Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go

[youtube-dl] / youtube_dl / extractor / pbs.py

diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 8f140d62660b896f5a6f819d621a762d13fbdb69..fec5d65ad94892ca0f40a9e49703c857d98b47a4 100644 (file)
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -1,9 +1,13 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
 import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
+    determine_ext,
+    int_or_none,
     unified_strdate,
     US_RATINGS,
 )
@@ -32,6 +36,9 @@ class PBSIE(InfoExtractor):
                 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
                 'duration': 3190,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
@@ -43,6 +50,9 @@ class PBSIE(InfoExtractor):
                 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
                 'duration': 5050,
             },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            }
         },
         {
             'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
@@ -65,7 +75,10 @@ class PBSIE(InfoExtractor):
                 'title': 'Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
                 'duration': 6559,
                 'thumbnail': 're:^https?://.*\.jpg$',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         },
         {
             'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
@@ -79,9 +92,33 @@ class PBSIE(InfoExtractor):
                 'duration': 3172,
                 'thumbnail': 're:^https?://.*\.jpg$',
                 'upload_date': '20140122',
-            }
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
+            'info_dict': {
+                'id': 'united-states-of-secrets',
+            },
+            'playlist_count': 2,
+        },
+        {
+            'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
+            'info_dict': {
+                'id': '2280706814',
+                'display_id': 'player',
+                'ext': 'mp4',
+                'title': 'Death and the Civil War',
+                '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': 6705,
+                'thumbnail': 're:^https?://.*\.jpg$',
+            },
+            'params': {
+                'skip_download': True,  # requires ffmpeg
+            },
         }
-
     ]
 
     def _extract_webpage(self, url):
@@ -96,6 +133,12 @@ class PBSIE(InfoExtractor):
                 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
                 webpage, 'upload date', default=None))
 
+            # tabbed frontline videos
+            tabbed_videos = re.findall(
+                r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
+            if tabbed_videos:
+                return tabbed_videos, presumptive_id, upload_date
+
             MEDIA_ID_REGEXES = [
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
@@ -108,7 +151,7 @@ class PBSIE(InfoExtractor):
                 return media_id, presumptive_id, upload_date
 
             url = self._search_regex(
-                r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
+                r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
                 webpage, 'player URL')
             mobj = re.match(self._VALID_URL, url)
 
@@ -130,23 +173,74 @@ class PBSIE(InfoExtractor):
     def _real_extract(self, 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)
+        if isinstance(video_id, list):
+            entries = [self.url_result(
+                'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
+                for vid_id in video_id]
+            return self.playlist_result(entries, display_id)
+
+        info = self._download_json(
+            'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
+            display_id)
+
+        formats = []
+        for encoding_name in ('recommended_encoding', 'alternate_encoding'):
+            redirect = info.get(encoding_name)
+            if not redirect:
+                continue
+            redirect_url = redirect.get('url')
+            if not redirect_url:
+                continue
+
+            redirect_info = self._download_json(
+                redirect_url + '?format=json', display_id,
+                '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)
+
+            format_url = redirect_info.get('url')
+            if not format_url:
+                continue
+
+            if determine_ext(format_url) == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
+            else:
+                formats.append({
+                    'url': format_url,
+                    'format_id': redirect.get('eeid'),
+                })
+        self._sort_formats(formats)
 
         rating_str = info.get('rating')
         if rating_str is not None:
             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,
+            }]
+
         return {
             'id': video_id,
             'display_id': display_id,
             'title': info['title'],
-            'url': info['alternate_encoding']['url'],
-            'ext': 'mp4',
             'description': info['program'].get('description'),
             'thumbnail': info.get('image_url'),
-            'duration': info.get('duration'),
+            'duration': int_or_none(info.get('duration')),
             'age_limit': age_limit,
             'upload_date': upload_date,
+            'formats': formats,
+            'subtitles': subtitles,
         }