[extractor/common] Add support for movies in _json_ld

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

diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py
index 2dbf81e6e27dc858eb038dffae8a8085f0e61eb6..f507400cc34facb450015bd7254d4f98b85487a5 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -69,6 +69,7 @@ from ..utils import (
     update_url_query,
     urljoin,
     url_basename,
+    url_or_none,
     xpath_element,
     xpath_text,
     xpath_with_ns,
@@ -605,6 +606,11 @@ class InfoExtractor(object):
         except (compat_urllib_error.URLError, compat_http_client.HTTPException, socket.error) as err:
             if isinstance(err, compat_urllib_error.HTTPError):
                 if self.__can_accept_status_code(err, expected_status):
+                    # Retain reference to error to prevent file object from
+                    # being closed before it can be read. Works around the
+                    # effects of <https://bugs.python.org/issue15002>
+                    # introduced in Python 3.4.1.
+                    err.fp._error = err
                     return err.fp
 
             if errnote is False:
@@ -1213,10 +1219,10 @@ class InfoExtractor(object):
         def extract_video_object(e):
             assert e['@type'] == 'VideoObject'
             info.update({
-                'url': e.get('contentUrl'),
+                'url': url_or_none(e.get('contentUrl')),
                 'title': unescapeHTML(e.get('name')),
                 'description': unescapeHTML(e.get('description')),
-                'thumbnail': e.get('thumbnailUrl') or e.get('thumbnailURL'),
+                'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')),
                 'duration': parse_duration(e.get('duration')),
                 'timestamp': unified_timestamp(e.get('uploadDate')),
                 'filesize': float_or_none(e.get('contentSize')),
@@ -1244,6 +1250,13 @@ class InfoExtractor(object):
                     part_of_series = e.get('partOfSeries') or e.get('partOfTVSeries')
                     if isinstance(part_of_series, dict) and part_of_series.get('@type') in ('TVSeries', 'Series', 'CreativeWorkSeries'):
                         info['series'] = unescapeHTML(part_of_series.get('name'))
+                elif item_type == 'Movie':
+                    info.update({
+                        'title': unescapeHTML(e.get('name')),
+                        'description': unescapeHTML(e.get('description')),
+                        'duration': parse_duration(e.get('duration')),
+                        'timestamp': unified_timestamp(e.get('dateCreated')),
+                    })
                 elif item_type in ('Article', 'NewsArticle'):
                     info.update({
                         'timestamp': parse_iso8601(e.get('datePublished')),