yt-dlp/youtube_dl/extractor/rtbf.py

# coding: utf-8
from __future__ import unicode_literals

from .common import InfoExtractor
from ..utils import (
    int_or_none,
    unescapeHTML,
)


class RTBFIE(InfoExtractor):
    _VALID_URL = r'https?://www.rtbf.be/video/[^\?]+\?id=(?P<id>\d+)'
    _TEST = {
        'url': 'https://www.rtbf.be/video/detail_les-diables-au-coeur-episode-2?id=1921274',
        'md5': '799f334ddf2c0a582ba80c44655be570',
        'info_dict': {
            'id': '1921274',
            'ext': 'mp4',
            'title': 'Les Diables au coeur (épisode 2)',
            'duration': 3099,
        }
    }

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

        webpage = self._download_webpage(
            'http://www.rtbf.be/video/embed?id=%s' % video_id, video_id)

        data = self._parse_json(
            unescapeHTML(self._search_regex(
                r'data-video="([^"]+)"', webpage, 'data video')),
            video_id)

        video_url = data.get('downloadUrl') or data.get('url')

        if data.get('provider').lower() == 'youtube':
            return self.url_result(video_url, 'Youtube')

        return {
            'id': video_id,
            'url': video_url,
            'title': data['title'],
            'description': data.get('description') or data.get('subtitle'),
            'thumbnail': data.get('thumbnail'),
            'duration': data.get('duration') or data.get('realDuration'),
            'timestamp': int_or_none(data.get('created')),
            'view_count': int_or_none(data.get('viewCount')),
        }