X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/6d835d4d6903cf5e18ad01844736929e06d16004..3e696c728febc53e74c912c40ccd3b9504d536df:/youtube_dl/extractor/sportbox.py diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py index becdf65..e5c28ae 100644 --- a/youtube_dl/extractor/sportbox.py +++ b/youtube_dl/extractor/sportbox.py @@ -4,37 +4,37 @@ from __future__ import unicode_literals import re from .common import InfoExtractor +from ..compat import compat_urlparse from ..utils import ( - parse_duration, - parse_iso8601, + js_to_json, + unified_strdate, ) 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$', - 'timestamp': 1411896237, - 'upload_date': '20140928', - 'duration': 4846, - }, - 'params': { - # m3u8 download - 'skip_download': True, - }, - }, { - 'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4', - 'only_matching': True, - } - ] + _VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P.+)' + _TESTS = [{ + 'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S', + 'md5': 'ff56a598c2cf411a9a38a69709e97079', + 'info_dict': { + 'id': '80822', + 'ext': 'mp4', + 'title': 'Гонка 2 заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн', + 'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad', + 'thumbnail': 're:^https?://.*\.jpg$', + 'upload_date': '20140928', + }, + '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, + }, { + 'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355', + 'only_matching': True, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) @@ -42,35 +42,89 @@ class SportBoxIE(InfoExtractor): 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') + player = self._search_regex( + r'src="/?(vdl/player/[^"]+)"', webpage, 'player') title = self._html_search_regex( - r'

([^<]+)

', webpage, 'title') - description = self._html_search_regex( - r'(?s)
(.+?)
', webpage, 'description', fatal=False) + [r'"nodetitle"\s*:\s*"([^"]+)"', r'class="node-header_{1,2}title">([^<]+)'], + webpage, 'title') + description = self._og_search_description(webpage) or self._html_search_meta( + 'description', webpage, 'description') 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)) + upload_date = unified_strdate(self._html_search_meta( + 'dateCreated', webpage, 'upload date')) return { - 'id': video_id, + '_type': 'url_transparent', + 'url': compat_urlparse.urljoin(url, '/%s' % player), 'display_id': display_id, 'title': title, 'description': description, 'thumbnail': thumbnail, - 'timestamp': timestamp, - 'duration': duration, + 'upload_date': upload_date, + } + + +class SportBoxEmbedIE(InfoExtractor): + _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P\d+)' + _TESTS = [{ + 'url': 'http://news.sportbox.ru/vdl/player/ci/211355', + 'info_dict': { + 'id': '211355', + 'ext': 'mp4', + 'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»', + 'thumbnail': 're:^https?://.*\.jpg$', + }, + 'params': { + # m3u8 download + 'skip_download': True, + }, + }, { + 'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580', + 'only_matching': True, + }] + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r']+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"', + webpage) + + def _real_extract(self, url): + video_id = self._match_id(url) + + webpage = self._download_webpage(url, video_id) + + formats = [] + + def cleanup_js(code): + # desktop_advert_config contains complex Javascripts and we don't need it + return js_to_json(re.sub(r'desktop_advert_config.*', '', code)) + + jwplayer_data = self._parse_json(self._search_regex( + r'(?s)player\.setup\(({.+?})\);', webpage, 'jwplayer settings'), video_id, + transform_source=cleanup_js) + + hls_url = jwplayer_data.get('hls_url') + if hls_url: + formats.extend(self._extract_m3u8_formats( + hls_url, video_id, ext='mp4', m3u8_id='hls')) + + rtsp_url = jwplayer_data.get('rtsp_url') + if rtsp_url: + formats.append({ + 'url': rtsp_url, + 'format_id': 'rtsp', + }) + + self._sort_formats(formats) + + title = jwplayer_data['node_title'] + thumbnail = jwplayer_data.get('image_url') + + return { + 'id': video_id, + 'title': title, + 'thumbnail': thumbnail, 'formats': formats, }