etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-04 23:35:04 +00:00
Code Issues Projects Releases Wiki Activity

[kontrtube] Modernize

Browse source
This commit is contained in:
Sergey M․ 2014-03-20 23:05:57 +07:00
parent 627a209f74
commit bc2bdf5709
1 changed files with 12 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
youtube_dl/extractor/kontrtube.py
View file

@ -4,6 +4,7 @@
import re import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import int_or_none
class KontrTubeIE(InfoExtractor): class KontrTubeIE(InfoExtractor):
@ -32,27 +33,26 @@ def _real_extract(self, url):
video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL') video_url = self._html_search_regex(r"video_url: '(.+?)/?',", webpage, 'video URL')
thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False) thumbnail = self._html_search_regex(r"preview_url: '(.+?)/?',", webpage, 'video thumbnail', fatal=False)
title = self._html_search_regex(r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage, title = self._html_search_regex(
'video title') r'<title>(.+?) - Труба зовёт - Интересный видеохостинг</title>', webpage, 'video title')
description = self._html_search_meta('description', webpage, 'video description') description = self._html_search_meta('description', webpage, 'video description')
mobj = re.search(r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', mobj = re.search(
webpage) r'<div class="col_2">Длительность: <span>(?P<minutes>\d+)м:(?P<seconds>\d+)с</span></div>', webpage)
duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None
view_count = self._html_search_regex(r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, view_count = self._html_search_regex(
'view count', fatal=False) r'<div class="col_2">Просмотров: <span>(\d+)</span></div>', webpage, 'view count', fatal=False)
view_count = int(view_count) if view_count is not None else None
comment_count = None comment_count = None
comment_str = self._html_search_regex(r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', comment_str = self._html_search_regex(
fatal=False) r'Комментарии: <span>([^<]+)</span>', webpage, 'comment count', fatal=False)
if comment_str.startswith('комментариев нет'): if comment_str.startswith('комментариев нет'):
comment_count = 0 comment_count = 0
else: else:
mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str) mobj = re.search(r'\d+ из (?P<total>\d+) комментариев', comment_str)
if mobj: if mobj:
comment_count = int(mobj.group('total')) comment_count = mobj.group('total')
return { return {
'id': video_id, 'id': video_id,
@ -61,6 +61,6 @@ def _real_extract(self, url):
'title': title, 'title': title,
'description': description, 'description': description,
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': int_or_none(view_count),
'comment_count': comment_count, 'comment_count': int_or_none(comment_count),
} }