diff --git a/youtube_dl/extractor/mojvideo.py b/youtube_dl/extractor/mojvideo.py index ddfef6d3c..90b460d65 100644 --- a/youtube_dl/extractor/mojvideo.py +++ b/youtube_dl/extractor/mojvideo.py @@ -1,41 +1,58 @@ # coding: utf-8 from __future__ import unicode_literals + import re from .common import InfoExtractor +from ..utils import ( + ExtractorError, + parse_duration, +) + class MojvideoIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-.*/(?P[a-f0-9]+)' + _VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P[^/]+)/(?P[a-f0-9]+)' _TEST = { 'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906', 'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7', 'info_dict': { 'id': '3d1ed4497707730b2906', + 'display_id': 'v-avtu-pred-mano-rdecelaska-alfi-nipic', 'ext': 'mp4', 'title': 'V avtu pred mano rdečelaska - Alfi Nipič', - 'description':'Video: V avtu pred mano rdečelaska - Alfi Nipič', - 'height':378, - 'width':480 + 'thumbnail': 're:^http://.*\.jpg$', + 'duration': 242, } } def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') + display_id = mobj.group('display_id') + + # XML is malformed + playerapi = self._download_webpage( + 'http://www.mojvideo.com/playerapi.php?v=%s&t=1' % video_id, display_id) - webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'(.*?)', webpage, 'title') - description = self._search_regex(r'', webpage, 'video description') - final_url = self._html_search_regex(r'mp4: \'(.*)\'', webpage, 'video url') - height=int(self._search_regex(r'',webpage,"video height")) - width=int(self._search_regex(r'',webpage,"video width")) + if 'true' in playerapi: + error_desc = self._html_search_regex( + r'([^<]*)', playerapi, 'error description', fatal=False) + raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True) + + title = self._html_search_regex( + r'([^<]+)', playerapi, 'title') + video_url = self._html_search_regex( + r'([^<]+)', playerapi, 'video URL') + thumbnail = self._html_search_regex( + r'([^<]+)', playerapi, 'thumbnail', fatal=False) + duration = parse_duration(self._html_search_regex( + r'([^<]+)', playerapi, 'duration', fatal=False)) return { 'id': video_id, + 'display_id': display_id, + 'url': video_url, 'title': title, - 'description': description, - 'ext': 'mp4', - 'url': final_url, - 'height':height, - 'width':width + 'thumbnail': thumbnail, + 'duration': duration, } \ No newline at end of file