95 lines
3.2 KiB
Python
Raw Normal View History

# coding: utf-8
2014-11-26 12:56:28 +01:00
from __future__ import unicode_literals
2015-12-05 08:51:08 +01:00
import re
from .common import InfoExtractor
2015-12-04 00:51:02 +01:00
from ..utils import (
ExtractorError,
parse_iso8601,
2015-12-05 08:51:08 +01:00
js_to_json,
parse_duration,
2015-12-04 00:51:02 +01:00
)
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,
},
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',
'timestamp': 1449187937,
},
}]
def _real_extract(self, url):
display_id = self._match_id(url)
2015-12-05 08:51:08 +01:00
webpage = self._download_webpage(url, display_id)
2015-12-04 06:53:33 +01:00
2015-12-05 08:51:08 +01:00
if re.search(r'Fişierul nu este disponibil pentru vizionare în ţara dumneavoastră', webpage):
raise ExtractorError(
'This video is not available in your country.', expected=True)
elif re.search('Fişierul poate fi accesat doar de către prietenii lui', webpage):
raise ExtractorError('This video is private.', expected=True)
player_vars = self._parse_json(
self._search_regex(r'(?s)playerVars\s*=\s*({.+?});', webpage, 'player vars'),
display_id, js_to_json)
2015-12-04 06:53:33 +01:00
2015-12-05 08:51:08 +01:00
uploader_id, media_id = self._search_regex(
r'<input type="hidden" id="identifier" value="([^"]+)"',
webpage, 'identifier').split('|')
2015-12-05 08:51:08 +01:00
media_class = player_vars.get('fileClass')
if media_class not in ('video', 'audio'):
raise ExtractorError('not a video or an audio')
2015-12-04 06:53:33 +01:00
# TODO: get correct ext for audio files
formats = [{
2015-12-05 08:51:08 +01:00
'url': player_vars['file'],
'ext': player_vars.get('streamType'),
2015-12-04 06:53:33 +01:00
}]
2015-12-05 08:51:08 +01:00
hd_url = player_vars.get('fileUrlHD')
if hd_url:
2015-12-04 06:53:33 +01:00
formats.append({
'format_id': 'hd',
2015-12-05 08:51:08 +01:00
'url': hd_url,
'ext': player_vars.get('fileTypeHD'),
2015-12-04 06:53:33 +01:00
})
2015-12-05 08:51:08 +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 {
2015-12-05 08:51:08 +01:00
'id': media_id,
'display_id': display_id,
'formats': formats,
2015-12-05 08:51:08 +01:00
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': player_vars.get('image'),
'uploader_id': uploader_id,
'timestamp': parse_iso8601(self._html_search_meta('uploadDate', webpage), ' '),
'duration': parse_duration(self._html_search_meta('duration', webpage)),
}