Browse Source

[makerschannel] Add new extractor(closes #8839)

master
remitamine 8 years ago
parent
commit
a42dfa629e
2 changed files with 41 additions and 0 deletions
  1. 1
      youtube_dl/extractor/__init__.py
  2. 40
      youtube_dl/extractor/makerschannel.py

1
youtube_dl/extractor/__init__.py

@ -389,6 +389,7 @@ from .lynda import (
from .m6 import M6IE
from .macgamestore import MacGameStoreIE
from .mailru import MailRuIE
from .makerschannel import MakersChannelIE
from .makertv import MakerTVIE
from .malemotion import MalemotionIE
from .matchtv import MatchTVIE

40
youtube_dl/extractor/makerschannel.py

@ -0,0 +1,40 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
class MakersChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?makerschannel\.com/.*(?P<id_type>video|production)_id=(?P<id>[0-9]+)'
_TEST = {
'url': 'http://makerschannel.com/en/zoomin/community-highlights?video_id=849',
'md5': '624a512c6969236b5967bf9286345ad1',
'info_dict': {
'id': '849',
'ext': 'mp4',
'title': 'Landing a bus on a plane is an epic win',
'uploader': 'ZoomIn',
'description': 'md5:cd9cca2ea7b69b78be81d07020c97139',
}
}
def _real_extract(self, url):
id_type, url_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, url_id)
video_data = self._html_search_regex(r'<div([^>]+data-%s-id="%s"[^>]+)>' % (id_type, url_id), webpage, 'video data')
def extract_data_val(attr, fatal=False):
return self._html_search_regex(r'data-%s\s*=\s*"([^"]+)"' % attr, video_data, attr, fatal=fatal)
minoto_id = self._search_regex(r'/id/([a-zA-Z0-9]+)', extract_data_val('video-src', True), 'minoto id')
return {
'_type': 'url_transparent',
'url': 'minoto:%s' % minoto_id,
'id': extract_data_val('video-id', True),
'title': extract_data_val('title', True),
'description': extract_data_val('description'),
'thumbnail': extract_data_val('image'),
'uploader': extract_data_val('channel'),
}
Loading…
Cancel
Save