debian/README.source: Change 'markup'.

[youtubedl] / youtube_dl / extractor / sportbox.py

diff --git a/youtube_dl/extractor/sportbox.py b/youtube_dl/extractor/sportbox.py
index e5c28ae890ee61536052a5716677d486d0a5b43e..b9017fd2ab67df5f3e1b855eb30047f790b53765 100644 (file)
--- a/youtube_dl/extractor/sportbox.py
+++ b/youtube_dl/extractor/sportbox.py
@@ -4,90 +4,51 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..compat import compat_urlparse

 from ..utils import (
 from ..utils import (

+    determine_ext,
+    int_or_none,

     js_to_json,
     js_to_json,

-    unified_strdate,
+    merge_dicts,

 )
 
 
 class SportBoxIE(InfoExtractor):
 )
 
 
 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 = [{
     _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': {
         'info_dict': {

-            'id': '80822',
+            'id': '109158',

             'ext': 'mp4',
             'ext': 'mp4',

-            'title': 'Гонка 2  заезд ««Объединенный 2000»: классы Туринг и Супер-продакшн',
-            'description': 'md5:3d72dc4a006ab6805d82f037fdc637ad',
-            'thumbnail': 're:^https?://.*\.jpg$',
-            'upload_date': '20140928',
+            'title': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
+            'description': 'В Новороссийске прошел детский турнир «Поле славы боевой»',
+            'thumbnail': r're:^https?://.*\.jpg$',
+            'duration': 292,
+            'view_count': int,
+            'timestamp': 1426237001,
+            'upload_date': '20150313',

         },
         'params': {
             # m3u8 download
             'skip_download': True,
         },
     }, {
         },
         '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,
     }, {
         '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,
         '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'"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)
-        upload_date = unified_strdate(self._html_search_meta(
-            'dateCreated', webpage, 'upload date'))
-
-        return {
-            '_type': 'url_transparent',
-            'url': compat_urlparse.urljoin(url, '/%s' % player),
-            'display_id': display_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'upload_date': upload_date,
-        }
-
-
-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(
         '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):
             webpage)
 
     def _real_extract(self, url):


@@ -95,36 +56,44 @@ class SportBoxEmbedIE(InfoExtractor):
 
         webpage = self._download_webpage(url, video_id)
 
 
         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)
+        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)

 
 

-        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'))
+        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)

 
 

-        rtsp_url = jwplayer_data.get('rtsp_url')
-        if rtsp_url:
-            formats.append({
-                'url': rtsp_url,
-                'format_id': 'rtsp',
-            })
+        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']

 
 

-        self._sort_formats(formats)
+        info = self._search_json_ld(webpage, media_id, default={})

 
 

-        title = jwplayer_data['node_title']
-        thumbnail = jwplayer_data.get('image_url')
+        view_count = int_or_none(self._search_regex(
+            r'Просмотров\s*:\s*(\d+)', webpage, 'view count', default=None))

 
 

-        return {
-            'id': video_id,
-            'title': title,
-            'thumbnail': thumbnail,
+        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,
             'formats': formats,

-        }
+        })