X-Git-Url: https://asedeno.scripts.mit.edu/gitweb/?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fgamespot.py;h=7a1beae3cf023a7d7f01a91f3b1b30c17094a57d;hb=199c645bee2052e43ec33cc8d0b0fa0c18853da8;hp=098768361ede01d8acc01dc773a31b5b8fc67241;hpb=850555c4843f7815030d015ec7df798332e60582;p=youtube-dl.git

diff --git a/youtube_dl/extractor/gamespot.py b/youtube_dl/extractor/gamespot.py
index 098768361e..7a1beae3cf 100644
--- a/youtube_dl/extractor/gamespot.py
+++ b/youtube_dl/extractor/gamespot.py
@@ -1,59 +1,79 @@
-import re
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    compat_urllib_parse,
-    compat_urlparse,
-    unescapeHTML,
-    get_meta_content,
-)
-
-
-class GameSpotIE(InfoExtractor):
-    _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?'
-    _TEST = {
-        u"url": u"http://www.gamespot.com/arma-iii/videos/arma-iii-community-guide-sitrep-i-6410818/",
-        u"file": u"gs-2300-6410818.mp4",
-        u"md5": u"b2a30deaa8654fcccd43713a6b6a4825",
-        u"info_dict": {
-            u"title": u"Arma 3 - Community Guide: SITREP I",
-            u'description': u'Check out this video where some of the basics of Arma 3 is explained.',
-        }
-    }
+from __future__ import unicode_literals
+
+from .once import OnceIE
+from ..compat import compat_urllib_parse_unquote
+
+
+class GameSpotIE(OnceIE):
+    _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
+        'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
+        'info_dict': {
+            'id': 'gs-2300-6410818',
+            'ext': 'mp4',
+            'title': 'Arma 3 - Community Guide: SITREP I',
+            'description': 'Check out this video where some of the basics of Arma 3 is explained.',
+        },
+        'skip': 'manifest URL give HTTP Error 404: Not Found',
+    }, {
+        'url': 'http://www.gamespot.com/videos/the-witcher-3-wild-hunt-xbox-one-now-playing/2300-6424837/',
+        'md5': '173ea87ad762cf5d3bf6163dceb255a6',
+        'info_dict': {
+            'id': 'gs-2300-6424837',
+            'ext': 'mp4',
+            'title': 'Now Playing - The Witcher 3: Wild Hunt',
+            'description': 'Join us as we take a look at the early hours of The Witcher 3: Wild Hunt and more.',
+        },
+    }, {
+        'url': 'https://www.gamespot.com/videos/embed/6439218/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.gamespot.com/articles/the-last-of-us-2-receives-new-ps4-trailer/1100-6454469/',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.gamespot.com/reviews/gears-of-war-review/1900-6161188/',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        page_id = video_id = mobj.group('page_id')
+        page_id = self._match_id(url)
         webpage = self._download_webpage(url, page_id)
-        data_video_json = self._search_regex(r'data-video=\'(.*?)\'', webpage, u'data video')
-        data_video = json.loads(unescapeHTML(data_video_json))
-
-        # Transform the manifest url to a link to the mp4 files
-        # they are used in mobile devices.
-        f4m_url = data_video['videoStreams']['f4m_stream']
-        f4m_path = compat_urlparse.urlparse(f4m_url).path
-        QUALITIES_RE = r'((,\d+)+,?)'
-        qualities = self._search_regex(QUALITIES_RE, f4m_path, u'qualities').strip(',').split(',')
-        http_path = f4m_path[1:].split('/', 1)[1]
-        http_template = re.sub(QUALITIES_RE, r'%s', http_path)
-        http_template = http_template.replace('.csmil/manifest.f4m', '')
-        http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template)
+        data_video = self._parse_json(self._html_search_regex(
+            r'data-video=(["\'])({.*?})\1', webpage,
+            'video data', group=2), page_id)
+        title = compat_urllib_parse_unquote(data_video['title'])
+        streams = data_video['videoStreams']
         formats = []
-        for q in qualities:
-            formats.append({
-                'url': http_template % q,
-                'ext': 'mp4',
-                'format_id': q,
-            })
-
-        info = {
-            'id': data_video['guid'],
-            'title': compat_urllib_parse.unquote(data_video['title']),
+
+        m3u8_url = streams.get('adaptive_stream')
+        if m3u8_url:
+            m3u8_formats = self._extract_m3u8_formats(
+                m3u8_url, page_id, 'mp4', 'm3u8_native',
+                m3u8_id='hls', fatal=False)
+            for f in m3u8_formats:
+                formats.append(f)
+                http_f = f.copy()
+                del http_f['manifest_url']
+                http_f.update({
+                    'format_id': f['format_id'].replace('hls-', 'http-'),
+                    'protocol': 'http',
+                    'url': f['url'].replace('.m3u8', '.mp4'),
+                })
+                formats.append(http_f)
+
+        mpd_url = streams.get('adaptive_dash')
+        if mpd_url:
+            formats.extend(self._extract_mpd_formats(
+                mpd_url, page_id, mpd_id='dash', fatal=False))
+
+        self._sort_formats(formats)
+
+        return {
+            'id': data_video.get('guid') or page_id,
+            'display_id': page_id,
+            'title': title,
             'formats': formats,
-            'description': get_meta_content('description', webpage),
+            'description': self._html_search_meta('description', webpage),
             'thumbnail': self._og_search_thumbnail(webpage),
         }
-        # TODO: Remove when #980 has been merged
-        info.update(formats[-1])
-        return info