youtube-dl/youtube_dl/extractor/kankids.py

# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
import re

CONTENT_DIR = r'/content/kids/'
DOMAIN = r'kankids.org.il'

class KanKidsIE(InfoExtractor):
    _VALID_URL = r'https?://(?:www\.)?' +\
        DOMAIN.replace('.', '\.') + CONTENT_DIR +\
        r'(?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):
        m = super()._match_valid_url(url)
        series_id = m.group('id')
        category = m.group('category')
        playlist_season = m.group('season')
        
        webpage = self._download_webpage(url, series_id)

        series_title = self._html_search_regex(r'<title>(?P<title>.+) \|', webpage, 'title')

        season = playlist_season if playlist_season else r'(?P<season>\w+)'
        content_dir = CONTENT_DIR + category + r'-main/'
        playlist = set(re.findall(
            r'href="' + content_dir +       # Content dir
            r'p-' + series_id + r'/' +      # Series
            season + r'/' +                 # Season
            r'(?P<id>[0-9]+)/"' +           # Episode
            r'.+title="(?P<title>.+)"'      # Title
            , webpage))
            # , 'Episode list')
        print('playlist:', playlist)

        entries = []
        content_dir = r'https://www.' + DOMAIN + content_dir
        for season, video_id, title in playlist if not playlist_season else map(lambda episode: (playlist_season,) + episode, playlist):
            entries.append(self.url_result(
                content_dir + season + r'/' + video_id + r'/',
                ie='Generic',
                video_id=video_id,
                video_title=title,
                ))

        return {
            '_type': 'playlist',
            'id': series_id,
            'title': series_title,
            'entries': entries,
            }