1
0
mirror of https://github.com/l1ving/youtube-dl synced 2024-12-05 10:19:30 +08:00
youtube-dl/youtube_dl/extractor/kontrtube.py

67 lines
2.7 KiB
Python
Raw Normal View History

# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-03-21 00:05:57 +08:00
from ..utils import int_or_none
class KontrTubeIE(InfoExtractor):
IE_NAME = 'kontrtube'
IE_DESC = 'KontrTube.ru - Труба зовёт'
_VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P<id>\d+)/.+'
_TEST = {
'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/',
'md5': '975a991a4926c9a85f383a736a2e6b80',
'info_dict': {
'id': '2678',
'ext': 'mp4',
'title': 'Над олимпийской деревней в Сочи поднят российский флаг',
'description': 'md5:80edc4c613d5887ae8ccf1d59432be41',
'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg',
'duration': 270,
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id, 'Downloading page')
video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
2014-03-21 00:05:57 +08:00
title = self._html_search_regex(
2014-10-13 12:33:55 +08:00
r'<title>(.+?)</title>', webpage, 'video title')
description = self._html_search_meta('description', webpage, 'video description')
2014-03-21 00:05:57 +08:00
mobj = re.search(
r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
2014-03-21 00:05:57 +08:00
view_count = self._html_search_regex(
r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
comment_count = None
2014-03-21 00:05:57 +08:00
comment_str = self._html_search_regex(
r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', fatal=False)
if comment_str.startswith('комментариев нет'):
comment_count = 0
else:
mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
if mobj:
2014-03-21 00:05:57 +08:00
comment_count = mobj.group('total')
return {
'id': video_id,
'url': video_url,
'thumbnail': thumbnail,
'title': title,
'description': description,
'duration': duration,
2014-03-21 00:05:57 +08:00
'view_count': int_or_none(view_count),
'comment_count': int_or_none(comment_count),
2014-11-24 03:41:03 +08:00
}