diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 99ba725d9..e813ba976 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -128,6 +128,7 @@ from .nhl import NHLIE, NHLVideocenterIE from .niconico import NiconicoIE from .ninegag import NineGagIE +from .novamov import NovamovIE from .nowvideo import NowVideoIE from .ooyala import OoyalaIE from .orf import ORFIE diff --git a/youtube_dl/extractor/novamov.py b/youtube_dl/extractor/novamov.py new file mode 100644 index 000000000..e26b5522b --- /dev/null +++ b/youtube_dl/extractor/novamov.py @@ -0,0 +1,65 @@ +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + ExtractorError, + compat_urlparse +) + +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})' + + _TEST = { + 'url': 'http://www.novamov.com/video/4rurhn9x446jj', + 'file': '4rurhn9x446jj.flv', + 'md5': '7205f346a52bbeba427603ba10d4b935', + 'info_dict': { + 'title': 'search engine optimization', + 'description': 'search engine optimization is used to rank the web page in the google search engine' + } + } + + 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') + + 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) + + mobj= re.search(r'flashvars\.filekey="(?P[^"]+)";', page) + if mobj is None: + raise ExtractorError('Unable to extract filekey', expected=True) + + filekey = mobj.group('filekey') + + title = self._html_search_regex( + r'(?s)
\s*

([^<]+)

', + page, 'title', 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') + + response = compat_urlparse.parse_qs(api_response) + + if 'error_msg' in response: + raise ExtractorError('novamov returned error: %s' % response['error_msg'][0], expected=True) + + video_url = response['url'][0] + + return { + 'id': video_id, + 'url': video_url, + 'title': title, + 'description': description + } \ No newline at end of file