[xtube] fix extractor (#17)

This commit is contained in:
insaneracist 2020-10-28 13:48:55 -07:00
parent ddb77f30ee
commit 576d233fe6

View File

@ -5,6 +5,7 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
ExtractorError,
int_or_none, int_or_none,
js_to_json, js_to_json,
orderedSet, orderedSet,
@ -33,27 +34,11 @@ class XTubeIE(InfoExtractor):
'title': 'strange erotica', 'title': 'strange erotica',
'description': 'contains:an ET kind of thing', 'description': 'contains:an ET kind of thing',
'uploader': 'greenshowers', 'uploader': 'greenshowers',
'duration': 450, 'duration': 449,
'view_count': int, 'view_count': int,
'comment_count': int, 'comment_count': int,
'age_limit': 18, 'age_limit': 18,
} }
}, {
# FLV videos with duplicated formats
'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752',
'md5': 'a406963eb349dd43692ec54631efd88b',
'info_dict': {
'id': '9299752',
'display_id': 'A-Super-Run-Part-1-YT',
'ext': 'flv',
'title': 'A Super Run - Part 1 (YT)',
'description': 'md5:4cc3af1aa1b0413289babc88f0d4f616',
'uploader': 'tshirtguy59',
'duration': 579,
'view_count': int,
'comment_count': int,
'age_limit': 18,
},
}, { }, {
# new URL schema # new URL schema
'url': 'http://www.xtube.com/video-watch/strange-erotica-625837', 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837',
@ -89,10 +74,18 @@ def _real_extract(self, url):
title, thumbnail, duration = [None] * 3 title, thumbnail, duration = [None] * 3
config = self._parse_json(self._search_regex( json_config_string = self._search_regex(
r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', r'playerConf=({.+?}),loaderConf',
default='{}'), video_id, transform_source=js_to_json, fatal=False) webpage, 'config', default=None)
if config: if not json_config_string:
raise ExtractorError("Could not extract video player data")
json_config_string = json_config_string.replace("!0", "true").replace("!1", "false")
config = self._parse_json(json_config_string, video_id, transform_source=js_to_json, fatal=False)
if not config:
raise ExtractorError("Could not extract video player data")
config = config.get('mainRoll') config = config.get('mainRoll')
if isinstance(config, dict): if isinstance(config, dict):
title = config.get('title') title = config.get('title')