1
1
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-05 03:02:56 +01:00
youtube-dl/youtube_dl/extractor/mojvideo.py

59 lines
2.0 KiB
Python
Raw Normal View History

2014-08-06 14:44:29 +02:00
# coding: utf-8
from __future__ import unicode_literals
2014-08-03 10:50:25 +02:00
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
parse_duration,
)
2014-08-03 10:50:25 +02:00
class MojvideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-(?P<display_id>[^/]+)/(?P<id>[a-f0-9]+)'
2014-08-03 10:50:25 +02:00
_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',
2014-08-03 10:50:25 +02:00
'ext': 'mp4',
'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
'thumbnail': 're:^http://.*\.jpg$',
'duration': 242,
2014-08-03 10:50:25 +02:00
}
}
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)
2014-08-03 10:50:25 +02:00
if '<error>true</error>' in playerapi:
error_desc = self._html_search_regex(
r'<errordesc>([^<]*)</errordesc>', playerapi, 'error description', fatal=False)
raise ExtractorError('%s said: %s' % (self.IE_NAME, error_desc), expected=True)
title = self._html_search_regex(
r'<title>([^<]+)</title>', playerapi, 'title')
video_url = self._html_search_regex(
r'<file>([^<]+)</file>', playerapi, 'video URL')
thumbnail = self._html_search_regex(
r'<preview>([^<]+)</preview>', playerapi, 'thumbnail', fatal=False)
duration = parse_duration(self._html_search_regex(
r'<duration>([^<]+)</duration>', playerapi, 'duration', fatal=False))
2014-08-03 10:50:25 +02:00
return {
'id': video_id,
'display_id': display_id,
'url': video_url,
2014-08-03 10:50:25 +02:00
'title': title,
'thumbnail': thumbnail,
'duration': duration,
2014-11-23 20:41:03 +01:00
}