diff options
author | Sergey M. <dstftw@gmail.com> | 2014-02-24 23:30:09 +0700 |
---|---|---|
committer | Sergey M. <dstftw@gmail.com> | 2014-02-24 23:30:09 +0700 |
commit | ce78943ae1be8cc24ec43f97dc67d34010ae08f7 (patch) | |
tree | b13b2df5fcdfa436ad99df4d13461e0eb5424e39 /youtube_dl/extractor/novamov.py | |
parent | d6f0d8664977f72f54aaf644e87586d4b0e0be2d (diff) |
[novamov] Generalize extractor
Diffstat (limited to 'youtube_dl/extractor/novamov.py')
-rw-r--r-- | youtube_dl/extractor/novamov.py | 42 |
1 files changed, 24 insertions, 18 deletions
diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py index 22a382457..fd310e219 100644 --- a/youtube_dl/extractor/novamov.py +++ b/youtube_dl/extractor/novamov.py @@ -9,14 +9,25 @@ from ..utils import ( ) -class NovamovIE(InfoExtractor): - _VALID_URL = r'http://(?:(?:www\.)?novamov\.com/video/|(?:(?:embed|www)\.)novamov\.com/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' +class NovaMovIE(InfoExtractor): + IE_NAME = 'novamov' + IE_DESC = 'NovaMov' + + _VALID_URL = r'http://(?:(?:www\.)?%(host)s/video/|(?:(?:embed|www)\.)%(host)s/embed\.php\?(?:.*?&)?v=)(?P<videoid>[a-z\d]{13})' % {'host': 'novamov\.com'} + + _HOST = 'www.novamov.com' + + _FILE_DELETED_REGEX = r'This file no longer exists on our servers!</h2>' + _FILEKEY_REGEX = r'flashvars\.filekey="(?P<filekey>[^"]+)";' + _TITLE_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>' + _DESCRIPTION_REGEX = r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>' _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' }, @@ -27,31 +38,26 @@ class NovamovIE(InfoExtractor): 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') + page = self._download_webpage( + 'http://%s/video/%s' % (self._HOST, video_id), video_id, 'Downloading video page') - if re.search(r'This file no longer exists on our servers!</h2>', page) is not None: + if re.search(self._FILE_DELETED_REGEX, page) is not None: raise ExtractorError(u'Video %s does not exist' % video_id, expected=True) - filekey = self._search_regex( - r'flashvars\.filekey="(?P<filekey>[^"]+)";', page, 'filekey') + filekey = self._search_regex(self._FILEKEY_REGEX, page, 'filekey') - title = self._html_search_regex( - r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>([^<]+)</h3>', - page, 'title', fatal=False) + title = self._html_search_regex(self._TITLE_REGEX, page, 'title', fatal=False) - description = self._html_search_regex( - r'(?s)<div class="v_tab blockborder rounded5" id="v_tab1">\s*<h3>[^<]+</h3><p>([^<]+)</p>', - page, 'description', fatal=False) + description = self._html_search_regex(self._DESCRIPTION_REGEX, page, 'description', default='', 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') + '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] @@ -60,4 +66,4 @@ class NovamovIE(InfoExtractor): 'url': video_url, 'title': title, 'description': description - } + }
\ No newline at end of file |