X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fsportbox.py;h=b9017fd2ab67df5f3e1b855eb30047f790b53765;hb=HEAD;hp=8686f9d11fa3178eefe3eb71fe5a1413e729beeb;hpb=9123d645923741056d1e1f2be28974e992eea950;p=youtube-dl

diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py
index 8686f9d11..b9017fd2a 100644
--- a/youtube_dl/extractor/sportbox.py
+++ b/youtube_dl/extractor/sportbox.py
@@ -4,97 +4,51 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urlparse
 from ..utils import (
-    parse_duration,
-    parse_iso8601,
+    determine_ext,
+    int_or_none,
+    js_to_json,
+    merge_dicts,
 )
 
 
 class SportBoxIE(InfoExtractor):
-    _VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
+    _VALID_URL = r'https?://(?:news\.sportbox|matchtv)\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\d+)'
     _TESTS = [{
-        'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
-        'md5': 'ff56a598c2cf411a9a38a69709e97079',
+        'url': 'http://news.sportbox.ru/vdl/player/ci/211355',
         'info_dict': {
-            'id': '80822',
+            'id': '109158',
             'ext': 'mp4',
-            'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
-            'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'timestamp': 1411896237,
-            'upload_date': '20140928',
-            'duration': 4846,
+            'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
+            'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 292,
+            'view_count': int,
+            'timestamp': 1426237001,
+            'upload_date': '20150313',
         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
     }, {
-        'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
+        'url': 'http://news.sportbox.ru/vdl/player?nid=370908&only_player=1&autostart=false&playeri=2&height=340&width=580',
         'only_matching': True,
     }, {
-        'url': 'http://news.sportbox.ru/video/no_ads/spbvideo_NI536574_V_Novorossijske_proshel_detskij_turnir_Pole_slavy_bojevoj?ci=211355',
+        'url': 'https://news.sportbox.ru/vdl/player/media/193095',
         '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)
-
-        player = self._search_regex(
-            r'src="/?(vdl/player/[^"]+)"', webpage, 'player')
-
-        title = self._html_search_regex(
-            r'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title')
-        description = self._html_search_regex(
-            r'(?s)<div itemprop="description">(.+?)</div>',
-            webpage, 'description', fatal=False)
-        thumbnail = self._og_search_thumbnail(webpage)
-        timestamp = parse_iso8601(self._search_regex(
-            r'<span itemprop="uploadDate">([^<]+)</span>',
-            webpage, 'timestamp', fatal=False))
-        duration = parse_duration(self._html_search_regex(
-            r'<meta itemprop="duration" content="PT([^"]+)">',
-            webpage, 'duration', fatal=False))
-
-        return {
-            '_type': 'url_transparent',
-            'url': compat_urlparse.urljoin(url, '/%s' % player),
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
-        }
-
-
-class SportBoxEmbedIE(InfoExtractor):
-    _VALID_URL = r'https?://news\.sportbox\.ru/vdl/player(?:/[^/]+/|\?.*?\bn?id=)(?P<id>\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',
+        'url': 'https://news.sportbox.ru/vdl/player/media/109158',
+        'only_matching': True,
+    }, {
+        'url': 'https://matchtv.ru/vdl/player/media/109158',
         'only_matching': True,
     }]
 
     @staticmethod
     def _extract_urls(webpage):
         return re.findall(
-            r'<iframe[^>]+src="(https?://news\.sportbox\.ru/vdl/player[^"]+)"',
+            r'<iframe[^>]+src="(https?://(?:news\.sportbox|matchtv)\.ru/vdl/player[^"]+)"',
             webpage)
 
     def _real_extract(self, url):
@@ -102,22 +56,44 @@ class SportBoxEmbedIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
-        hls = self._search_regex(
-            r"sportboxPlayer\.jwplayer_common_params\.file\s*=\s*['\"]([^'\"]+)['\"]",
-            webpage, 'hls file')
-
-        formats = self._extract_m3u8_formats(hls, video_id, 'mp4')
-
-        title = self._search_regex(
-            r'sportboxPlayer\.node_title\s*=\s*"([^"]+)"', webpage, 'title')
-
-        thumbnail = self._search_regex(
-            r'sportboxPlayer\.jwplayer_common_params\.image\s*=\s*"([^"]+)"',
-            webpage, 'thumbnail', default=None)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
+        sources = self._parse_json(
+            self._search_regex(
+                r'(?s)playerOptions\.sources(?:WithRes)?\s*=\s*(\[.+?\])\s*;\s*\n',
+                webpage, 'sources'),
+            video_id, transform_source=js_to_json)
+
+        formats = []
+        for source in sources:
+            src = source.get('src')
+            if not src:
+                continue
+            if determine_ext(src) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    src, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+            else:
+                formats.append({
+                    'url': src,
+                })
+        self._sort_formats(formats)
+
+        player = self._parse_json(
+            self._search_regex(
+                r'(?s)playerOptions\s*=\s*({.+?})\s*;\s*\n', webpage,
+                'player options', default='{}'),
+            video_id, transform_source=js_to_json)
+        media_id = player['mediaId']
+
+        info = self._search_json_ld(webpage, media_id, default={})
+
+        view_count = int_or_none(self._search_regex(
+            r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None))
+
+        return merge_dicts(info, {
+            'id': media_id,
+            'title': self._og_search_title(webpage, default=None) or media_id,
+            'thumbnail': player.get('poster'),
+            'duration': int_or_none(player.get('duration')),
+            'view_count': view_count,
             'formats': formats,
-        }
+        })