X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvk.py;h=38ff3c1a949c0511d08518b77180be653defce62;hb=8084be78c50e0e921508f13e69fda34a907dc5f8;hp=deaad6c3e14ad25947795414fd3a619dceb1e89b;hpb=02a12f9fe69508525c9cad06782151f5cf950671;p=youtube-dl diff --git a/youtube_dl/extractor/vk.py b/youtube_dl/extractor/vk.py index deaad6c3e..38ff3c1a9 100644 --- a/youtube_dl/extractor/vk.py +++ b/youtube_dl/extractor/vk.py @@ -5,13 +5,18 @@ import re import json from .common import InfoExtractor +from ..compat import ( + compat_str, + compat_urllib_parse, + compat_urllib_request, +) from ..utils import ( ExtractorError, - compat_urllib_request, - compat_urllib_parse, - compat_str, + orderedSet, + str_to_int, unescapeHTML, - unified_strdate) + unified_strdate, +) class VKIE(InfoExtractor): @@ -27,19 +32,23 @@ class VKIE(InfoExtractor): 'id': '162222515', 'ext': 'flv', 'title': 'ProtivoGunz - Хуёвая песня', - 'uploader': 're:Noize MC.*', + 'uploader': 're:(?:Noize MC|Alexander Ilyashenko).*', 'duration': 195, + 'upload_date': '20120212', + 'view_count': int, }, }, { - 'url': 'http://vk.com/video4643923_163339118', - 'md5': 'f79bccb5cd182b1f43502ca5685b2b36', + 'url': 'http://vk.com/video205387401_165548505', + 'md5': '6c0aeb2e90396ba97035b9cbde548700', 'info_dict': { - 'id': '163339118', + 'id': '165548505', 'ext': 'mp4', - 'uploader': 'Elya Iskhakova', - 'title': 'Dream Theater - Hollow Years Live at Budokan 720*', - 'duration': 558, + 'uploader': 'Tom Cruise', + 'title': 'No name', + 'duration': 9, + 'upload_date': '20130721', + 'view_count': int, } }, { @@ -52,9 +61,13 @@ class VKIE(InfoExtractor): 'uploader': 'Vladimir Gavrin', 'title': 'Lin Dan', 'duration': 101, + 'upload_date': '20120730', + 'view_count': int, } }, { + # VIDEO NOW REMOVED + # please update if you find a video whose URL follows the same pattern 'url': 'http://vk.com/video-8871596_164049491', 'md5': 'a590bcaf3d543576c9bd162812387666', 'note': 'Only available for registered users', @@ -64,18 +77,8 @@ class VKIE(InfoExtractor): 'uploader': 'Триллеры', 'title': '► Бойцовский клуб / Fight Club 1999 [HD 720]', 'duration': 8352, - }, - 'skip': 'Requires vk account credentials', - }, - { - 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', - 'md5': 'd82c22e449f036282d1d3f7f4d276869', - 'info_dict': { - 'id': '166094326', - 'ext': 'mp4', - 'uploader': 'Киномания - лучшее из мира кино', - 'title': 'Запах женщины (1992)', - 'duration': 9392, + 'upload_date': '20121218', + 'view_count': int, }, 'skip': 'Requires vk account credentials', }, @@ -88,6 +91,7 @@ class VKIE(InfoExtractor): 'uploader': 'Киномания - лучшее из мира кино', 'title': ' ', 'duration': 7291, + 'upload_date': '20140328', }, 'skip': 'Requires vk account credentials', }, @@ -100,9 +104,16 @@ class VKIE(InfoExtractor): 'ext': 'mp4', 'title': 'Книга Илая', 'duration': 6771, + 'upload_date': '20140626', + 'view_count': int, }, 'skip': 'Only works from Russia', }, + { + # removed video, just testing that we match the pattern + 'url': 'http://vk.com/feed?z=video-43215063_166094326%2Fbb50cacd3177146d7a', + 'only_matching': True, + }, ] def _login(self): @@ -114,12 +125,12 @@ class VKIE(InfoExtractor): 'act': 'login', 'role': 'al_frame', 'expire': '1', - 'email': username, - 'pass': password, + 'email': username.encode('cp1251'), + 'pass': password.encode('cp1251'), } request = compat_urllib_request.Request('https://login.vk.com/?act=login', - compat_urllib_parse.urlencode(login_form).encode('utf-8')) + compat_urllib_parse.urlencode(login_form).encode('utf-8')) login_page = self._download_webpage(request, None, note='Logging in as %s' % username) if re.search(r'onLoginFailed', login_page): @@ -135,17 +146,22 @@ class VKIE(InfoExtractor): if not video_id: video_id = '%s_%s' % (mobj.group('oid'), mobj.group('id')) - info_url = 'http://vk.com/al_video.php?act=show&al=1&video=%s' % video_id + info_url = 'http://vk.com/al_video.php?act=show&al=1&module=video&video=%s' % video_id info_page = self._download_webpage(info_url, video_id) ERRORS = { r'>Видеозапись .*? была изъята из публичного доступа в связи с обращением правообладателя.<': - 'Video %s has been removed from public access due to rightholder complaint.', + 'Video %s has been removed from public access due to rightholder complaint.', + r'Please log in or <': - 'Video %s is only available for registered users, ' - 'use --username and --password options to provide account credentials.', - 'Unknown error': - 'Video %s does not exist.' + 'Video %s is only available for registered users, ' + 'use --username and --password options to provide account credentials.', + + r'Unknown error': + 'Video %s does not exist.', + + r'Видео временно недоступно': + 'Video %s is temporarily unavailable.', } for error_re, error_msg in ERRORS.items(): @@ -157,24 +173,37 @@ class VKIE(InfoExtractor): self.to_screen('Youtube video detected') return self.url_result(m_yt.group(1), 'Youtube') - m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.*?});', info_page) + m_rutube = re.search( + r'\ssrc="((?:https?:)?//rutube\.ru\\?/video\\?/embed(?:.*?))\\?"', info_page) + if m_rutube is not None: + self.to_screen('rutube video detected') + rutube_url = self._proto_relative_url( + m_rutube.group(1).replace('\\', '')) + return self.url_result(rutube_url) + + m_opts = re.search(r'(?s)var\s+opts\s*=\s*({.+?});', info_page) if m_opts: - m_opts_url = re.search(r"url\s*:\s*'([^']+)", m_opts.group(1)) + m_opts_url = re.search(r"url\s*:\s*'((?!/\b)[^']+)", m_opts.group(1)) if m_opts_url: opts_url = m_opts_url.group(1) if opts_url.startswith('//'): opts_url = 'http:' + opts_url return self.url_result(opts_url) - data_json = self._search_regex(r'var vars = ({.*?});', info_page, 'vars') + data_json = self._search_regex(r'var\s+vars\s*=\s*({.+?});', info_page, 'vars') data = json.loads(data_json) # Extract upload date upload_date = None - mobj = re.search(r'id="mv_date_wrap".*?Added ([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page) + mobj = re.search(r'id="mv_date(?:_views)?_wrap"[^>]*>([a-zA-Z]+ [0-9]+), ([0-9]+) at', info_page) if mobj is not None: + mobj.group(1) + ' ' + mobj.group(2) upload_date = unified_strdate(mobj.group(1) + ' ' + mobj.group(2)) + view_count = str_to_int(self._search_regex( + r'"mv_views_count_number"[^>]*>([\d,.]+) views<', + info_page, 'view count', fatal=False)) + formats = [{ 'format_id': k, 'url': v, @@ -191,39 +220,30 @@ class VKIE(InfoExtractor): 'uploader': data.get('md_author'), 'duration': data.get('duration'), 'upload_date': upload_date, + 'view_count': view_count, } class VKUserVideosIE(InfoExtractor): IE_NAME = 'vk.com:user-videos' - IE_DESC = 'All of a user\'s videos' - _VALID_URL = r'https?://(?:m\.)?vk\.com/videos([0-9]+)(?:m\?.*)?' + IE_DESC = 'vk.com:All of a user\'s videos' + _VALID_URL = r'https?://vk\.com/videos(?P[0-9]+)(?:m\?.*)?' _TEMPLATE_URL = 'https://vk.com/videos' _TEST = { 'url': 'http://vk.com/videos205387401', + 'info_dict': { + 'id': '205387401', + }, 'playlist_mincount': 4, } - def extract_videos_from_page(self, page): - ids_in_page = [] - for mobj in re.finditer(r'href="/video([0-9_]+)"', page): - if mobj.group(1) not in ids_in_page: - ids_in_page.append(mobj.group(1)) - return ids_in_page - def _real_extract(self, url): - # Extract page id - mobj = re.match(self._VALID_URL, url) - if mobj is None: - raise ExtractorError('Invalid URL: %s' % url) - - # Download page and get video ids - page_id = mobj.group(1) + page_id = self._match_id(url) page = self._download_webpage(url, page_id) - video_ids = self.extract_videos_from_page(page) - - self._downloader.to_screen('[vk] User videos %s: Found %i videos' % (page_id, len(video_ids))) - - url_entries = [self.url_result('http://vk.com/video' + video_id, 'VK', video_id=video_id) - for video_id in video_ids] - return self.playlist_result(url_entries, page_id) \ No newline at end of file + video_ids = orderedSet( + m.group(1) for m in re.finditer(r'href="/video([0-9_]+)"', page)) + url_entries = [ + self.url_result( + 'http://vk.com/video' + video_id, 'VK', video_id=video_id) + for video_id in video_ids] + return self.playlist_result(url_entries, page_id)