youtube-dl/youtube_dl/extractor/firsttv.py

80 lines
2.9 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
2016-08-21 18:55:47 +02:00
from ..compat import compat_urlparse
2016-04-09 23:02:35 +02:00
from ..utils import (
int_or_none,
qualities,
unified_strdate,
)
class FirstTVIE(InfoExtractor):
2015-02-13 21:04:28 +01:00
IE_NAME = '1tv'
IE_DESC = 'Первый канал'
2016-08-21 18:55:47 +02:00
_VALID_URL = r'https?://(?:www\.)?1tv\.ru/(?:[^/]+/)+(?P<id>[^/?#]+)'
2015-02-13 21:04:28 +01:00
_TESTS = [{
2016-08-21 18:55:47 +02:00
'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': {
2016-08-21 18:55:47 +02:00
'id': '40049',
'ext': 'mp4',
2016-04-09 23:02:35 +02:00
'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
2016-08-21 18:55:47 +02:00
'description': 'md5:36a39c1d19618fec57d12efe212a8370',
2015-02-13 21:04:28 +01:00
'thumbnail': 're:^https?://.*\.(?:jpg|JPG)$',
2016-04-09 23:02:35 +02:00
'upload_date': '20150212',
'duration': 2694,
2014-02-11 04:26:52 +01:00
},
2015-02-13 21:04:28 +01:00
}, {
2016-08-21 18:55:47 +02:00
'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
'only_matching': 'true',
2015-02-13 21:04:28 +01:00
}]
def _real_extract(self, url):
2016-08-21 18:55:47 +02:00
display_id = self._match_id(url)
2016-08-21 18:55:47 +02:00
webpage = self._download_webpage(url, display_id)
playlist_url = compat_urlparse.urljoin(url, self._search_regex(
r'data-playlist-url="([^"]+)', webpage, 'playlist url'))
2016-08-21 18:55:47 +02:00
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),
})
2016-04-09 23:02:35 +02:00
self._sort_formats(formats)
2016-08-21 18:55:47 +02:00
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>&nbsp;</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,
2016-08-21 18:55:47 +02:00
'thumbnail': item.get('poster') or self._og_search_thumbnail(webpage),
'title': title,
'description': description,
2016-04-09 23:02:35 +02:00
'upload_date': upload_date,
'duration': int_or_none(duration),
2016-04-09 23:02:35 +02:00
'formats': formats
2014-11-23 20:41:03 +01:00
}