mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-26 08:31:03 +01:00
80 lines
2.9 KiB
Python
80 lines
2.9 KiB
Python
# encoding: utf-8
|
||
from __future__ import unicode_literals
|
||
|
||
from .common import InfoExtractor
|
||
from ..compat import compat_urlparse
|
||
from ..utils import (
|
||
int_or_none,
|
||
qualities,
|
||
unified_strdate,
|
||
)
|
||
|
||
|
||
class FirstTVIE(InfoExtractor):
|
||
IE_NAME = '1tv'
|
||
IE_DESC = 'Первый канал'
|
||
_VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
|
||
|
||
_TESTS = [{
|
||
'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
|
||
'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
|
||
'info_dict': {
|
||
'id': '40049',
|
||
'ext': 'mp4',
|
||
'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
|
||
'description': 'md5:36a39c1d19618fec57d12efe212a8370',
|
||
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
|
||
'upload_date': '20150212',
|
||
'duration': 2694,
|
||
},
|
||
}, {
|
||
'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
|
||
'only_matching': 'true',
|
||
}]
|
||
|
||
def _real_extract(self, url):
|
||
display_id = self._match_id(url)
|
||
|
||
webpage = self._download_webpage(url, display_id)
|
||
playlist_url = compat_urlparse.urljoin(url, self._search_regex(
|
||
r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
|
||
|
||
item = self._download_json(playlist_url, display_id)[0]
|
||
video_id = item['id']
|
||
quality = qualities(('ld', 'sd', 'hd', ))
|
||
formats = []
|
||
for f in item.get('mbr', []):
|
||
src = f.get('src')
|
||
if not src:
|
||
continue
|
||
fname = f.get('name')
|
||
formats.append({
|
||
'url': src,
|
||
'format_id': fname,
|
||
'quality': quality(fname),
|
||
})
|
||
self._sort_formats(formats)
|
||
|
||
title = self._html_search_regex(
|
||
(r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
|
||
r"'title'\s*:\s*'([^']+)'"),
|
||
webpage, 'title', default=None) or item['title']
|
||
description = self._html_search_regex(
|
||
r'<div class="descr">\s*<div> </div>\s*<p>([^<]*)</p></div>',
|
||
webpage, 'description', default=None) or self._html_search_meta(
|
||
'description', webpage, 'description')
|
||
duration = int_or_none(self._html_search_meta(
|
||
'video:duration', webpage, 'video duration', fatal=False))
|
||
upload_date = unified_strdate(self._html_search_meta(
|
||
'ya:ovs:upload_date', webpage, 'upload date', fatal=False))
|
||
|
||
return {
|
||
'id': video_id,
|
||
'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
|
||
'title': title,
|
||
'description': description,
|
||
'upload_date': upload_date,
|
||
'duration': int_or_none(duration),
|
||
'formats': formats
|
||
}
|