youtube-dl/youtube_dl/extractor/twentythreevideo.py

81 lines
3.2 KiB
Python
Raw Permalink Normal View History

2016-08-17 16:02:59 +02:00
from __future__ import unicode_literals
2017-12-26 19:41:08 +01:00
import re
2016-08-17 16:02:59 +02:00
from .common import InfoExtractor
2017-12-26 19:41:08 +01:00
from ..utils import int_or_none
2016-08-17 16:02:59 +02:00
class TwentyThreeVideoIE(InfoExtractor):
IE_NAME = '23video'
2020-10-19 19:56:23 +02:00
_VALID_URL = r'https?://(?P<domain>[^.]+\.(?:twentythree\.net|23video\.com|filmweb\.no))/v\.ihtml/player\.html\?(?P<query>.*?\bphoto(?:_|%5f)id=(?P<id>\d+).*)'
_TESTS = [{
2017-12-26 19:41:08 +01:00
'url': 'https://video.twentythree.net/v.ihtml/player.html?showDescriptions=0&source=site&photo%5fid=20448876&autoPlay=1',
'md5': '75fcf216303eb1dae9920d651f85ced4',
'info_dict': {
'id': '20448876',
'ext': 'mp4',
'title': 'Video Marketing Minute: Personalized Video',
'timestamp': 1513855354,
'upload_date': '20171221',
'uploader_id': '12258964',
'uploader': 'Rasmus Bysted',
2016-08-17 16:02:59 +02:00
}
2020-10-19 19:56:23 +02:00
}, {
'url': 'https://bonnier-publications-danmark.23video.com/v.ihtml/player.html?token=f0dc46476e06e13afd5a1f84a29e31e8&source=embed&photo%5fid=36137620',
'only_matching': True,
}]
2016-08-17 16:02:59 +02:00
2017-12-26 19:41:08 +01:00
def _real_extract(self, url):
domain, query, photo_id = re.match(self._VALID_URL, url).groups()
2020-10-19 19:56:23 +02:00
base_url = 'https://%s' % domain
2017-12-26 19:41:08 +01:00
photo_data = self._download_json(
base_url + '/api/photo/list?' + query, photo_id, query={
'format': 'json',
}, transform_source=lambda s: self._search_regex(r'(?s)({.+})', s, 'photo data'))['photo']
title = photo_data['title']
2016-08-17 16:02:59 +02:00
formats = []
2017-12-26 19:41:08 +01:00
audio_path = photo_data.get('audio_download')
if audio_path:
2016-08-17 16:02:59 +02:00
formats.append({
2017-12-26 19:41:08 +01:00
'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')),
2016-08-17 16:02:59 +02:00
})
2017-12-26 19:41:08 +01:00
for f in ('mobile_high', 'medium', 'hd', '1080p', '4k'):
add_common_info_to_list(formats, 'video_%s_', 'format_id', f)
2016-08-17 16:02:59 +02:00
2017-12-26 19:41:08 +01:00
thumbnails = []
for t in ('quad16', 'quad50', 'quad75', 'quad100', 'small', 'portrait', 'standard', 'medium', 'large', 'original'):
add_common_info_to_list(thumbnails, '%s_', 'id', t)
return {
'id': photo_id,
'title': title,
'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,
}