X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/90cd207d52d77e075e62cc256cc39dceee05bbf3..0652569e481a8cf0995a00635ef62143fa779add:/youtube_dl/extractor/extremetube.py?ds=sidebyside diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index 1c20e43..c826a54 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -1,50 +1,75 @@ -import os +from __future__ import unicode_literals + import re from .common import InfoExtractor -from ..utils import ( - compat_urllib_parse_urlparse, +from ..compat import ( + compat_parse_qs, compat_urllib_request, - compat_urllib_parse, ) +from ..utils import ( + qualities, + str_to_int, +) + class ExtremeTubeIE(InfoExtractor): - _VALID_URL = r'^(?:https?://)?(?:www\.)?(?Pextremetube\.com/video/.+?(?P[0-9]+))(?:[/?&]|$)' - _TEST = { - u'url': u'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', - u'file': u'652431.mp4', - u'md5': u'1fb9228f5e3332ec8c057d6ac36f33e0', - u'info_dict': { - u"title": u"Music Video 14 british euro brit european cumshots swallow", - u"uploader": u"unknown", - u"age_limit": 18, + _VALID_URL = r'https?://(?:www\.)?(?Pextremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' + _TESTS = [{ + 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', + 'md5': '344d0c6d50e2f16b06e49ca011d8ac69', + 'info_dict': { + 'id': '652431', + 'ext': 'mp4', + 'title': 'Music Video 14 british euro brit european cumshots swallow', + 'uploader': 'unknown', + 'view_count': int, + 'age_limit': 18, } - } + }, { + 'url': 'http://www.extremetube.com/gay/video/abcde-1234', + 'only_matching': True, + }] 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) req.add_header('Cookie', 'age_verified=1') webpage = self._download_webpage(req, video_id) - video_title = self._html_search_regex(r'

]*?title="([^"]+)"[^>]*>\1<', webpage, u'title') - uploader = self._html_search_regex(r'>Posted by:(?=<)(?:\s|<[^>]*>)*(.+?)\|', webpage, u'uploader', fatal=False) - video_url = compat_urllib_parse.unquote(self._html_search_regex(r'video_url=(.+?)&', webpage, u'video_url')) - path = compat_urllib_parse_urlparse(video_url).path - extension = os.path.splitext(path)[1][1:] - format = path.split('/')[5].split('_')[:2] - format = "-".join(format) + video_title = self._html_search_regex( + r'

]*?title="([^"]+)"[^>]*>', webpage, 'title') + uploader = self._html_search_regex( + 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)) + + flash_vars = compat_parse_qs(self._search_regex( + r']+?name="flashvars"[^>]+?value="([^"]+)"', webpage, 'flash vars')) + + formats = [] + quality = qualities(['180p', '240p', '360p', '480p', '720p', '1080p']) + for k, vals in flash_vars.items(): + m = re.match(r'quality_(?P[0-9]+p)$', k) + if m is not None: + formats.append({ + 'format_id': m.group('quality'), + 'quality': quality(m.group('quality')), + 'url': vals[0], + }) + + self._sort_formats(formats) return { 'id': video_id, 'title': video_title, + 'formats': formats, 'uploader': uploader, - 'url': video_url, - 'ext': extension, - 'format': format, - 'format_id': format, + 'view_count': view_count, 'age_limit': 18, }