1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-01 06:27:44 +00:00
youtube-dl/youtube_dl/extractor/kankids.py

45 lines
1.7 KiB
Python
Raw Normal View History

# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
class KanKidsIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?kankids\.org\.il/content/kids/(?P<category>[a-z]+)-main/p-(?P<id>[0-9]+)/(?P<season>\w+/)?$'
_TEST = {
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/',
'md5': 'TODO: md5 sum of the first 10241 bytes of the video file (use --test)',
'info_dict': {
'id': '42',
'ext': 'mp4',
'title': 'Video title goes here',
'thumbnail': r're:^https?://.*\.jpg$',
# 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):
a = super()._match_valid_url(url)
print(a.groupdict())
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
# title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
title = 'hi'
return {
'id': video_id,
'title': title,
'description': self._og_search_description(webpage),
'url': 'https://www.kankids.org.il/content/kids/hinuchit-main/p-12050/s1/89707/',
'ie_key': 'Generic',
'_type': 'url',
# 'uploader': self._search_regex(r'<div[^>]+id="uploader"[^>]*>([^<]+)<', webpage, 'uploader', fatal=False),
# TODO more properties (see youtube_dl/extractor/common.py)
}