1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-18 00:45:03 +01:00
yt-dlp/yt_dlp/extractor/tass.py
pukkandan 86e5f3ed2e
[cleanup] Upgrade syntax
Using https://github.com/asottile/pyupgrade

1. `__future__` imports and `coding: utf-8` were removed
2. Files were rewritten with `pyupgrade --py36-plus --keep-percent-format`
3. f-strings were cherry-picked from `pyupgrade --py36-plus`

Extractors are left untouched (except removing header) to avoid unnecessary merge conflicts
2022-04-12 05:32:51 +05:30

60 lines
1.9 KiB
Python

import json
from .common import InfoExtractor
from ..utils import (
js_to_json,
qualities,
)
class TassIE(InfoExtractor):
_VALID_URL = r'https?://(?:tass\.ru|itar-tass\.com)/[^/]+/(?P<id>\d+)'
_TESTS = [
{
'url': 'http://tass.ru/obschestvo/1586870',
'md5': '3b4cdd011bc59174596b6145cda474a4',
'info_dict': {
'id': '1586870',
'ext': 'mp4',
'title': 'Посетителям московского зоопарка показали красную панду',
'description': 'Приехавшую из Дублина Зейну можно увидеть в павильоне "Кошки тропиков"',
'thumbnail': r're:^https?://.*\.jpg$',
},
},
{
'url': 'http://itar-tass.com/obschestvo/1600009',
'only_matching': True,
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
sources = json.loads(js_to_json(self._search_regex(
r'(?s)sources\s*:\s*(\[.+?\])', webpage, 'sources')))
quality = qualities(['sd', 'hd'])
formats = []
for source in sources:
video_url = source.get('file')
if not video_url or not video_url.startswith('http') or not video_url.endswith('.mp4'):
continue
label = source.get('label')
formats.append({
'url': video_url,
'format_id': label,
'quality': quality(label),
})
self._sort_formats(formats)
return {
'id': video_id,
'title': self._og_search_title(webpage),
'description': self._og_search_description(webpage),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
}