X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fescapist.py;h=4303feccdaedd865e2c769a282173de6a4d5ffce;hb=163d966707a7e49bcdad4ebd9189922b58223395;hp=86b145bca9d9da95024525be3f4b5cf441b36b58;hpb=825e0984e27f0c626c4d072066e0c9cae9069704;p=youtube-dl

diff --git a/youtube_dl/extractor/escapist.py b/youtube_dl/extractor/escapist.py
index 86b145bca..4303feccd 100644
--- a/youtube_dl/extractor/escapist.py
+++ b/youtube_dl/extractor/escapist.py
@@ -1,68 +1,85 @@
-import json
-import re
+from __future__ import unicode_literals
 
 from .common import InfoExtractor
-from ..utils import (
-    compat_str,
+from ..compat import (
     compat_urllib_parse,
-
+)
+from ..utils import (
     ExtractorError,
+    js_to_json,
 )
 
 
 class EscapistIE(InfoExtractor):
-    _VALID_URL = r'^(https?://)?(www\.)?escapistmagazine\.com/videos/view/(?P<showname>[^/]+)/(?P<episode>[^/?]+)[/?]?.*$'
+    _VALID_URL = r'https?://?(www\.)?escapistmagazine\.com/videos/view/[^/?#]+/(?P<id>[0-9]+)-[^/?#]*(?:$|[?#])'
+    _TEST = {
+        'url': 'http://www.escapistmagazine.com/videos/view/the-escapist-presents/6618-Breaking-Down-Baldurs-Gate',
+        'md5': 'ab3a706c681efca53f0a35f1415cf0d1',
+        'info_dict': {
+            'id': '6618',
+            'ext': 'mp4',
+            'description': "Baldur's Gate: Original, Modded or Enhanced Edition? I'll break down what you can expect from the new Baldur's Gate: Enhanced Edition.",
+            'uploader_id': 'the-escapist-presents',
+            'uploader': 'The Escapist Presents',
+            'title': "Breaking Down Baldur's Gate",
+        }
+    }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        if mobj is None:
-            raise ExtractorError(u'Invalid URL: %s' % url)
-        showName = mobj.group('showname')
-        videoId = mobj.group('episode')
-
-        self.report_extraction(videoId)
-        webpage = self._download_webpage(url, videoId)
-
-        videoDesc = self._html_search_regex('<meta name="description" content="([^"]*)"',
-            webpage, u'description', fatal=False)
-
-        imgUrl = self._html_search_regex('<meta property="og:image" content="([^"]*)"',
-            webpage, u'thumbnail', fatal=False)
-
-        playerUrl = self._html_search_regex('<meta property="og:video" content="([^"]*)"',
-            webpage, u'player url')
-
-        title = self._html_search_regex('<meta name="title" content="([^"]*)"',
-            webpage, u'player url').split(' : ')[-1]
-
-        configUrl = self._search_regex('config=(.*)$', playerUrl, u'config url')
-        configUrl = compat_urllib_parse.unquote(configUrl)
-
-        configJSON = self._download_webpage(configUrl, videoId,
-                                            u'Downloading configuration',
-                                            u'unable to download configuration')
-
-        # Technically, it's JavaScript, not JSON
-        configJSON = configJSON.replace("'", '"')
-
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        uploader_id = self._html_search_regex(
+            r"<h1 class='headline'><a href='/videos/view/(.*?)'",
+            webpage, 'uploader ID', fatal=False)
+        uploader = self._html_search_regex(
+            r"<h1 class='headline'>(.*?)</a>",
+            webpage, 'uploader', fatal=False)
+        description = self._html_search_meta('description', webpage)
+
+        raw_title = self._html_search_meta('title', webpage, fatal=True)
+        title = raw_title.partition(' : ')[2]
+
+        player_url = self._og_search_video_url(webpage, name='player URL')
+        config_url = compat_urllib_parse.unquote(self._search_regex(
+            r'config=(.*)$', player_url, 'config URL'))
+
+        formats = []
+
+        def _add_format(name, cfgurl, quality):
+            config = self._download_json(
+                cfgurl, video_id,
+                'Downloading ' + name + ' configuration',
+                'Unable to download ' + name + ' configuration',
+                transform_source=js_to_json)
+
+            playlist = config['playlist']
+            video_url = next(
+                p['url'] for p in playlist
+                if p.get('eventCategory') == 'Video')
+            formats.append({
+                'url': video_url,
+                'format_id': name,
+                'quality': quality,
+            })
+
+        _add_format('normal', config_url, quality=0)
+        hq_url = (config_url +
+                  ('&hq=1' if '?' in config_url else config_url + '?hq=1'))
         try:
-            config = json.loads(configJSON)
-        except (ValueError,) as err:
-            raise ExtractorError(u'Invalid JSON in configuration file: ' + compat_str(err))
+            _add_format('hq', hq_url, quality=1)
+        except ExtractorError:
+            pass  # That's fine, we'll just use normal quality
 
-        playlist = config['playlist']
-        videoUrl = playlist[1]['url']
+        self._sort_formats(formats)
 
-        info = {
-            'id': videoId,
-            'url': videoUrl,
-            'uploader': showName,
-            'upload_date': None,
+        return {
+            'id': video_id,
+            'formats': formats,
+            'uploader': uploader,
+            'uploader_id': uploader_id,
             'title': title,
-            'ext': 'mp4',
-            'thumbnail': imgUrl,
-            'description': videoDesc,
-            'player_url': playerUrl,
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'description': description,
+            'player_url': player_url,
         }
-
-        return [info]