0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 03:03:01 +00:00
yt-dlp/yt_dlp/extractor/videopress.py
sepro add96eb9f8
[cleanup] Add more ruff rules (#10149)
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
2024-06-12 01:09:58 +02:00

89 lines
3.1 KiB
Python

from .common import InfoExtractor
from ..utils import (
determine_ext,
float_or_none,
int_or_none,
parse_age_limit,
qualities,
random_birthday,
unified_timestamp,
urljoin,
)
class VideoPressIE(InfoExtractor):
_ID_REGEX = r'[\da-zA-Z]{8}'
_PATH_REGEX = r'video(?:\.word)?press\.com/embed/'
_VALID_URL = rf'https?://{_PATH_REGEX}(?P<id>{_ID_REGEX})'
_EMBED_REGEX = [rf'<iframe[^>]+src=["\'](?P<url>(?:https?://)?{_PATH_REGEX}{_ID_REGEX})']
_TESTS = [{
'url': 'https://videopress.com/embed/kUJmAcSf',
'md5': '706956a6c875873d51010921310e4bc6',
'info_dict': {
'id': 'kUJmAcSf',
'ext': 'mp4',
'title': 'VideoPress Demo',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 634.6,
'timestamp': 1434983935,
'upload_date': '20150622',
'age_limit': 0,
},
}, {
# 17+, requires birth_* params
'url': 'https://videopress.com/embed/iH3gstfZ',
'only_matching': True,
}, {
'url': 'https://video.wordpress.com/embed/kUJmAcSf',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
query = random_birthday('birth_year', 'birth_month', 'birth_day')
query['fields'] = 'description,duration,file_url_base,files,height,original,poster,rating,title,upload_date,width'
video = self._download_json(
f'https://public-api.wordpress.com/rest/v1.1/videos/{video_id}',
video_id, query=query)
title = video['title']
file_url_base = video.get('file_url_base') or {}
base_url = file_url_base.get('https') or file_url_base.get('http')
QUALITIES = ('std', 'dvd', 'hd')
quality = qualities(QUALITIES)
formats = []
for format_id, f in (video.get('files') or {}).items():
if not isinstance(f, dict):
continue
for ext, path in f.items():
if ext in ('mp4', 'ogg'):
formats.append({
'url': urljoin(base_url, path),
'format_id': f'{format_id}-{ext}',
'ext': determine_ext(path, ext),
'quality': quality(format_id),
})
original_url = video.get('original')
if original_url:
formats.append({
'url': original_url,
'format_id': 'original',
'quality': len(QUALITIES),
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
})
return {
'id': video_id,
'title': title,
'description': video.get('description'),
'thumbnail': video.get('poster'),
'duration': float_or_none(video.get('duration'), 1000),
'timestamp': unified_timestamp(video.get('upload_date')),
'age_limit': parse_age_limit(video.get('rating')),
'formats': formats,
}