Merge branch 'maddoger-sportbox-fix'

youtube_dl/extractor/__init__.py

@@ -502,7 +502,10 @@
 from .spiegeltv import SpiegeltvIE
 from .spike import SpikeIE
 from .sport5 import Sport5IE
-from .sportbox import SportBoxIE
+from .sportbox import (
+    SportBoxIE,
+    SportBoxEmbedIE,
+)
 from .sportdeutschland import SportDeutschlandIE
 from .srf import SrfIE
 from .srmediathek import SRMediathekIE

youtube_dl/extractor/generic.py

@@ -32,6 +32,7 @@
 from .nbc import NBCSportsVPlayerIE
 from .ooyala import OoyalaIE
 from .rutv import RUTVIE
+from .sportbox import SportBoxEmbedIE
 from .smotri import SmotriIE
 from .condenast import CondeNastIE
 from .udn import UDNEmbedIE
@@ -224,6 +225,37 @@ class GenericIE(InfoExtractor):
                 'skip_download': True,
             },
         },
+        # SportBox embed
+        {
+            'url': 'http://www.vestifinance.ru/articles/25753',
+            'info_dict': {
+                'id': '25753',
+                'title': 'Вести Экономика ― Прямые трансляции с Форума-выставки "Госзаказ-2013"',
+            },
+            'playlist': [{
+                'info_dict': {
+                    'id': '370908',
+                    'title': 'Госзаказ. День 3',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370905',
+                    'title': 'Госзаказ. День 2',
+                    'ext': 'mp4',
+                }
+            }, {
+                'info_dict': {
+                    'id': '370902',
+                    'title': 'Госзаказ. День 1',
+                    'ext': 'mp4',
+                }
+            }],
+            'params': {
+                # m3u8 download
+                'skip_download': True,
+            },
+        },
         # Embedded TED video
         {
             'url': 'http://en.support.wordpress.com/videos/ted-talks/',
@@ -1229,6 +1261,11 @@ def _playlist_from_matches(matches, getter=None, ie=None):
         if rutv_url:
             return self.url_result(rutv_url, 'RUTV')
 
+        # Look for embedded SportBox player
+        sportbox_urls = SportBoxEmbedIE._extract_urls(webpage)
+        if sportbox_urls:
+            return _playlist_from_matches(sportbox_urls, ie='SportBoxEmbed')
+
         # Look for embedded TED player
         mobj = re.search(
             r'<iframe[^>]+?src=(["\'])(?P<url>https?://embed(?:-ssl)?\.ted\.com/.+?)\1', webpage)

youtube_dl/extractor/sportbox.py

@@ -4,6 +4,7 @@
 import re
 
 from .common import InfoExtractor
+from ..compat import compat_urlparse
 from ..utils import (
     parse_duration,
     parse_iso8601,
@@ -11,30 +12,31 @@
 
 
 class SportBoxIE(InfoExtractor):
-    _VALID_URL = r'https?://news\.sportbox\.ru/Vidy_sporta/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
+    _VALID_URL = r'https?://news\.sportbox\.ru/(?:[^/]+/)+spbvideo_NI\d+_(?P<display_id>.+)'
-    _TESTS = [
+    _TESTS = [{
-        {
+        'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
-            'url': 'http://news.sportbox.ru/Vidy_sporta/Avtosport/Rossijskij/spbvideo_NI483529_Gonka-2-zaezd-Obyedinenniy-2000-klassi-Turing-i-S',
+        'md5': 'ff56a598c2cf411a9a38a69709e97079',
-            'md5': 'ff56a598c2cf411a9a38a69709e97079',
+        'info_dict': {
-            'info_dict': {
+            'id': '80822',
-                'id': '80822',
+            'ext': 'mp4',
-                'ext': 'mp4',
+            'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
-                'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
+            'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
-                'description': 'md5:81715fa9c4ea3d9e7915dc8180c778ed',
+            'thumbnail': 're:^https?://.*\.jpg$',
-                'thumbnail': 're:^https?://.*\.jpg$',
+            'timestamp': 1411896237,
-                'timestamp': 1411896237,
+            'upload_date': '20140928',
-                'upload_date': '20140928',
+            'duration': 4846,
-                'duration': 4846,
+        },
-            },
+        'params': {
-            'params': {
+            # m3u8 download
-                # m3u8 download
+            'skip_download': True,
-                'skip_download': True,
+        },
-            },
+    }, {
-        }, {
+        'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
-            'url': 'http://news.sportbox.ru/Vidy_sporta/billiard/spbvideo_NI486287_CHempionat-mira-po-dinamichnoy-piramide-4',
+        'only_matching': True,
-            '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 +44,80 @@ def _real_extract(self, url):
 
         webpage = self._download_webpage(url, display_id)
 
-        video_id = self._search_regex(
+        player = self._search_regex(
-            r'src="/vdl/player/media/(\d+)"', webpage, 'video id')
+            r'src="/?(vdl/player/[^"]+)"', webpage, 'player')
-
-        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'<h1 itemprop="name">([^<]+)</h1>', webpage, 'title')
         description = self._html_search_regex(
-            r'(?s)<div itemprop="description">(.+?)</div>', webpage, 'description', fatal=False)
+            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))
+            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))
+            r'<meta itemprop="duration" content="PT([^"]+)">',
+            webpage, 'duration', fatal=False))
 
         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,
+        }
+
+
+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',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+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)
+
+        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,
             'formats': formats,
         }