X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;ds=sidebyside;f=youtube_dl%2Fextractor%2Fpbs.py;h=b787e2a73c66a0ff1bf2d17b9f20c13bf166aae7;hb=7dc011c063c5c51712605ac08cf1c01841d5867c;hp=82218b933aa532a0161cf1faf8727ea5f37d4271;hpb=7faf7e752342b21772c8647902bbf4f13cc57956;p=youtube-dl

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 82218b933..b787e2a73 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -8,6 +8,7 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     int_or_none,
+    strip_jsonp,
     unified_strdate,
     US_RATINGS,
 )
@@ -21,7 +22,7 @@ class PBSIE(InfoExtractor):
            # Article with embedded player (or direct video)
            (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
-           video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
+           (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
     '''
 
@@ -39,7 +40,6 @@ class PBSIE(InfoExtractor):
             'params': {
                 'skip_download': True,  # requires ffmpeg
             },
-            'skip': 'Expired',
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
@@ -154,8 +154,34 @@ class PBSIE(InfoExtractor):
             'params': {
                 'skip_download': True,  # requires ffmpeg
             },
+        },
+        {
+            # Frontline video embedded via flp2012.js
+            'url': 'http://www.pbs.org/wgbh/pages/frontline/the-atomic-artists',
+            'info_dict': {
+                'id': '2070868960',
+                'display_id': 'the-atomic-artists',
+                'ext': 'mp4',
+                'title': 'FRONTLINE - The Atomic Artists',
+                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+                'duration': 723,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
+        },
+        {
+            'url': 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true',
+            'only_matching': True,
         }
     ]
+    _ERRORS = {
+        101: 'We\'re sorry, but this video is not yet available.',
+        403: 'We\'re sorry, but this video is not available in your region due to right restrictions.',
+        404: 'We are experiencing technical difficulties that are preventing us from playing the video at this time. Please check back again soon.',
+        410: 'This video has expired and is no longer available for online streaming.',
+    }
 
     def _extract_webpage(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -186,9 +212,30 @@ class PBSIE(InfoExtractor):
             if media_id:
                 return media_id, presumptive_id, upload_date
 
-            url = self._search_regex(
-                r'(?s)<iframe[^>]+?(?:[a-z-]+?=["\'].*?["\'][^>]+?)*?\bsrc=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
-                webpage, 'player URL')
+            # Fronline video embedded via flp
+            video_id = self._search_regex(
+                r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid', default=None)
+            if video_id:
+                # pkg_id calculation is reverse engineered from
+                # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
+                prg_id = self._search_regex(
+                    r'videoid\s*:\s*"([\d+a-z]{7,})"', webpage, 'videoid')[7:]
+                if 'q' in prg_id:
+                    prg_id = prg_id.split('q')[1]
+                prg_id = int(prg_id, 16)
+                getdir = self._download_json(
+                    'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir%d.json' % prg_id,
+                    presumptive_id, 'Downloading getdir JSON',
+                    transform_source=strip_jsonp)
+                return getdir['mid'], presumptive_id, upload_date
+
+            for iframe in re.findall(r'(?s)<iframe(.+?)></iframe>', webpage):
+                url = self._search_regex(
+                    r'src=(["\'])(?P<url>.+?partnerplayer.+?)\1', iframe,
+                    'player URL', default=None, group='url')
+                if url:
+                    break
+
             mobj = re.match(self._VALID_URL, url)
 
         player_id = mobj.group('player_id')
@@ -216,7 +263,7 @@ class PBSIE(InfoExtractor):
             return self.playlist_result(entries, display_id)
 
         info = self._download_json(
-            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
+            'http://player.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
             display_id)
 
         formats = []
@@ -233,18 +280,11 @@ class PBSIE(InfoExtractor):
                 'Downloading %s video url info' % encoding_name)
 
             if redirect_info['status'] == 'error':
-                http_code = redirect_info['http_code']
-                if http_code == 403:
-                    message = 'We\'re sorry, but this video is not available in your region due to right restrictions.'
-                elif http_code == 101:
-                    message = 'We\'re sorry, but this video is not yet available.'
-                elif http_code == 404:
-                    message = 'We are experiencing technical difficulties that are preventing us from playing the video at this time. Please check back again soon.'
-                elif http_code == 410:
-                    message = 'This video has expired and is no longer available for online streaming.'
-                else:
-                    message = redirect_info['message']
-                raise ExtractorError('PBS said: %s' % message, expected=True)
+                raise ExtractorError(
+                    '%s said: %s' % (
+                        self.IE_NAME,
+                        self._ERRORS.get(redirect_info['http_code'], redirect_info['message'])),
+                    expected=True)
 
             format_url = redirect_info.get('url')
             if not format_url: