From 86be3cdc2a623a522500ca073835579b853a1ae1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Tue, 16 Feb 2016 22:05:23 +0600 Subject: [PATCH] [xtube] Fix extraction (Closes #8565) --- youtube_dl/extractor/xtube.py | 94 +++++++++++++++++------------------ 1 file changed, 46 insertions(+), 48 deletions(-) diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 8cd3a0687..24df5c48e 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -7,15 +7,16 @@ from .common import InfoExtractor from ..compat import compat_urllib_parse_unquote from ..utils import ( int_or_none, - parse_duration, sanitized_Request, str_to_int, ) class XTubeIE(InfoExtractor): - _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/watch\.php\?.*\bv=)(?P[^/?&#]+)' - _TEST = { + _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P[^/]+)-))(?P[^/?&#]+)' + + _TESTS = [{ + # old URL schema 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', 'info_dict': { @@ -27,63 +28,60 @@ class XTubeIE(InfoExtractor): 'duration': 450, 'age_limit': 18, } - } + }, { + # new URL schema + 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837', + 'only_matching': True, + }, { + 'url': 'xtube:625837', + 'only_matching': True, + }] def _real_extract(self, url): - video_id = self._match_id(url) - - req = sanitized_Request('http://www.xtube.com/watch.php?v=%s' % video_id) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) - - video_title = self._html_search_regex( - r'

([^<]+)', webpage, 'title') - video_uploader = self._html_search_regex( - [r"var\s+contentOwnerId\s*=\s*'([^']+)", - r'By:\s*([^<]+)', webpage, 'title') + video_url = compat_urllib_parse_unquote(flashvars['video_url']) + duration = int_or_none(flashvars.get('video_duration')) + + uploader = self._search_regex( + r']+name="contentOwnerId"[^>]+value="([^"]+)"', webpage, 'uploader', fatal=False) - video_description = self._html_search_regex( - r'

([^<]+)', - webpage, 'description', fatal=False) - duration = parse_duration(self._html_search_regex( - r'Runtime: ([^<]+)

', - webpage, 'duration', fatal=False)) - view_count = str_to_int(self._html_search_regex( - r'Views: ([\d,\.]+)

', + description = self._search_regex( + r'\s*

([^<]+)', webpage, 'description', fatal=False) + view_count = str_to_int(self._search_regex( + r'

Views:
\s*
([\d,\.]+)
', webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( - r'
([\d,\.]+) Comments
', + r'>Comments? \(([\d,\.]+)\)<', webpage, 'comment count', fatal=False)) - formats = [] - for format_id, video_url in re.findall( - r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage): - fmt = { - 'url': compat_urllib_parse_unquote(video_url), - 'format_id': format_id, - } - m = re.search(r'^(?P\d+)[pP]', format_id) - if m: - fmt['height'] = int(m.group('height')) - formats.append(fmt) - - if not formats: - video_url = compat_urllib_parse_unquote(self._search_regex( - r'flashvars\.video_url\s*=\s*"([^"]+)"', - webpage, 'video URL')) - formats.append({'url': video_url}) - - self._sort_formats(formats) - return { 'id': video_id, - 'title': video_title, - 'uploader': video_uploader, - 'description': video_description, + 'display_id': display_id, + 'url': video_url, + 'title': title, + 'description': description, + 'uploader': uploader, 'duration': duration, 'view_count': view_count, 'comment_count': comment_count, - 'formats': formats, 'age_limit': 18, }