ytdl/youtube_dl/extractor/trilulilu.py

104 lines
3.5 KiB
Python
Raw Normal View History

# coding: utf-8
2014-11-26 12:56:28 +01:00
from __future__ import unicode_literals
from .common import InfoExtractor
2015-12-04 00:51:02 +01:00
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
)
class TriluliluIE(InfoExtractor):
2015-12-04 00:51:02 +01:00
_VALID_URL = r'https?://(?:(?:www|m)\.)?trilulilu\.ro/(?:[^/]+/)?(?P<id>[^/#\?]+)'
_TESTS = [{
'url': 'http://www.trilulilu.ro/big-buck-bunny-1',
'md5': '68da087b676a6196a413549212f60cc6',
2014-11-26 12:56:28 +01:00
'info_dict': {
'id': 'ae2899e124140b',
2014-11-26 12:56:28 +01:00
'ext': 'mp4',
'title': 'Big Buck Bunny',
'description': ':) pentru copilul din noi',
2015-12-04 00:51:02 +01:00
'uploader_id': 'chipy',
'upload_date': '20120304',
'timestamp': 1330830647,
'uploader': 'chipy',
'view_count': int,
'like_count': int,
'comment_count': int,
},
2015-12-04 00:51:02 +01:00
}, {
'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta',
'md5': '929dfb8729dc71750463af88bbbbf4a4',
'info_dict': {
'id': 'f299710e3c91c5',
'ext': 'mp4',
'title': 'Adena ft. Morreti - Inocenta',
'description': 'pop music',
'uploader_id': 'VEVOmixt',
'upload_date': '20151204',
'uploader': 'VEVOmixt',
'timestamp': 1449187937,
'view_count': int,
'like_count': int,
'comment_count': int,
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
2015-12-04 00:51:02 +01:00
media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id)
2015-12-04 06:53:33 +01:00
2015-12-05 09:29:14 +01:00
age_limit = 0
errors = media_info.get('errors', {})
if errors.get('friends'):
raise ExtractorError('This video is private.', expected=True)
elif errors.get('geoblock'):
raise ExtractorError('This video is not available in your country.', expected=True)
elif errors.get('xxx_unlogged'):
age_limit = 18
2015-12-04 06:53:33 +01:00
media_class = media_info.get('class')
if media_class not in ('video', 'audio'):
raise ExtractorError('not a video or an audio')
2015-12-04 00:51:02 +01:00
user = media_info.get('user', {})
2015-12-04 00:51:02 +01:00
thumbnail = media_info.get('cover_url')
if thumbnail:
thumbnail.format(width='1600', height='1200')
2015-12-04 06:53:33 +01:00
# TODO: get correct ext for audio files
stream_type = media_info.get('stream_type')
formats = [{
'url': media_info['href'],
'ext': stream_type,
}]
if media_info.get('is_hd'):
formats.append({
'format_id': 'hd',
'url': media_info['hrefhd'],
2015-12-04 00:51:02 +01:00
'ext': stream_type,
2015-12-04 06:53:33 +01:00
})
2015-12-04 00:51:02 +01:00
if media_class == 'audio':
formats[0]['vcodec'] = 'none'
2015-12-04 06:53:33 +01:00
else:
formats[0]['format_id'] = 'sd'
return {
2015-12-04 00:51:02 +01:00
'id': media_info['identifier'].split('|')[1],
'display_id': display_id,
'formats': formats,
2015-12-04 00:51:02 +01:00
'title': media_info['title'],
'description': media_info.get('description'),
'thumbnail': thumbnail,
2015-12-04 00:51:02 +01:00
'uploader_id': user.get('username'),
'uploader': user.get('fullname'),
'timestamp': parse_iso8601(media_info.get('published'), ' '),
'duration': int_or_none(media_info.get('duration')),
'view_count': int_or_none(media_info.get('count_views')),
'like_count': int_or_none(media_info.get('count_likes')),
'comment_count': int_or_none(media_info.get('count_comments')),
2015-12-05 09:29:14 +01:00
'age_limit': age_limit,
}