mirrors/yt-dlp
1
1
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-27 02:42:30 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

[kontrtube] Fix extraction (Closes #6644)

Browse Source
This commit is contained in:
Sergey M․ 2015-08-23 21:43:28 +06:00
parent 2b6bda1ed8
commit 2006a06eff
1 changed files with 19 additions and 21 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

40
youtube_dl/extractor/kontrtube.py
View File

@ -4,7 +4,10 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none from ..utils import (
int_or_none,
parse_duration,
)
class KontrTubeIE(InfoExtractor): class KontrTubeIE(InfoExtractor):
@ -34,33 +37,28 @@ def _real_extract(self, url):
webpage = self._download_webpage( webpage = self._download_webpage(
url, display_id, 'Downloading page') url, display_id, 'Downloading page')
video_url = self._html_search_regex( video_url = self._search_regex(
r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL') r"video_url\s*:\s*'(.+?)/?',", webpage, 'video URL')
thumbnail = self._html_search_regex( thumbnail = self._search_regex(
r"preview_url\s*:\s*'(.+?)/?',", webpage, 'video thumbnail', fatal=False) r"preview_url\s*:\s*'(.+?)/?',", webpage, 'thumbnail', fatal=False)
title = self._html_search_regex( title = self._html_search_regex(
r'<title>(.+?)</title>', webpage, 'video title') r'(?s)<h2>(.+?)</h2>', webpage, 'title')
description = self._html_search_meta( description = self._html_search_meta(
'description', webpage, 'video description') 'description', webpage, 'description')
mobj = re.search( duration = self._search_regex(
r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', r'Длительность: <em>([^<]+)</em>', webpage, 'duration', fatal=False)
webpage) if duration:
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None duration = parse_duration(duration.replace('мин', 'min').replace('сек', 'sec'))
view_count = self._html_search_regex( view_count = self._search_regex(
r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', r'Просмотров: <em>([^<]+)</em>',
webpage, 'view count', fatal=False) webpage, 'view count', fatal=False)
if view_count:
view_count = int_or_none(view_count.replace(' ', ''))
comment_count = None comment_count = int_or_none(self._search_regex(
comment_str = self._html_search_regex( r'Комментарии \((\d+)\)<', webpage, ' comment count', fatal=False))
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:
comment_count = mobj.group('total')
return { return {
'id': video_id, 'id': video_id,