X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/415fdb62500dca2e22067a05008dfbf87c75b662..83c8b40add31fb501d587b64fb17a936ffd5dbc5:/youtube_dl/extractor/novamov.py diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 2e7ab1e..3bbd473 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -3,9 +3,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( ExtractorError, - compat_urlparse + NO_DEFAULT, + sanitized_Request, + urlencode_postdata, ) @@ -13,42 +16,70 @@ class NovaMovIE(InfoExtractor): IE_NAME = 'novamov' IE_DESC = 'NovaMov' - _VALID_URL_TEMPLATE = r'http://(?:(?:www\.)?%(host)s/(?:file|video)/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P[a-z\d]{13})' + _VALID_URL_TEMPLATE = r'''(?x) + http:// + (?: + (?:www\.)?%(host)s/(?:file|video|mobile/\#/videos)/| + (?:(?:embed|www)\.)%(host)s/embed(?:\.php|/)?\?(?:.*?&)?\bv= + ) + (?P[a-z\d]{13}) + ''' _VALID_URL = _VALID_URL_TEMPLATE % {'host': 'novamov\.com'} _HOST = 'www.novamov.com' _FILE_DELETED_REGEX = r'This file no longer exists on our servers!' - _FILEKEY_REGEX = r'flashvars\.filekey="(?P[^"]+)";' + _FILEKEY_REGEX = r'flashvars\.filekey=(?P"?[^"]+"?);' _TITLE_REGEX = r'(?s)
\s*

([^<]+)

' _DESCRIPTION_REGEX = r'(?s)
\s*

[^<]+

([^<]+)

' + _URL_TEMPLATE = 'http://%s/video/%s' - _TEST = { - 'url': 'http://www.novamov.com/video/4rurhn9x446jj', - 'md5': '7205f346a52bbeba427603ba10d4b935', - 'info_dict': { - 'id': '4rurhn9x446jj', - 'ext': 'flv', - 'title': 'search engine optimization', - 'description': 'search engine optimization is used to rank the web page in the google search engine' - }, - 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)' - } - - def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - video_id = mobj.group('id') - - page = self._download_webpage( - 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page') + _TEST = None - if re.search(self._FILE_DELETED_REGEX, page) is not None: + def _check_existence(self, webpage, video_id): + if re.search(self._FILE_DELETED_REGEX, webpage) is not None: raise ExtractorError('Video %s does not exist' % video_id, expected=True) - filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') - - title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) - description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', fatal=False) + def _real_extract(self, url): + video_id = self._match_id(url) + + url = self._URL_TEMPLATE % (self._HOST, video_id) + + webpage = self._download_webpage( + url, video_id, 'Downloading video page') + + self._check_existence(webpage, video_id) + + def extract_filekey(default=NO_DEFAULT): + filekey = self._search_regex( + self._FILEKEY_REGEX, webpage, 'filekey', default=default) + if filekey is not default and (filekey[0] != '"' or filekey[-1] != '"'): + return self._search_regex( + r'var\s+%s\s*=\s*"([^"]+)"' % re.escape(filekey), webpage, 'filekey', default=default) + else: + return filekey + + filekey = extract_filekey(default=None) + + if not filekey: + fields = self._hidden_inputs(webpage) + post_url = self._search_regex( + r']+action=(["\'])(?P.+?)\1', webpage, + 'post url', default=url, group='url') + if not post_url.startswith('http'): + post_url = compat_urlparse.urljoin(url, post_url) + request = sanitized_Request( + post_url, urlencode_postdata(fields)) + request.add_header('Content-Type', 'application/x-www-form-urlencoded') + request.add_header('Referer', post_url) + webpage = self._download_webpage( + request, video_id, 'Downloading continue to the video page') + self._check_existence(webpage, video_id) + + filekey = extract_filekey() + + title = self._html_search_regex(self._TITLE_REGEX, webpage, 'title') + description = self._html_search_regex(self._DESCRIPTION_REGEX, webpage, 'description', default='', fatal=False) api_response = self._download_webpage( 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id, @@ -66,4 +97,116 @@ class NovaMovIE(InfoExtractor): 'url': video_url, 'title': title, 'description': description - } \ No newline at end of file + } + + +class WholeCloudIE(NovaMovIE): + IE_NAME = 'wholecloud' + IE_DESC = 'WholeCloud' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': '(?:wholecloud\.net|movshare\.(?:net|sx|ag))'} + + _HOST = 'www.wholecloud.net' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'Title: ([^<]+)

' + _DESCRIPTION_REGEX = r'Description: ([^<]+)

' + + _TEST = { + 'url': 'http://www.wholecloud.net/video/559e28be54d96', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': '559e28be54d96', + 'ext': 'flv', + 'title': 'dissapeared image', + 'description': 'optical illusion dissapeared image magic illusion', + } + } + + +class NowVideoIE(NovaMovIE): + IE_NAME = 'nowvideo' + IE_DESC = 'NowVideo' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'nowvideo\.(?:to|ch|ec|sx|eu|at|ag|co|li)'} + + _HOST = 'www.nowvideo.to' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'

([^<]+)

' + _DESCRIPTION_REGEX = r'\s*

([^<]+)

' + + _TEST = { + 'url': 'http://www.nowvideo.sx/video/f1d6fce9a968b', + 'md5': '12c82cad4f2084881d8bc60ee29df092', + 'info_dict': { + 'id': 'f1d6fce9a968b', + 'ext': 'flv', + 'title': 'youtubedl test video BaWjenozKc', + 'description': 'Description', + }, + } + + +class VideoWeedIE(NovaMovIE): + IE_NAME = 'videoweed' + IE_DESC = 'VideoWeed' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'videoweed\.(?:es|com)'} + + _HOST = 'www.videoweed.es' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r'

([^<]+)

' + _URL_TEMPLATE = 'http://%s/file/%s' + + _TEST = { + 'url': 'http://www.videoweed.es/file/b42178afbea14', + 'md5': 'abd31a2132947262c50429e1d16c1bfd', + 'info_dict': { + 'id': 'b42178afbea14', + 'ext': 'flv', + 'title': 'optical illusion dissapeared image magic illusion', + 'description': '' + }, + } + + +class CloudTimeIE(NovaMovIE): + IE_NAME = 'cloudtime' + IE_DESC = 'CloudTime' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'cloudtime\.to'} + + _HOST = 'www.cloudtime.to' + + _FILE_DELETED_REGEX = r'>This file no longer exists on our servers.<' + _TITLE_REGEX = r']+class=["\']video_det["\'][^>]*>\s*([^<]+)' + + _TEST = None + + +class AuroraVidIE(NovaMovIE): + IE_NAME = 'auroravid' + IE_DESC = 'AuroraVid' + + _VALID_URL = NovaMovIE._VALID_URL_TEMPLATE % {'host': 'auroravid\.to'} + + _HOST = 'www.auroravid.to' + + _FILE_DELETED_REGEX = r'This file no longer exists on our servers!<' + + _TESTS = [{ + 'url': 'http://www.auroravid.to/video/4rurhn9x446jj', + 'md5': '7205f346a52bbeba427603ba10d4b935', + 'info_dict': { + 'id': '4rurhn9x446jj', + 'ext': 'flv', + 'title': 'search engine optimization', + 'description': 'search engine optimization is used to rank the web page in the google search engine' + }, + 'skip': '"Invalid token" errors abound (in web interface as well as youtube-dl, there is nothing we can do about it.)' + }, { + 'url': 'http://www.auroravid.to/embed/?v=4rurhn9x446jj', + 'only_matching': True, + }]