X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/6d835d4d6903cf5e18ad01844736929e06d16004..67afe88251ff8b1fcb43246c9a4bb1a0ea0185a2:/youtube_dl/extractor/extremetube.py diff --git a/youtube_dl/extractor/extremetube.py b/youtube_dl/extractor/extremetube.py index aacbf14..c826a54 100644 --- a/youtube_dl/extractor/extremetube.py +++ b/youtube_dl/extractor/extremetube.py @@ -3,19 +3,21 @@ 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]+))(?:[/?&]|$)' + _VALID_URL = r'https?://(?:www\.)?(?Pextremetube\.com/.*?video/.+?(?P[0-9]+))(?:[/?&]|$)' _TESTS = [{ 'url': 'http://www.extremetube.com/video/music-video-14-british-euro-brit-european-cumshots-swallow-652431', - 'md5': '1fb9228f5e3332ec8c057d6ac36f33e0', + 'md5': '344d0c6d50e2f16b06e49ca011d8ac69', 'info_dict': { 'id': '652431', 'ext': 'mp4', @@ -31,7 +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) @@ -47,19 +49,27 @@ class ExtremeTubeIE(InfoExtractor): 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 - format = path.split('/')[5].split('_')[:2] - format = "-".join(format) + 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, 'view_count': view_count, - 'url': video_url, - 'format': format, - 'format_id': format, 'age_limit': 18, }