From: Sergey M․ Date: Tue, 4 Mar 2014 09:12:11 +0000 (+0700) Subject: [xtube] Fix extraction add more metafields X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=607dbbad762aef41925229ee8bd53844413b9440;p=youtube-dl [xtube] Fix extraction add more metafields --- diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 982619922..d3eefd086 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -7,19 +7,24 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse_urlparse, compat_urllib_request, + parse_duration, + str_to_int, ) + class XTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pxtube\.com/watch\.php\?v=(?P[^/?&]+))' + _VALID_URL = r'https?://(?:www\.)?(?Pxtube\.com/watch\.php\?v=(?P[^/?&]+))' _TEST = { 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', - 'file': 'kVTUy_G222_.mp4', 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', 'info_dict': { - "title": "strange erotica", - "description": "surreal gay themed erotica...almost an ET kind of thing", - "uploader": "greenshowers", - "age_limit": 18, + 'id': 'kVTUy_G222_', + 'ext': 'mp4', + 'title': 'strange erotica', + 'description': 'surreal gay themed erotica...almost an ET kind of thing', + 'uploader': 'greenshowers', + 'duration': 450, + 'age_limit': 18, } } @@ -32,10 +37,23 @@ class XTubeIE(InfoExtractor): req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'
([^<]+)', webpage, 'description', fatal=False) - video_url= self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, 'video_url').replace('\\/', '/') + video_title = self._html_search_regex(r'

([^<]+)', webpage, 'title') + video_uploader = self._html_search_regex( + r'so_s\.addVariable\("owner_u", "([^"]+)', webpage, 'uploader', fatal=False) + video_description = self._html_search_regex( + r'

([^<]+)', webpage, 'description', fatal=False) + video_url = self._html_search_regex(r'var videoMp4 = "([^"]+)', webpage, 'video_url').replace('\\/', '/') + duration = parse_duration(self._html_search_regex( + r'Runtime: ([^<]+)

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

', webpage, 'view count', fatal=False) + if view_count: + view_count = str_to_int(view_count) + comment_count = self._html_search_regex( + r'
([\d,\.]+) Comments
', webpage, 'comment count', fatal=False) + if comment_count: + comment_count = str_to_int(comment_count) + path = compat_urllib_parse_urlparse(video_url).path extension = os.path.splitext(path)[1][1:] format = path.split('/')[5].split('_')[:2] @@ -48,6 +66,9 @@ class XTubeIE(InfoExtractor): 'title': video_title, 'uploader': video_uploader, 'description': video_description, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, 'url': video_url, 'ext': extension, 'format': format,