Archives/yt-dlp
2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-19 09:25:43 +00:00
Code Issues Projects Releases Wiki Activity

[lifenews] Minor improvements

Browse Source
This commit is contained in:
Sergey M. 2014-02-10 21:07:41 +07:00
parent ac6e4ca1ed
commit bcb891e82b
1 changed files with 16 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

26
youtube_dl/extractor/lifenews.py
View File

@ -4,19 +4,23 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import unified_strdate from ..utils import (
int_or_none,
unified_strdate
)
class LifeNewsIE(InfoExtractor): class LifeNewsIE(InfoExtractor):
IE_NAME = 'lifenews' IE_NAME = 'lifenews'
IE_DESC = 'LIFE | NEWS' IE_DESC = 'LIFE | NEWS'
_VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)' _VALID_URL = r'http://lifenews\.ru/(?:mobile/)?news/(?P<id>\d+)'
_TEST = { _TEST = {
'url': 'http://lifenews.ru/news/126342', 'url': 'http://lifenews.ru/news/126342',
'file': '126342.mp4',
'md5': 'e1b50a5c5fb98a6a544250f2e0db570a', 'md5': 'e1b50a5c5fb98a6a544250f2e0db570a',
'info_dict': { 'info_dict': {
'id': '126342',
'ext': 'mp4',
'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом', 'title': 'МВД разыскивает мужчин, оставивших в IKEA сумку с автоматом',
'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.', 'description': 'Камеры наблюдения гипермаркета зафиксировали троих мужчин, спрятавших оружейный арсенал в камере хранения.',
'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg', 'thumbnail': 'http://lifenews.ru/static/posts/2014/1/126342/.video.jpg',
@ -32,7 +36,7 @@ def _real_extract(self, url):
video_url = self._html_search_regex( video_url = self._html_search_regex(
r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL') r'<video.*?src="([^"]+)".*?></video>', webpage, 'video URL')
thumbnail = self._html_search_regex( thumbnail = self._html_search_regex(
r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail') r'<video.*?poster="([^"]+)".*?"></video>', webpage, 'video thumbnail')
@ -44,12 +48,14 @@ def _real_extract(self, url):
description = self._og_search_description(webpage) description = self._og_search_description(webpage)
view_count = self._html_search_regex( view_count = self._html_search_regex(
r'<div class=\'views\'>(\d+)</div>', webpage, 'view count') r'<div class=\'views\'>(\d+)</div>', webpage, 'view count', fatal=False)
comment_count = self._html_search_regex( comment_count = self._html_search_regex(
r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count') r'<div class=\'comments\'>(\d+)</div>', webpage, 'comment count', fatal=False)
upload_date = self._html_search_regex( upload_date = self._html_search_regex(
r'<time datetime=\'([^\']+)\'>', webpage, 'upload date') r'<time datetime=\'([^\']+)\'>', webpage, 'upload date',fatal=False)
if upload_date is not None:
upload_date = unified_strdate(upload_date)
return { return {
'id': video_id, 'id': video_id,
@ -57,7 +63,7 @@ def _real_extract(self, url):
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'title': title, 'title': title,
'description': description, 'description': description,
'view_count': view_count, 'view_count': int_or_none(view_count),
'comment_count': comment_count, 'comment_count': int_or_none(comment_count),
'upload_date': unified_strdate(upload_date), 'upload_date': upload_date,
} }