X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fnovamov.py;h=04d779890af1960d65b070d0b2f80e429db21d07;hb=1cc79574fc5df21bf35dccf61eac0e9e75ed8d20;hp=e26b5522b33d8566f172df103b47389e3d333e9c;hpb=166ff8a3c7f18e0ab34660d526592b1a6c62df98;p=youtube-dl diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index e26b5522b..04d779890 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -3,57 +3,63 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import ( + compat_urlparse, +) from ..utils import ( ExtractorError, - compat_urlparse ) -class NovamovIE(InfoExtractor): + +class NovaMovIE(InfoExtractor): IE_NAME = 'novamov' - IE_DESC = 'novamov.com videos' - _VALID_URL = r'http://(?:www\.novamov\.com/video/|embed\.novamov\.com/embed\.php\?v=)(?P[a-z\d]{13})' + 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 = _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[^"]+)";' + _TITLE_REGEX = r'(?s)
\s*

([^<]+)

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

[^<]+

([^<]+)

' _TEST = { 'url': 'http://www.novamov.com/video/4rurhn9x446jj', - 'file': '4rurhn9x446jj.flv', '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('videoid') - - page = self._download_webpage('http://www.novamov.com/video/%s' % video_id, - video_id, 'Downloading video page') + video_id = mobj.group('id') - if re.search(r'This file no longer exists on our servers!', page) is not None: - raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) + page = self._download_webpage( + 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page') - mobj= re.search(r'flashvars\.filekey="(?P[^"]+)";', page) - if mobj is None: - raise ExtractorError('Unable to extract filekey', expected=True) + if re.search(self._FILE_DELETED_REGEX, page) is not None: + raise ExtractorError('Video %s does not exist' % video_id, expected=True) - filekey = mobj.group('filekey') + filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') - title = self._html_search_regex( - r'(?s)
\s*

([^<]+)

', - page, 'title', fatal=False) + 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) - description = self._html_search_regex( - r'(?s)
\s*

[^<]+

([^<]+)

', - page, 'description', fatal=False) - - api_response = self._download_webpage('http://www.novamov.com/api/player.api.php?key=%s&file=%s' % (filekey, video_id), - video_id, 'Downloading video api response') + api_response = self._download_webpage( + 'http://%s/api/player.api.php?key=%s&file=%s' % (self._HOST, filekey, video_id), video_id, + 'Downloading video api response') response = compat_urlparse.parse_qs(api_response) if 'error_msg' in response: - raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True) + raise ExtractorError('%s returned error: %s' % (self.IE_NAME, response['error_msg'][0]), expected=True) video_url = response['url'][0] @@ -62,4 +68,4 @@ class NovamovIE(InfoExtractor): 'url': video_url, 'title': title, 'description': description - } \ No newline at end of file + }