2014-01-31 04:48:00 +08:00
|
|
|
|
# encoding: utf-8
|
|
|
|
|
from __future__ import unicode_literals
|
|
|
|
|
|
|
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
2014-02-10 22:07:41 +08:00
|
|
|
|
from ..utils import (
|
|
|
|
|
int_or_none,
|
2014-02-28 23:52:06 +08:00
|
|
|
|
unified_strdate,
|
|
|
|
|
ExtractorError,
|
2014-02-10 22:07:41 +08:00
|
|
|
|
)
|
2014-01-31 04:48:00 +08:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
class LifeNewsIE(InfoExtractor):
|
|
|
|
|
IE_NAME = 'lifenews'
|
|
|
|
|
IE_DESC = 'LIFE | NEWS'
|
|
|
|
|
_VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
|
2014-02-10 22:07:41 +08:00
|
|
|
|
|
2015-05-04 01:24:19 +08:00
|
|
|
|
_TESTS = [{
|
2014-01-31 04:48:00 +08:00
|
|
|
|
'url': 'http://lifenews.ru/news/126342',
|
|
|
|
|
'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
|
|
|
|
|
'info_dict': {
|
2014-02-10 22:07:41 +08:00
|
|
|
|
'id': '126342',
|
|
|
|
|
'ext': 'mp4',
|
2014-02-01 02:10:15 +08:00
|
|
|
|
'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
|
2014-01-31 04:48:00 +08:00
|
|
|
|
'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
|
2014-06-19 22:34:48 +08:00
|
|
|
|
'thumbnail': 're:http://.*\.jpg',
|
2014-01-31 04:48:00 +08:00
|
|
|
|
'upload_date': '20140130',
|
|
|
|
|
}
|
2015-05-04 01:24:19 +08:00
|
|
|
|
}, {
|
|
|
|
|
# video in <iframe>
|
|
|
|
|
'url': 'http://lifenews.ru/news/152125',
|
|
|
|
|
'md5': '77d19a6f0886cd76bdbf44b4d971a273',
|
|
|
|
|
'info_dict': {
|
|
|
|
|
'id': '152125',
|
|
|
|
|
'ext': 'mp4',
|
|
|
|
|
'title': 'В Сети появилось видео захвата «Правым сектором» колхозных полей ',
|
|
|
|
|
'description': 'Жители двух поселков Днепропетровской области не простили радикалам угрозу лишения плодородных земель и пошли в лобовую. ',
|
|
|
|
|
'upload_date': '20150402',
|
|
|
|
|
'uploader': 'embed.life.ru',
|
|
|
|
|
}
|
|
|
|
|
}]
|
2014-01-31 04:48:00 +08:00
|
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
|
video_id = mobj.group('id')
|
|
|
|
|
|
2014-02-27 22:45:34 +08:00
|
|
|
|
webpage = self._download_webpage('http://lifenews.ru/news/%s' % video_id, video_id, 'Downloading page')
|
2014-01-31 04:48:00 +08:00
|
|
|
|
|
2014-02-28 23:52:06 +08:00
|
|
|
|
videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
|
2015-05-04 01:24:19 +08:00
|
|
|
|
iframe_link = self._html_search_regex(
|
|
|
|
|
'<iframe[^>]+src="([^"]+)', webpage, 'iframe link', default=None)
|
|
|
|
|
if not videos and not iframe_link:
|
2014-02-28 23:52:06 +08:00
|
|
|
|
raise ExtractorError('No media links available for %s' % video_id)
|
2014-01-31 04:48:00 +08:00
|
|
|
|
|
|
|
|
|
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(
|
2015-05-04 01:11:23 +08:00
|
|
|
|
r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
|
2014-01-31 04:48:00 +08:00
|
|
|
|
comment_count = self._html_search_regex(
|
2015-05-04 01:11:23 +08:00
|
|
|
|
r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
|
2014-01-31 04:48:00 +08:00
|
|
|
|
|
|
|
|
|
upload_date = self._html_search_regex(
|
2014-11-24 03:41:03 +08:00
|
|
|
|
r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
|
2014-02-10 22:07:41 +08:00
|
|
|
|
if upload_date is not None:
|
|
|
|
|
upload_date = unified_strdate(upload_date)
|
2014-01-31 04:48:00 +08:00
|
|
|
|
|
2015-05-04 01:24:19 +08:00
|
|
|
|
common_info = {
|
|
|
|
|
'description': description,
|
|
|
|
|
'view_count': int_or_none(view_count),
|
|
|
|
|
'comment_count': int_or_none(comment_count),
|
|
|
|
|
'upload_date': upload_date,
|
|
|
|
|
}
|
|
|
|
|
|
2014-02-28 23:52:06 +08:00
|
|
|
|
def make_entry(video_id, media, video_number=None):
|
2015-05-04 01:24:19 +08:00
|
|
|
|
cur_info = dict(common_info)
|
|
|
|
|
cur_info.update({
|
2014-02-28 23:52:06 +08:00
|
|
|
|
'id': video_id,
|
|
|
|
|
'url': media[1],
|
|
|
|
|
'thumbnail': media[0],
|
|
|
|
|
'title': title if video_number is None else '%s-video%s' % (title, video_number),
|
2015-05-04 01:24:19 +08:00
|
|
|
|
})
|
|
|
|
|
return cur_info
|
|
|
|
|
|
|
|
|
|
if iframe_link:
|
|
|
|
|
cur_info = dict(common_info)
|
|
|
|
|
cur_info.update({
|
|
|
|
|
'_type': 'url_transparent',
|
|
|
|
|
'id': video_id,
|
|
|
|
|
'title': title,
|
|
|
|
|
'url': iframe_link,
|
|
|
|
|
})
|
|
|
|
|
return cur_info
|
2014-02-28 23:52:06 +08:00
|
|
|
|
|
|
|
|
|
if len(videos) == 1:
|
|
|
|
|
return make_entry(video_id, videos[0])
|
|
|
|
|
else:
|
2014-11-24 04:23:05 +08:00
|
|
|
|
return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)]
|