youtube-dl/youtube_dl/extractor/byutv.py

from __future__ import unicode_literals

import re

from .common import InfoExtractor
from ..utils import ExtractorError


class BYUtvIE(InfoExtractor):
    _VALID_URL = r'^https?://(?:www\.)?byutv.org/watch/[0-9a-f-]+/(?P<id>[^/?#]+)'
    _TEST = {
        'url': 'http://www.byutv.org/watch/6587b9a3-89d2-42a6-a7f7-fd2f81840a7d/studio-c-season-5-episode-5',
        'md5': '05850eb8c749e2ee05ad5a1c34668493',
        'info_dict': {
            'id': 'studio-c-season-5-episode-5',
            'ext': 'mp4',
            'description': 'md5:e07269172baff037f8e8bf9956bc9747',
            'title': 'Season 5 Episode 5',
            'thumbnail': 're:^https?://.*\.jpg$',
            'duration': 1486.486,
        },
        'params': {
            'skip_download': True,
        },
        'add_ie': ['Ooyala'],
    }

    def _real_extract(self, url):
        video_id = self._match_id(url)

        webpage = self._download_webpage(url, video_id)
        episode_code = self._search_regex(
            r'(?s)episode:(.*?\}),\s*\n', webpage, 'episode information')

        ep = self._parse_json(
            episode_code, video_id, transform_source=lambda s:
            re.sub(r'(\n\s+)([a-zA-Z]+):\s+\'(.*?)\'', r'\1"\2": "\3"', s))

        if ep['providerType'] == 'Ooyala':
            return {
                '_type': 'url_transparent',
                'ie_key': 'Ooyala',
                'url': 'ooyala:%s' % ep['providerId'],
                'id': video_id,
                'title': ep['title'],
                'description': ep.get('description'),
                'thumbnail': ep.get('imageThumbnail'),
            }
        else:
            raise ExtractorError('Unsupported provider %s' % ep['provider'])