00
'url': 'http://www.viddler.com/v/4d03aad9/',
2016-02-09 20:12:47 +01:00
'md5': 'f12c5a7fa839c47a79363bfdf69404fb',
2015-01-28 17:49:42 +01:00
'info_dict': {
'id': '4d03aad9',
2016-02-09 20:12:47 +01:00
'ext': 'ts',
2015-01-28 17:49:42 +01:00
'title': 'WALL-TO-GORTAT',
'upload_date': '20150126',
'uploader': 'deadspin',
'timestamp': 1422285291,
2015-01-28 18:21:17 +01:00
'view_count': int,
'comment_count': int,
}
}, {
2015-01-28 17:49:42 +01:00
'url': 'http://www.viddler.com/player/221ebbbd/0/',
2016-02-09 20:12:47 +01:00
'md5': '740511f61d3d1bb71dc14a0fe01a1c10',
2015-01-28 17:49:42 +01:00
'info_dict': {
'id': '221ebbbd',
2016-02-09 20:12:47 +01:00
'ext': 'mov',
2015-01-28 17:49:42 +01:00
'title': 'LETeens-Grammar-snack-third-conditional',
'description': ' ',
'upload_date': '20140929',
'uploader': 'BCLETeens',
'timestamp': 1411997190,
2015-01-28 18:21:17 +01:00
'view_count': int,
'comment_count': int,
}
}, {
# secret protected
'url': 'http://www.viddler.com/v/890c0985?secret=34051570',
'info_dict': {
'id': '890c0985',
'ext': 'mp4',
'title': 'Complete Property Training - Traineeships',
'description': ' ',
'upload_date': '20130606',
'uploader': 'TiffanyBowtell',
'timestamp': 1370496993,
'view_count': int,
'comment_count': int,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url):
2014-10-25 00:10:11 +02:00
video_id = self._match_id(url)
query = {
'video_id': video_id,
'key': 'v0vhrt7bg2xq1vyxhkct',
}
qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
secret = qs.get('secret', [None])[0]
if secret:
query['secret'] = secret
headers = {'Referer': 'http://static.cdn-ec.viddler.com/js/arpeggio/v2/embed.html'}
request = sanitized_Request(
'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json?%s'
% compat_urllib_parse.urlencode(query), None, headers)
data = self._download_json(request, video_id)['video']
2014-10-25 00:10:11 +02:00
formats = []
for filed in data['files']:
if filed.get('status', 'ready') != 'ready':
continue
2015-01-28 18:21:17 +01:00
format_id = filed.get('profile_id') or filed['profile_name']
2014-10-25 00:10:11 +02:00
f = {
2015-01-28 18:21:17 +01:00
'format_id': format_id,
2014-10-25 00:10:11 +02:00
'format_note': filed['profile_name'],
'url': self._proto_relative_url(filed['url']),
'width': int_or_none(filed.get('width')),
'height': int_or_none(filed.get('height')),
'filesize': int_or_none(filed.get('size')),
'ext': filed.get('ext'),
'source_preference': -1,
}
formats.append(f)
if filed.get('cdn_url'):
f = f.copy()
f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
2015-01-28 18:21:17 +01:00
f['format_id'] = format_id + '-cdn'
2014-10-25 00:10:11 +02:00
f['source_preference'] = 1
formats.append(f)
if filed.get('html5_video_source'):
f = f.copy()
2015-01-28 17:49:42 +01:00
f['url'] = self._proto_relative_url(filed['html5_video_source'])
2015-01-28 18:21:17 +01:00
f['format_id'] = format_id + '-html5'
2014-10-25 00:10:11 +02:00
f['source_preference'] = 0
formats.append(f)
self._sort_formats(formats)
categories = [
t.get('text') for t in data.get('tags', []) if 'text' in t]
return {
'id': video_id,
2014-10-25 00:10:11 +02:00
'title': data['title'],
'formats': formats,
2014-10-25 00:10:11 +02:00
'description': data.get('description'),
'timestamp': int_or_none(data.get('upload_time')),
'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
'uploader': data.get('author'),
'duration': float_or_none(data.get('length')),
'view_count': int_or_none(data.get('view_count')),
2015-01-28 18:21:17 +01:00
'comment_count': int_or_none(data.get('comment_count')),
2014-10-25 00:10:11 +02:00
'categories': categories,
}