Yt-DLP plugin for detandreteatret / 23video.com

twentythreevideoex.py

# coding: utf-8

from __future__ import unicode_literals

import re

# ⚠ Don't use relative imports
from yt_dlp.extractor.common import InfoExtractor
from yt_dlp.utils import int_or_none, try_get, clean_html, unescapeHTML

class TwentyThreeVideoExIE(InfoExtractor):
    IE_NAME = '23videoEx'
    _VALID_URL = r'https?://(?P<domain>[^.]+\.(?:twentythree\.net|23video\.com))/video/(?P<id>\d+)(?:/[A-Za-z0-9\-_]*)?'
    _TESTS = [{
        'url': 'https://detandreteatret.23video.com/video/7742017/murder-she-improvised-en-ganske',
        'info_dict': {
            'id': '7742017',
            'ext': 'mp4',
            'title': 'Murder, she Improvised  - en ganske grundig forklaring',
            'upload_date': '20130212',
        }
    }]

    def _real_extract(self, url):
        domain, photo_id = self._match_valid_url(url).groups()
        base_url = 'https://%s' % domain
        photo_data = self._download_json(
            base_url + '/api/photo/list', photo_id, query={
                'format': 'json',
                'photo_id': photo_id
            }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo']
        title = photo_data['title']

        formats = []

        audio_path = photo_data.get('audio_download')
        if audio_path:
            formats.append({
                'format_id': 'audio',
                'url': base_url + audio_path,
                'filesize': int_or_none(photo_data.get('audio_size')),
                'vcodec': 'none',
            })

        def add_common_info_to_list(l, template, id_field, id_value):
            f_base = template % id_value
            f_path = photo_data.get(f_base + 'download')
            if not f_path:
                return
            l.append({
                id_field: id_value,
                'url': base_url + f_path,
                'width': int_or_none(photo_data.get(f_base + 'width')),
                'height': int_or_none(photo_data.get(f_base + 'height')),
                'filesize': int_or_none(photo_data.get(f_base + 'size')),
            })

        for f in ('mobile_high', 'medium', 'hd', '1080p', '4k'):
            add_common_info_to_list(formats, 'video_%s_', 'format_id', f)

        thumbnails = []
        for t in ('quad16', 'quad50', 'quad75', 'quad100', 'small', 'portrait', 'standard', 'medium', 'large', 'original'):
            add_common_info_to_list(thumbnails, '%s_', 'id', t)

        tags = try_get(photo_data, lambda x: x['tags'], list)

        description = clean_html(unescapeHTML(photo_data.get('content_text')))

        return {
            'id': photo_id,
            'title': title,
            'description': description,
            'timestamp': int_or_none(photo_data.get('creation_date_epoch')),
            'duration': int_or_none(photo_data.get('video_length')),
            'view_count': int_or_none(photo_data.get('view_count')),
            'comment_count': int_or_none(photo_data.get('number_of_comments')),
            'uploader_id': photo_data.get('user_id'),
            'uploader': photo_data.get('display_name'),
            'thumbnails': thumbnails,
            'formats': formats,
            'tags': tags
        }

class TwentyThreeVideoAlbumExIE(InfoExtractor):
    IE_NAME = '23VideoAlbumEx'
    _VALID_URL = r'https?://(?P<domain>[^.]+\.(?:twentythree\.net|23video\.com))/channel/(?P<id>\d+)(?:/[A-Za-z0-9\-_]*)?'
    _TESTS = [{
        'url': 'https://detandreteatret.23video.com/channel/7742261/forestillinger',
        'info_dict': {
            'id': '7742261',
            'title': 'Forestillinger'
        }
    }]

    def _real_extract(self, url):
        domain, album_id = self._match_valid_url(url).groups()
        base_url = 'https://%s' % domain

        album_info = self._download_json(
            base_url + '/api/album/list', album_id, query={
                'format': 'json',
                'album_id': album_id
            }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'album data'))['album']

        album_data = self._download_json(
            base_url + '/api/photo/list', album_id, query={
                'format': 'json',
                'album_id': album_id,
                'size': 100,
            }, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'album data'))['photos']
        

        title = album_info['title']
        
        entries = [self.url_result(base_url + item['one']) for item in album_data]
        return self.playlist_result(entries, album_id, title)