X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fxtube.py;h=01b253dcb1e8c92232a06c0b2b4153a545dabcc1;hb=HEAD;hp=8cd3a06877251ac6d8ec75eea7fb3756b4026b37;hpb=34dd81c03a23ef7e4db31f8aa9a61473f2d8f727;p=youtube-dl diff --git a/youtube_dl/extractor/xtube.py b/youtube_dl/extractor/xtube.py index 8cd3a0687..01b253dcb 100644 --- a/youtube_dl/extractor/xtube.py +++ b/youtube_dl/extractor/xtube.py @@ -4,9 +4,10 @@ import itertools import re from .common import InfoExtractor -from ..compat import compat_urllib_parse_unquote from ..utils import ( int_or_none, + js_to_json, + orderedSet, parse_duration, sanitized_Request, str_to_int, @@ -14,8 +15,16 @@ from ..utils import ( class XTubeIE(InfoExtractor): - _VALID_URL = r'(?:xtube:|https?://(?:www\.)?xtube\.com/watch\.php\?.*\bv=)(?P[^/?&#]+)' - _TEST = { + _VALID_URL = r'''(?x) + (?: + xtube:| + https?://(?:www\.)?xtube\.com/(?:watch\.php\?.*\bv=|video-watch/(?:embedded/)?(?P[^/]+)-) + ) + (?P[^/?&#]+) + ''' + + _TESTS = [{ + # old URL schema 'url': 'http://www.xtube.com/watch.php?v=kVTUy_G222_', 'md5': '092fbdd3cbe292c920ef6fc6a8a9cdab', 'info_dict': { @@ -25,66 +34,124 @@ class XTubeIE(InfoExtractor): 'description': 'contains:an ET kind of thing', 'uploader': 'greenshowers', 'duration': 450, + 'view_count': int, + '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': 'md5:4cc3af1aa1b0413289babc88f0d4f616', + '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', + 'only_matching': True, + }, { + 'url': 'xtube:625837', + 'only_matching': True, + }, { + '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): - video_id = self._match_id(url) + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + display_id = mobj.group('display_id') + + if not display_id: + display_id = video_id + + if video_id.isdigit() and len(video_id) < 11: + url_pattern = 'http://www.xtube.com/video-watch/-%s' + else: + url_pattern = 'http://www.xtube.com/watch.php?v=%s' + + webpage = self._download_webpage( + url_pattern % video_id, display_id, headers={ + 'Cookie': 'age_verified=1; cookiesAccepted=1', + }) + + title, thumbnail, duration = [None] * 3 + + config = self._parse_json(self._search_regex( + r'playerConf\s*=\s*({.+?})\s*,\s*\n', webpage, 'config', + default='{}'), video_id, transform_source=js_to_json, fatal=False) + if config: + config = config.get('mainRoll') + if isinstance(config, dict): + title = config.get('title') + thumbnail = config.get('poster') + duration = int_or_none(config.get('duration')) + sources = config.get('sources') or config.get('format') + + if not isinstance(sources, dict): + sources = self._parse_json(self._search_regex( + r'(["\'])?sources\1?\s*:\s*(?P{.+?}),', + webpage, 'sources', group='sources'), video_id, + transform_source=js_to_json) - req = sanitized_Request('http://www.xtube.com/watch.php?v=%s' % video_id) - req.add_header('Cookie', 'age_verified=1') - webpage = self._download_webpage(req, video_id) + formats = [] + for format_id, format_url in sources.items(): + formats.append({ + 'url': format_url, + 'format_id': format_id, + 'height': int_or_none(format_id), + }) + self._remove_duplicate_formats(formats) + self._sort_formats(formats) - video_title = self._html_search_regex( - r'

([^<]+)', webpage, 'title') - video_uploader = self._html_search_regex( - [r"var\s+contentOwnerId\s*=\s*'([^']+)", - r'By:\s*\s*(?P[^<]+?)\s*</h1>', r'videoTitle\s*:\s*(["\'])(?P<title>.+?)\1'), + webpage, 'title', group='title') + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage, default=None) or self._search_regex( + r'</h1>\s*<p>([^<]+)', webpage, 'description', fatal=False) + uploader = self._search_regex( + (r'<input[^>]+name="contentOwnerId"[^>]+value="([^"]+)"', + r'<span[^>]+class="nickname"[^>]*>([^<]+)'), webpage, 'uploader', fatal=False) - video_description = self._html_search_regex( - r'<p class="fieldsDesc">([^<]+)', - webpage, 'description', fatal=False) - duration = parse_duration(self._html_search_regex( - r'<span class="bold">Runtime:</span> ([^<]+)</p>', - webpage, 'duration', fatal=False)) - view_count = str_to_int(self._html_search_regex( - r'<span class="bold">Views:</span> ([\d,\.]+)</p>', + if not duration: + duration = parse_duration(self._search_regex( + r'<dt>Runtime:?</dt>\s*<dd>([^<]+)</dd>', + webpage, 'duration', fatal=False)) + view_count = str_to_int(self._search_regex( + (r'["\']viewsCount["\'][^>]*>(\d+)\s+views', + r'<dt>Views:?</dt>\s*<dd>([\d,\.]+)</dd>'), webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( - r'<div id="commentBar">([\d,\.]+) Comments</div>', + r'>Comments? \(([\d,\.]+)\)<', webpage, 'comment count', fatal=False)) - formats = [] - for format_id, video_url in re.findall( - r'flashvars\.quality_(.+?)\s*=\s*"([^"]+)"', webpage): - fmt = { - 'url': compat_urllib_parse_unquote(video_url), - 'format_id': format_id, - } - m = re.search(r'^(?P<height>\d+)[pP]', format_id) - if m: - fmt['height'] = int(m.group('height')) - formats.append(fmt) - - if not formats: - video_url = compat_urllib_parse_unquote(self._search_regex( - r'flashvars\.video_url\s*=\s*"([^"]+)"', - webpage, 'video URL')) - formats.append({'url': video_url}) - - self._sort_formats(formats) - return { 'id': video_id, - 'title': video_title, - 'uploader': video_uploader, - 'description': video_description, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'uploader': uploader, 'duration': duration, 'view_count': view_count, 'comment_count': comment_count, - 'formats': formats, 'age_limit': 18, + 'formats': formats, } @@ -97,7 +164,7 @@ class XTubeUserIE(InfoExtractor): 'id': 'greenshowers-4056496', 'age_limit': 18, }, - 'playlist_mincount': 155, + 'playlist_mincount': 154, } def _real_extract(self, url): @@ -120,7 +187,8 @@ class XTubeUserIE(InfoExtractor): if not html: break - for _, video_id in re.findall(r'data-plid=(["\'])(.+?)\1', html): + for video_id in orderedSet([video_id for _, video_id in re.findall( + r'data-plid=(["\'])(.+?)\1', html)]): entries.append(self.url_result('xtube:%s' % video_id, XTubeIE.ie_key())) page_count = int_or_none(page.get('pageCount'))