youtube-dl/youtube_dl/extractor/lifenews.py

104 lines
4.1 KiB
Python
Raw Normal View History

2014-01-30 20:48:00 +00:00
# encoding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
2014-02-10 14:07:41 +00:00
from ..utils import (
int_or_none,
unified_strdate,
ExtractorError,
2014-02-10 14:07:41 +00:00
)
2014-01-30 20:48:00 +00:00
class LifeNewsIE(InfoExtractor):
IE_NAME = 'lifenews'
IE_DESC = 'LIFE | NEWS'
_VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
2014-02-10 14:07:41 +00:00
_TESTS = [{
2014-01-30 20:48:00 +00:00
'url': 'http://lifenews.ru/news/126342',
'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
'info_dict': {
2014-02-10 14:07:41 +00:00
'id': '126342',
'ext': 'mp4',
2014-01-31 18:10:15 +00:00
'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
2014-01-30 20:48:00 +00:00
'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
2014-06-19 15:34:48 +01:00
'thumbnail': 're:http://.*\.jpg',
2014-01-30 20:48:00 +00:00
'upload_date': '20140130',
}
}, {
# 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',
}
}]
2014-01-30 20:48:00 +00:00
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 20:48:00 +00:00
videos = re.findall(r'<video.*?poster="(?P<poster>[^"]+)".*?src="(?P<video>[^"]+)".*?></video>', webpage)
iframe_link = self._html_search_regex(
'<iframe[^>]+src="([^"]+)', webpage, 'iframe link', default=None)
if not videos and not iframe_link:
raise ExtractorError('No media links available for %s' % video_id)
2014-01-30 20:48:00 +00:00
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(
r'<div class=\'views\'>\s*(\d+)\s*</div>', webpage, 'view count', fatal=False)
2014-01-30 20:48:00 +00:00
comment_count = self._html_search_regex(
r'<div class=\'comments\'>\s*<span class=\'counter\'>\s*(\d+)\s*</span>', webpage, 'comment count', fatal=False)
2014-01-30 20:48:00 +00:00
upload_date = self._html_search_regex(
2014-11-23 19:41:03 +00:00
r'<time datetime=\'([^\']+)\'>', webpage, 'upload date', fatal=False)
2014-02-10 14:07:41 +00:00
if upload_date is not None:
upload_date = unified_strdate(upload_date)
2014-01-30 20:48:00 +00:00
common_info = {
'description': description,
'view_count': int_or_none(view_count),
'comment_count': int_or_none(comment_count),
'upload_date': upload_date,
}
def make_entry(video_id, media, video_number=None):
cur_info = dict(common_info)
cur_info.update({
'id': video_id,
'url': media[1],
'thumbnail': media[0],
'title': title if video_number is None else '%s-video%s' % (title, video_number),
})
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
if len(videos) == 1:
return make_entry(video_id, videos[0])
else:
2014-11-23 20:23:05 +00:00
return [make_entry(video_id, media, video_number + 1) for video_number, media in enumerate(videos)]