1
0
mirror of https://codeberg.org/polarisfm/youtube-dl synced 2024-12-22 22:47:55 +01:00

[Mojvideo] Add new extractor

This commit is contained in:
David Fabijan 2014-08-03 10:50:25 +02:00
parent 493987fefe
commit 5537dce84d
2 changed files with 47 additions and 0 deletions

View File

@ -181,6 +181,7 @@ from .mixcloud import MixcloudIE
from .mlb import MLBIE from .mlb import MLBIE
from .mpora import MporaIE from .mpora import MporaIE
from .mofosex import MofosexIE from .mofosex import MofosexIE
from .mojvideo import MojvideoIE
from .mooshare import MooshareIE from .mooshare import MooshareIE
from .morningstar import MorningstarIE from .morningstar import MorningstarIE
from .motherless import MotherlessIE from .motherless import MotherlessIE

View File

@ -0,0 +1,46 @@
import re
from .common import InfoExtractor
class MojvideoIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?mojvideo\.com/video-.*/(?P<id>[a-f0-9]+)'
_TEST = {
'url': 'http://www.mojvideo.com/video-v-avtu-pred-mano-rdecelaska-alfi-nipic/3d1ed4497707730b2906',
'md5': 'f7fd662cc8ce2be107b0d4f2c0483ae7',
'info_dict': {
'id': '3d1ed4497707730b2906',
'ext': 'mp4',
'title': 'V avtu pred mano rdečelaska - Alfi Nipič',
'description':'Video: V avtu pred mano rdečelaska - Alfi Nipič',
'height':378,
'width':480
# TODO more properties, either as:
# * A value
# * MD5 checksum; start the string with md5:
# * A regular expression; start the string with re:
# * Any Python type (for example int or float)
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
# TODO more code goes here, for example ...
webpage = self._download_webpage(url, video_id)
title = self._html_search_regex(r'<title>(.*?)</title>', webpage, 'title')
description = self._search_regex(r'<meta name="description" content="(.*)" />', webpage, 'video description')
final_url = self._html_search_regex(r'mp4: \'(.*)\'', webpage, 'video url')
height=int(self._search_regex(r'<meta name="video_height" content="([0-9]*)" />',webpage,"video height"))
width=int(self._search_regex(r'<meta name="video_width" content="([0-9]*)" />',webpage,"video width"))
return {
'id': video_id,
'title': title,
'description': description,
'ext': 'mp4',
'url': final_url,
'height':height,
'width':width
# TODO more properties (see youtube_dl/extractor/common.py)
}