From b542d4bbd7c620e35b2d61cf11827665372d8ff5 Mon Sep 17 00:00:00 2001 From: "Sergey M." Date: Sun, 9 Feb 2014 19:53:11 +0700 Subject: [PATCH] [kontrtube] Add support for kontrtube.ru (Closes #2354) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/kontrtube.py | 66 +++++++++++++++++++++++++++++++ 2 files changed, 67 insertions(+) create mode 100644 youtube_dl/extractor/kontrtube.py diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 4678cf06c7..e2a9294dd5 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -115,6 +115,7 @@ from .khanacademy import KhanAcademyIE from .kickstarter import KickStarterIE from .keek import KeekIE +from .kontrtube import KontrTubeIE from .la7 import LA7IE from .lifenews import LifeNewsIE from .liveleak import LiveLeakIE diff --git a/youtube_dl/extractor/kontrtube.py b/youtube_dl/extractor/kontrtube.py new file mode 100644 index 0000000000..1b45b67b05 --- /dev/null +++ b/youtube_dl/extractor/kontrtube.py @@ -0,0 +1,66 @@ +# encoding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor + + +class KontrTubeIE(InfoExtractor): + IE_NAME = 'kontrtube' + IE_DESC = 'KontrTube.ru - Труба зовёт' + _VALID_URL = r'http://(?:www\.)?kontrtube\.ru/videos/(?P\d+)/.+' + + _TEST = { + 'url': 'http://www.kontrtube.ru/videos/2678/nad-olimpiyskoy-derevney-v-sochi-podnyat-rossiyskiy-flag/', + 'md5': '975a991a4926c9a85f383a736a2e6b80', + 'info_dict': { + 'id': '2678', + 'ext': 'mp4', + 'title': 'Над олимпийской деревней в Сочи поднят российский флаг', + 'description': 'md5:80edc4c613d5887ae8ccf1d59432be41', + 'thumbnail': 'http://www.kontrtube.ru/contents/videos_screenshots/2000/2678/preview.mp4.jpg', + 'duration': 270, + } + } + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + video_id = mobj.group('id') + + webpage = self._download_webpage(url, video_id, 'Downloading page') + + 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) + title = self._html_search_regex(r'(.+?) - Труба зовёт - Интересный видеохостинг', webpage, + 'video title') + description = self._html_search_meta('description', webpage, 'video description') + + mobj = re.search(r'
Длительность: (?P\d+)м:(?P\d+)с
', + webpage) + duration = int(mobj.group('minutes')) * 60 + int(mobj.group('seconds')) if mobj else None + + view_count = self._html_search_regex(r'
Просмотров: (\d+)
', webpage, + 'view count', fatal=False) + view_count = int(view_count) if view_count is not None else None + + comment_count = None + comment_str = self._html_search_regex(r'Комментарии: ([^<]+)', webpage, 'comment count', + fatal=False) + if comment_str.startswith('комментариев нет'): + comment_count = 0 + else: + mobj = re.search(r'\d+ из (?P\d+) комментариев', comment_str) + if mobj: + comment_count = int(mobj.group('total')) + + return { + 'id': video_id, + 'url': video_url, + 'thumbnail': thumbnail, + 'title': title, + 'description': description, + 'duration': duration, + 'view_count': view_count, + 'comment_count': comment_count, + } \ No newline at end of file