R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[trilulilu] extract info from webpage

Browse Source
This commit is contained in:
remitamine 2015-12-05 08:51:08 +01:00
parent bee4c5571a
commit 23b1009d19
1 changed files with 35 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
youtube_dl/extractor/trilulilu.py
View File

@ -1,11 +1,14 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
js_to_json,
parse_duration,
)
@ -22,10 +25,6 @@ class TriluliluIE(InfoExtractor):
'uploader_id': 'chipy',
'upload_date': '20120304',
'timestamp': 1330830647,
'uploader': 'chipy',
'view_count': int,
'like_count': int,
'comment_count': int,
},
}, {
'url': 'http://www.trilulilu.ro/adena-ft-morreti-inocenta',
@ -37,57 +36,59 @@ class TriluliluIE(InfoExtractor):
'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)
media_info = self._download_json('http://m.trilulilu.ro/%s?format=json' % display_id, display_id)
webpage = self._download_webpage(url, display_id)
media_class = media_info.get('class')
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)
uploader_id, media_id = self._search_regex(
r'<input type="hidden" id="identifier" value="([^"]+)"',
webpage, 'identifier').split('|')
media_class = player_vars.get('fileClass')
if media_class not in ('video', 'audio'):
raise ExtractorError('not a video or an audio')
user = media_info.get('user', {})
thumbnail = media_info.get('cover_url')
if thumbnail:
thumbnail.format(width='1600', height='1200')
# TODO: get correct ext for audio files
stream_type = media_info.get('stream_type')
formats = [{
'url': media_info['href'],
'ext': stream_type,
'url': player_vars['file'],
'ext': player_vars.get('streamType'),
}]
if media_info.get('is_hd'):
hd_url = player_vars.get('fileUrlHD')
if hd_url:
formats.append({
'format_id': 'hd',
'url': media_info['hrefhd'],
'ext': stream_type,
'url': hd_url,
'ext': player_vars.get('fileTypeHD'),
})
if media_class == 'audio':
formats[0]['vcodec'] = 'none'
else:
formats[0]['format_id'] = 'sd'
return {
'id': media_info['identifier'].split('|')[1],
'id': media_id,
'display_id': display_id,
'formats': formats,
'title': media_info['title'],
'description': media_info.get('description'),
'thumbnail': thumbnail,
'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')),
'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)),
}