Merge branch 'pr-twitter' of https://github.com/atomicdryad/youtube-dl into atomicdry...
[youtube-dl] / youtube_dl / extractor / pbs.py
index 761bd6d8dcaa7bcabe4181e691ce4607b1736a07..3448736a258458ff1a2b4a2ee126ce703894e6dc 100644 (file)
@@ -1,3 +1,4 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
@@ -31,10 +32,13 @@ class PBSIE(InfoExtractor):
             'info_dict': {
                 'id': '2365006249',
                 'ext': 'mp4',
-                'title': 'A More Perfect Union',
+                'title': 'Constitution USA with Peter Sagal - A More Perfect Union',
                 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
                 'duration': 3190,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
@@ -42,10 +46,13 @@ class PBSIE(InfoExtractor):
             'info_dict': {
                 'id': '2365297690',
                 'ext': 'mp4',
-                'title': 'Losing Iraq',
+                'title': 'FRONTLINE - Losing Iraq',
                 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
                 'duration': 5050,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            }
         },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
@@ -53,7 +60,7 @@ class PBSIE(InfoExtractor):
             'info_dict': {
                 'id': '2201174722',
                 'ext': 'mp4',
-                'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
+                'title': 'PBS NewsHour - Cyber Schools Gain Popularity, but Quality Questions Persist',
                 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
                 'duration': 801,
             },
@@ -65,10 +72,13 @@ class PBSIE(InfoExtractor):
                 'id': '2365297708',
                 'ext': 'mp4',
                 'description': 'md5:68d87ef760660eb564455eb30ca464fe',
-                'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
+                'title': 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
                 'duration': 6559,
                 'thumbnail': 're:^https?://.*\.jpg$',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
@@ -78,11 +88,15 @@ class PBSIE(InfoExtractor):
                 'display_id': 'killer-typhoon',
                 'ext': 'mp4',
                 'description': 'md5:c741d14e979fc53228c575894094f157',
-                'title': 'Killer Typhoon',
+                'title': 'NOVA - Killer Typhoon',
                 'duration': 3172,
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'upload_date': '20140122',
-            }
+                'age_limit': 10,
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
@@ -90,8 +104,63 @@ class PBSIE(InfoExtractor):
                 'id': 'united-states-of-secrets',
             },
             'playlist_count': 2,
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
+            'info_dict': {
+                'id': '2276541483',
+                'display_id': 'player',
+                'ext': 'mp4',
+                'title': 'American Experience - Death and the Civil War, Chapter 1',
+                'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
+                'duration': 682,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
+        },
+        {
+            'url': 'http://video.pbs.org/video/2365367186/',
+            'info_dict': {
+                'id': '2365367186',
+                'display_id': '2365367186',
+                'ext': 'mp4',
+                'title': 'To Catch A Comet - Full Episode',
+                'description': 'On November 12, 2014, billions of kilometers from Earth, spacecraft orbiter Rosetta and lander Philae did what no other had dared to attempt \u2014 land on the volatile surface of a comet as it zooms around the sun at 67,000 km/hr. The European Space Agency hopes this mission can help peer into our past and unlock secrets of our origins.',
+                'duration': 3342,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
+            'skip': 'Expired',
+        },
+        {
+            # Video embedded in iframe containing angle brackets as attribute's value (e.g.
+            # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
+            # https://github.com/rg3/youtube-dl/issues/7059)
+            'url': 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/',
+            'info_dict': {
+                'id': '2365546844',
+                'display_id': 'a-chefs-life-season-3-episode-5-prickly-business',
+                'ext': 'mp4',
+                'title': "A Chef's Life - Season 3, Ep. 5: Prickly Business",
+                'description': 'md5:61db2ddf27c9912f09c241014b118ed1',
+                'duration': 1480,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         }
     ]
+    _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)
@@ -123,7 +192,7 @@ class PBSIE(InfoExtractor):
                 return media_id, presumptive_id, upload_date
 
             url = self._search_regex(
-                r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                r'(?s)<iframe[^>]+?(?:[a-z-]+?=["\'].*?["\'][^>]+?)*?\bsrc=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 
@@ -169,13 +238,11 @@ class PBSIE(InfoExtractor):
                 'Downloading %s video url info' % encoding_name)
 
             if redirect_info['status'] == 'error':
-                if redirect_info['http_code'] == 403:
-                    message = (
-                        'The video is not available in your region due to '
-                        'right restrictions')
-                else:
-                    message = redirect_info['message']
-                raise ExtractorError(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:
@@ -187,6 +254,7 @@ class PBSIE(InfoExtractor):
             else:
                 formats.append({
                     'url': format_url,
+                    'format_id': redirect.get('eeid'),
                 })
         self._sort_formats(formats)
 
@@ -195,6 +263,20 @@ class PBSIE(InfoExtractor):
             rating_str = rating_str.rpartition('-')[2]
         age_limit = US_RATINGS.get(rating_str)
 
+        subtitles = {}
+        closed_captions_url = info.get('closed_captions_url')
+        if closed_captions_url:
+            subtitles['en'] = [{
+                'ext': 'ttml',
+                'url': closed_captions_url,
+            }]
+
+        # info['title'] is often incomplete (e.g. 'Full Episode', 'Episode 5', etc)
+        # Try turning it to 'program - title' naming scheme if possible
+        alt_title = info.get('program', {}).get('title')
+        if alt_title:
+            info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + '[\s\-:]+', '', info['title'])
+
         return {
             'id': video_id,
             'display_id': display_id,
@@ -205,4 +287,5 @@ class PBSIE(InfoExtractor):
             'age_limit': age_limit,
             'upload_date': upload_date,
             'formats': formats,
+            'subtitles': subtitles,
         }