X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fextremetube.py;h=36ba331285b434136b8d3c10e6a8a16bef18e7b7;hb=c2a30b250cdea5a8c73225e6a14707a669640de0;hp=ff7c0cd3e6595740f1c98b834f1d2b818d04d25c;hpb=117a7d194432788435d9a2e697378c8bfc9a640d;p=youtube-dl diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index ff7c0cd3e..36ba33128 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -3,15 +3,18 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( +from ..compat import ( compat_urllib_parse_urlparse, compat_urllib_request, compat_urllib_parse, ) +from ..utils import ( + str_to_int, +) class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pextremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?(?Pextremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', @@ -20,6 +23,7 @@ class ExtremeTubeIE(InfoExtractor): 'ext': 'mp4', 'title': 'Music Video 14 british euro brit european cumshots swallow', 'uploader': 'unknown', + 'view_count': int, 'age_limit': 18, } }, { @@ -29,7 +33,7 @@ class ExtremeTubeIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('videoid') + video_id = mobj.group('id') url = 'http://www.' + mobj.group('url') req = compat_urllib_request.Request(url) @@ -37,10 +41,14 @@ class ExtremeTubeIE(InfoExtractor): webpage = self._download_webpage(req, video_id) video_title = self._html_search_regex( - r'

]*?title="([^"]+)"[^>]*>\1<', webpage, 'title') + r'

]*?title="([^"]+)"[^>]*>', webpage, 'title') uploader = self._html_search_regex( - r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, 'uploader', - fatal=False) + r'Uploaded by:\s*\s*(.+?)\s*', + webpage, 'uploader', fatal=False) + view_count = str_to_int(self._html_search_regex( + r'Views:\s*\s*([\d,\.]+)', + webpage, 'view count', fatal=False)) + video_url = compat_urllib_parse.unquote(self._html_search_regex( r'video_url=(.+?)&', webpage, 'video_url')) path = compat_urllib_parse_urlparse(video_url).path @@ -51,6 +59,7 @@ class ExtremeTubeIE(InfoExtractor): 'id': video_id, 'title': video_title, 'uploader': uploader, + 'view_count': view_count, 'url': video_url, 'format': format, 'format_id': format,