X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxtube.py;h=c6c0b3291c8320064fa0a7529be5b5d78f14461c;hb=77d95677b7ab4a9840ef142b14627b07a9a31120;hp=5584674a061fc5a67bbb65bc0b58fc96e96eae3b;hpb=085f169ffebc17ec8b2bfc63aec8f5df57c7bdcf;p=youtube-dl diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 5584674a0..c6c0b3291 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -6,6 +6,7 @@ import re from .common import InfoExtractor from ..utils import ( int_or_none, + js_to_json, orderedSet, parse_duration, sanitized_Request, @@ -17,7 +18,7 @@ class XTubeIE(InfoExtractor): _VALID_URL = r'''(?x) (?: xtube:| - https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?P[^/]+)-) + https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P[^/]+)-) ) (?P[^/?&#]+) ''' @@ -37,6 +38,22 @@ class XTubeIE(InfoExtractor): 'comment_count': int, 'age_limit': 18, } + }, { + # FLV videos with duplicated formats + 'url': 'http://www.xtube.com/video-watch/A-Super-Run-Part-1-YT-9299752', + 'md5': 'a406963eb349dd43692ec54631efd88b', + 'info_dict': { + 'id': '9299752', + 'display_id': 'A-Super-Run-Part-1-YT', + 'ext': 'flv', + 'title': 'A Super Run - Part 1 (YT)', + 'description': 'md5:ca0d47afff4a9b2942e4b41aa970fd93', + 'uploader': 'tshirtguy59', + 'duration': 579, + 'view_count': int, + 'comment_count': int, + 'age_limit': 18, + }, }, { # new URL schema 'url': 'http://www.xtube.com/video-watch/strange-erotica-625837', @@ -47,6 +64,9 @@ class XTubeIE(InfoExtractor): }, { 'url': 'xtube:kVTUy_G222_', 'only_matching': True, + }, { + 'url': 'https://www.xtube.com/video-watch/embedded/milf-tara-and-teen-shared-and-cum-covered-extreme-bukkake-32203482?embedsize=big', + 'only_matching': True, }] def _real_extract(self, url): @@ -68,8 +88,9 @@ class XTubeIE(InfoExtractor): }) sources = self._parse_json(self._search_regex( - r'(["\'])sources\1\s*:\s*(?P{.+?}),', - webpage, 'sources', group='sources'), video_id) + r'(["\'])?sources\1?\s*:\s*(?P{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) formats = [] for format_id, format_url in sources.items(): @@ -78,6 +99,7 @@ class XTubeIE(InfoExtractor): 'format_id': format_id, 'height': int_or_none(format_id), }) + self._remove_duplicate_formats(formats) self._sort_formats(formats) title = self._search_regex(