X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fpbs.py;h=8f140d62660b896f5a6f819d621a762d13fbdb69;hb=852f8641e8fb910160b809bb05f7c2533882195d;hp=09bee6561d0cf31ae770f0a10a4c3368d2923013;hpb=4d9bd478f9d846291c722da002266504fce824ba;p=youtube-dl

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 09bee6561..8f140d626 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -4,6 +4,7 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    unified_strdate,
     US_RATINGS,
 )
 
@@ -11,10 +12,10 @@ from ..utils import (
 class PBSIE(InfoExtractor):
     _VALID_URL = r'''(?x)https?://
         (?:
-            # Direct video URL
-            video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
-            # Article with embedded player
-           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) |
+           # Direct video URL
+           video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
+           # Article with embedded player (or direct video)
+           (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
            # Player
            video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
         )
@@ -32,6 +33,17 @@ class PBSIE(InfoExtractor):
                 'duration': 3190,
             },
         },
+        {
+            'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
+            'md5': '143c98aa54a346738a3d78f54c925321',
+            'info_dict': {
+                'id': '2365297690',
+                'ext': 'mp4',
+                'title': 'Losing Iraq',
+                'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
+                'duration': 5050,
+            },
+        },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
             'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
@@ -43,9 +55,36 @@ class PBSIE(InfoExtractor):
                 'duration': 801,
             },
         },
+        {
+            'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
+            'md5': 'c62859342be2a0358d6c9eb306595978',
+            'info_dict': {
+                'id': '2365297708',
+                'ext': 'mp4',
+                'description': 'md5:68d87ef760660eb564455eb30ca464fe',
+                'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
+                'duration': 6559,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            }
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
+            'md5': '908f3e5473a693b266b84e25e1cf9703',
+            'info_dict': {
+                'id': '2365160389',
+                'display_id': 'killer-typhoon',
+                'ext': 'mp4',
+                'description': 'md5:c741d14e979fc53228c575894094f157',
+                'title': 'Killer Typhoon',
+                'duration': 3172,
+                'thumbnail': 're:^https?://.*\.jpg$',
+                'upload_date': '20140122',
+            }
+        }
+
     ]
 
-    def _extract_ids(self, url):
+    def _extract_webpage(self, url):
         mobj = re.match(self._VALID_URL, url)
 
         presumptive_id = mobj.group('presumptive_id')
@@ -53,18 +92,23 @@ class PBSIE(InfoExtractor):
         if presumptive_id:
             webpage = self._download_webpage(url, display_id)
 
+            upload_date = unified_strdate(self._search_regex(
+                r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
+                webpage, 'upload date', default=None))
+
             MEDIA_ID_REGEXES = [
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
+                r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>',  # jwplayer
             ]
 
             media_id = self._search_regex(
                 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
             if media_id:
-                return media_id, presumptive_id
+                return media_id, presumptive_id, upload_date
 
             url = self._search_regex(
-                r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 
@@ -81,10 +125,10 @@ class PBSIE(InfoExtractor):
             video_id = mobj.group('id')
             display_id = video_id
 
-        return video_id, display_id
+        return video_id, display_id, None
 
     def _real_extract(self, url):
-        video_id, display_id = self._extract_ids(url)
+        video_id, display_id, upload_date = self._extract_webpage(url)
 
         info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
         info = self._download_json(info_url, display_id)
@@ -96,6 +140,7 @@ class PBSIE(InfoExtractor):
 
         return {
             'id': video_id,
+            'display_id': display_id,
             'title': info['title'],
             'url': info['alternate_encoding']['url'],
             'ext': 'mp4',
@@ -103,4 +148,5 @@ class PBSIE(InfoExtractor):
             'thumbnail': info.get('image_url'),
             'duration': info.get('duration'),
             'age_limit': age_limit,
+            'upload_date': upload_date,
         }