youtube-dl/youtube_dl/extractor/lifenews.py

69 lines
2.6 KiB
Python
Raw Normal View History

2014-01-30 21:48:00 +01:00
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-02-10 15:07:41 +01:00
from ..utils import (
int_or_none,
unified_strdate
)
2014-01-30 21:48:00 +01:00
class LifeNewsIE(InfoExtractor):
IE_NAME = 'lifenews'
IE_DESC = 'LIFE | NEWS'
_VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
2014-02-10 15:07:41 +01:00
2014-01-30 21:48:00 +01:00
_TEST = {
'url': 'http://lifenews.ru/news/126342',
'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
'info_dict': {
2014-02-10 15:07:41 +01:00
'id': '126342',
'ext': 'mp4',
2014-01-31 19:10:15 +01:00
'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
2014-01-30 21:48:00 +01:00
'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
'upload_date': '20140130',
}
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group('id')
webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
2014-01-30 21:48:00 +01:00
video_url = self._html_search_regex(
r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
2014-02-10 15:07:41 +01:00
2014-01-30 21:48:00 +01:00
thumbnail = self._html_search_regex(
r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
title = self._og_search_title(webpage)
TITLE_SUFFIX = ' - Первый по срочным новостям — LIFE | NEWS'
if title.endswith(TITLE_SUFFIX):
title = title[:-len(TITLE_SUFFIX)]
description = self._og_search_description(webpage)
view_count = self._html_search_regex(
2014-02-10 15:07:41 +01:00
r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
2014-01-30 21:48:00 +01:00
comment_count = self._html_search_regex(
r'<div class=\'comments\'>\s*<span class=\'counter\'>(\d+)</span>', webpage, 'comment count', fatal=False)
2014-01-30 21:48:00 +01:00
upload_date = self._html_search_regex(
2014-02-10 15:07:41 +01:00
r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False)
if upload_date is not None:
upload_date = unified_strdate(upload_date)
2014-01-30 21:48:00 +01:00
return {
'id': video_id,
'url': video_url,
'thumbnail': thumbnail,
'title': title,
'description': description,
2014-02-10 15:07:41 +01:00
'view_count': int_or_none(view_count),
'comment_count': int_or_none(comment_count),
'upload_date': upload_date,
2014-01-30 21:48:00 +01:00
}