yt-dlp/youtube_dl/extractor/viki.py

122 lines
4.1 KiB
Python
Raw Normal View History

2014-03-21 00:53:18 +01:00
from __future__ import unicode_literals
2013-11-24 07:30:05 +01:00
import re
from ..compat import (
compat_urlparse,
compat_urllib_request,
)
2013-11-24 07:30:05 +01:00
from ..utils import (
ExtractorError,
2013-11-25 06:06:18 +01:00
unescapeHTML,
2013-11-24 07:30:05 +01:00
unified_strdate,
2014-03-21 00:59:51 +01:00
US_RATINGS,
clean_html,
2013-11-24 07:30:05 +01:00
)
2015-02-18 20:37:16 +01:00
from .common import InfoExtractor
2013-11-24 07:30:05 +01:00
2015-02-18 20:37:16 +01:00
class VikiIE(InfoExtractor):
2014-03-21 00:53:18 +01:00
IE_NAME = 'viki'
2013-11-24 07:30:05 +01:00
# iPad2
_USER_AGENT = 'Mozilla/5.0(iPad; U; CPU OS 4_3 like Mac OS X; en-us) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8F191 Safari/6533.18.5'
2013-11-24 07:30:05 +01:00
_VALID_URL = r'^https?://(?:www\.)?viki\.com/videos/(?P<id>[0-9]+v)'
_TESTS = [{
2014-03-21 00:53:18 +01:00
'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
'info_dict': {
'id': '1023585v',
'ext': 'mp4',
'title': 'Heirs Episode 14',
'uploader': 'SBS',
'description': 'md5:c4b17b9626dd4b143dcc4d855ba3474e',
'upload_date': '20131121',
'age_limit': 13,
},
2014-03-21 00:53:18 +01:00
'skip': 'Blocked in the US',
}, {
'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
'md5': 'ca6493e6f0a6ec07da9aa8d6304b4b2c',
'info_dict': {
'id': '1067139v',
'ext': 'mp4',
'description': 'md5:d70b2f9428f5488321bfe1db10d612ea',
'upload_date': '20150430',
'title': '\'The Avengers: Age of Ultron\' Press Conference',
}
}]
2013-11-24 07:30:05 +01:00
def _real_extract(self, url):
2015-01-07 07:21:24 +01:00
video_id = self._match_id(url)
2013-11-24 07:30:05 +01:00
webpage = self._download_webpage(url, video_id)
title = self._og_search_title(webpage)
description = self._og_search_description(webpage)
thumbnail = self._og_search_thumbnail(webpage)
uploader_m = re.search(
r'<strong>Broadcast Network: </strong>\s*([^<]*)<', webpage)
if uploader_m is None:
uploader = None
else:
2013-11-25 05:57:55 +01:00
uploader = uploader_m.group(1).strip()
2013-11-24 07:30:05 +01:00
rating_str = self._html_search_regex(
r'<strong>Rating: </strong>\s*([^<]*)<', webpage,
2014-03-21 00:53:18 +01:00
'rating information', default='').strip()
2014-03-21 00:59:51 +01:00
age_limit = US_RATINGS.get(rating_str)
2013-11-24 07:30:05 +01:00
req = compat_urllib_request.Request(
'http://www.viki.com/player5_fragment/%s?action=show&controller=videos' % video_id)
req.add_header('User-Agent', self._USER_AGENT)
2013-11-24 15:20:16 +01:00
info_webpage = self._download_webpage(
req, video_id, note='Downloading info page')
err_msg = self._html_search_regex(r'<div[^>]+class="video-error[^>]+>(.+)</div>', info_webpage, 'error message', default=None)
if err_msg:
err_msg = clean_html(err_msg)
if 'not available in your region' in err_msg:
raise ExtractorError(
'Video %s is blocked from your location.' % video_id,
expected=True)
else:
raise ExtractorError('Viki said: ' + err_msg)
2013-11-24 07:30:05 +01:00
video_url = self._html_search_regex(
2014-03-21 00:53:18 +01:00
r'<source[^>]+src="([^"]+)"', info_webpage, 'video URL')
2013-11-24 07:30:05 +01:00
upload_date_str = self._html_search_regex(
2014-03-21 00:53:18 +01:00
r'"created_at":"([^"]+)"', info_webpage, 'upload date')
2013-11-24 07:30:05 +01:00
upload_date = (
unified_strdate(upload_date_str)
if upload_date_str is not None
else None
)
# subtitles
video_subtitles = self.extract_subtitles(video_id, info_webpage)
return {
'id': video_id,
'title': title,
'url': video_url,
'description': description,
'thumbnail': thumbnail,
'age_limit': age_limit,
'uploader': uploader,
'subtitles': video_subtitles,
'upload_date': upload_date,
}
2015-02-18 20:37:16 +01:00
def _get_subtitles(self, video_id, info_webpage):
2013-11-24 07:30:05 +01:00
res = {}
2015-02-18 20:37:16 +01:00
for sturl_html in re.findall(r'<track src="([^"]+)"', info_webpage):
2013-11-25 06:06:18 +01:00
sturl = unescapeHTML(sturl_html)
2013-11-24 07:30:05 +01:00
m = re.search(r'/(?P<lang>[a-z]+)\.vtt', sturl)
if not m:
continue
2015-02-18 20:37:16 +01:00
res[m.group('lang')] = [{
'url': compat_urlparse.urljoin('http://www.viki.com', sturl),
'ext': 'vtt',
}]
2013-11-24 07:30:05 +01:00
return res