youtube-dl/youtube_dl/extractor/veoh.py

128 lines
4.7 KiB
Python
Raw Normal View History

2014-01-05 13:48:12 +09:00
from __future__ import unicode_literals
2013-07-09 05:02:23 +09:00
import re
import json
from .common import InfoExtractor
from ..utils import (
int_or_none,
2014-06-09 01:05:20 +09:00
ExtractorError,
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
2015-11-22 01:18:17 +09:00
sanitized_Request,
)
2014-01-05 13:48:12 +09:00
2013-07-09 05:02:23 +09:00
class VeohIE(InfoExtractor):
2017-07-09 16:54:52 +09:00
_VALID_URL = r'https?://(?:www\.)?veoh\.com/(?:watch|iphone/#_Watch)/(?P<id>(?:v|e|yapi-)[\da-zA-Z]+)'
2017-07-09 16:54:52 +09:00
_TESTS = [{
'url': 'http://www.veoh.com/watch/v56314296nk7Zdmz3',
'md5': '620e68e6a3cff80086df3348426c9ca3',
'info_dict': {
'id': '56314296',
'ext': 'mp4',
'title': 'Straight Backs Are Stronger',
'uploader': 'LUMOback',
'description': 'At LUMOback, we believe straight backs are stronger. The LUMOback Posture & Movement Sensor: It gently vibrates when you slouch, inspiring improved posture and mobility. Use the app to track your data and improve your posture over time. ',
},
2017-07-09 16:54:52 +09:00
}, {
'url': 'http://www.veoh.com/watch/v27701988pbTc4wzN?h1=Chile+workers+cover+up+to+avoid+skin+damage',
'md5': '4a6ff84b87d536a6a71e6aa6c0ad07fa',
'info_dict': {
'id': '27701988',
'ext': 'mp4',
'title': 'Chile workers cover up to avoid skin damage',
'description': 'md5:2bd151625a60a32822873efc246ba20d',
'uploader': 'afp-news',
'duration': 123,
},
2017-07-09 16:54:52 +09:00
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/v69525809F6Nc4frX',
'md5': '4fde7b9e33577bab2f2f8f260e30e979',
'note': 'Embedded ooyala video',
'info_dict': {
'id': '69525809',
'ext': 'mp4',
'title': 'Doctors Alter Plan For Preteen\'s Weight Loss Surgery',
'description': 'md5:f5a11c51f8fb51d2315bca0937526891',
'uploader': 'newsy-videos',
},
2017-07-09 16:54:52 +09:00
'skip': 'This video has been deleted.',
}, {
'url': 'http://www.veoh.com/watch/e152215AJxZktGS',
'only_matching': True,
}]
def _extract_formats(self, source):
formats = []
link = source.get('aowPermalink')
if link:
formats.append({
'url': link,
'ext': 'mp4',
'format_id': 'aow',
})
link = source.get('fullPreviewHashLowPath')
if link:
formats.append({
'url': link,
'format_id': 'low',
})
link = source.get('fullPreviewHashHighPath')
if link:
formats.append({
'url': link,
'format_id': 'high',
})
return formats
def _extract_video(self, source):
return {
'id': source.get('videoId'),
'title': source.get('title'),
'description': source.get('description'),
'thumbnail': source.get('highResImage') or source.get('medResImage'),
'uploader': source.get('username'),
'duration': int_or_none(source.get('length')),
'view_count': int_or_none(source.get('views')),
'age_limit': 18 if source.get('isMature') == 'true' or source.get('isSexy') == 'true' else 0,
'formats': self._extract_formats(source),
2013-07-09 05:02:23 +09:00
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
if video_id.startswith('v'):
rsp = self._download_xml(
r'http://www.veoh.com/api/findByPermalink?permalink=%s' % video_id, video_id, 'Downloading video XML')
2014-06-09 01:05:20 +09:00
stat = rsp.get('stat')
if stat == 'ok':
return self._extract_video(rsp.find('./videoList/video'))
2014-06-09 01:05:20 +09:00
elif stat == 'fail':
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, rsp.find('./errorList/error').get('errorMessage')), expected=True)
2013-07-09 05:02:23 +09:00
webpage = self._download_webpage(url, video_id)
age_limit = 0
if 'class="adultwarning-container"' in webpage:
self.report_age_confirmation()
age_limit = 18
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
2015-11-22 01:18:17 +09:00
request = sanitized_Request(url)
request.add_header('Cookie', 'confirmedAdult=true')
webpage = self._download_webpage(request, video_id)
2013-07-09 05:02:23 +09:00
m_youtube = re.search(r'http://www\.youtube\.com/v/(.*?)(\&|"|\?)', webpage)
2013-07-09 05:02:23 +09:00
if m_youtube is not None:
youtube_id = m_youtube.group(1)
2014-01-05 13:48:12 +09:00
self.to_screen('%s: detected Youtube video.' % video_id)
2013-07-09 05:02:23 +09:00
return self.url_result(youtube_id, 'Youtube')
info = json.loads(
self._search_regex(r'videoDetailsJSON = \'({.*?})\';', webpage, 'info').replace('\\\'', '\''))
2014-01-05 13:48:12 +09:00
video = self._extract_video(info)
video['age_limit'] = age_limit
return video