From fc6861b175ec1ad1d7aa322438b095840c437249 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Sergey=20M=E2=80=A4?= Date: Thu, 9 Oct 2014 21:05:39 +0700 Subject: [sportbox] Add extractor (Closes #3906) --- youtube_dl/extractor/__init__.py | 1 + youtube_dl/extractor/sportbox.py | 81 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 82 insertions(+) create mode 100644 youtube_dl/extractor/sportbox.py (limited to 'youtube_dl') diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py index 76726305a..f96ddfd23 100644 --- a/youtube_dl/extractor/__init__.py +++ b/youtube_dl/extractor/__init__.py @@ -347,6 +347,7 @@ from .spiegel import SpiegelIE, SpiegelArticleIE from .spiegeltv import SpiegeltvIE from .spike import SpikeIE from .sport5 import Sport5IE +from .sportbox import SportBoxIE from .sportdeutschland import SportDeutschlandIE from .stanfordoc import StanfordOpenClassroomIE from .steam import SteamIE diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py new file mode 100644 index 000000000..19cc976e3 --- /dev/null +++ b/youtube_dl/extractor/sportbox.py @@ -0,0 +1,81 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from ..utils import ( + parse_duration, + parse_iso8601, + int_or_none, +) + + +class SportBoxIE(InfoExtractor): + _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P.+)' + _TESTS = [ + { + 'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '80822', + 'ext': 'mp4', + 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', + 'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed', + 'thumbnail': 're:^https?://.*\.jpg$', + 'timestamp': 1411896237, + 'upload_date': '20140928', + 'duration': 4846, + 'view_count': int, + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4', + 'only_matching': True, + } + ] + + def _real_extract(self, url): + mobj = re.match(self._VALID_URL, url) + display_id = mobj.group('display_id') + + webpage = self._download_webpage(url, display_id) + + video_id = self._search_regex( + r'src="/vdl/player/media/(\d+)"', webpage, 'video id') + + player = self._download_webpage( + 'http://news.sportbox.ru/vdl/player/media/%s' % video_id, + display_id, 'Downloading player webpage') + + hls = self._search_regex( + r"var\s+original_hls_file\s*=\s*'([^']+)'", player, 'hls file') + + formats = self._extract_m3u8_formats(hls, display_id, 'mp4') + + title = self._html_search_regex( + r'

([^<]+)

', webpage, 'title') + description = self._html_search_regex( + r'(?s)
(.+?)
', webpage, 'description', fatal=False) + thumbnail = self._og_search_thumbnail(webpage) + timestamp = parse_iso8601(self._search_regex( + r'([^<]+)', webpage, 'timestamp', fatal=False)) + duration = parse_duration(self._html_search_regex( + r'', webpage, 'duration', fatal=False)) + view_count = int_or_none(self._html_search_regex( + r'Просмотров: (\d+)', player, 'view count', fatal=False)) + + return { + 'id': video_id, + 'display_id': display_id, + 'title': title, + 'description': description, + 'thumbnail': thumbnail, + 'timestamp': timestamp, + 'duration': duration, + 'view_count': view_count, + 'formats': formats, + } -- cgit v1.2.3