[extractor/common] Extract more metadata for VideoObject 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 bfd4321605a906862987063b243703445136dc5e..9ffe64d05533ae5c5ac2a8d21bb1223b388e9789 100644 (file)
--- a/youtube_dl/extractor/common.py
+++ b/youtube_dl/extractor/common.py
@@ -44,6 +44,7 @@ from ..utils import (
     sanitized_Request,
     unescapeHTML,
     unified_strdate,
+    unified_timestamp,
     url_basename,
     xpath_element,
     xpath_text,
@@ -53,6 +54,7 @@ from ..utils import (
     mimetype2ext,
     update_Request,
     update_url_query,
+    parse_m3u8_attributes,
 )
 
 
@@ -160,6 +162,7 @@ class InfoExtractor(object):
                         * "height" (optional, int)
                         * "resolution" (optional, string "{width}x{height"},
                                         deprecated)
+                        * "filesize" (optional, int)
     thumbnail:      Full URL to a video thumbnail image.
     description:    Full video description.
     uploader:       Full name of the video uploader.
@@ -748,10 +751,12 @@ class InfoExtractor(object):
         return self._og_search_property('url', html, **kargs)
 
     def _html_search_meta(self, name, html, display_name=None, fatal=False, **kwargs):
+        if not isinstance(name, (list, tuple)):
+            name = [name]
         if display_name is None:
-            display_name = name
+            display_name = name[0]
         return self._html_search_regex(
-            self._meta_regex(name),
+            [self._meta_regex(n) for n in name],
             html, display_name, fatal=fatal, group='content', **kwargs)
 
     def _dc_search_uploader(self, html):
@@ -834,6 +839,19 @@ class InfoExtractor(object):
                     'title': unescapeHTML(json_ld.get('headline')),
                     'description': unescapeHTML(json_ld.get('articleBody')),
                 })
+            elif item_type == 'VideoObject':
+                info.update({
+                    'url': json_ld.get('contentUrl'),
+                    'title': unescapeHTML(json_ld.get('name')),
+                    'description': unescapeHTML(json_ld.get('description')),
+                    'thumbnail': json_ld.get('thumbnailUrl'),
+                    'duration': parse_duration(json_ld.get('duration')),
+                    'timestamp': unified_timestamp(json_ld.get('uploadDate')),
+                    'filesize': float_or_none(json_ld.get('contentSize')),
+                    'tbr': int_or_none(json_ld.get('bitrate')),
+                    'width': int_or_none(json_ld.get('width')),
+                    'height': int_or_none(json_ld.get('height')),
+                })
         return dict((k, v) for k, v in info.items() if v is not None)
 
     @staticmethod
@@ -875,7 +893,11 @@ class InfoExtractor(object):
                 f['ext'] = determine_ext(f['url'])
 
             if isinstance(field_preference, (list, tuple)):
-                return tuple(f.get(field) if f.get(field) is not None else -1 for field in field_preference)
+                return tuple(
+                    f.get(field)
+                    if f.get(field) is not None
+                    else ('' if field == 'format_id' else -1)
+                    for field in field_preference)
 
             preference = f.get('preference')
             if preference is None:
@@ -1150,23 +1172,11 @@ class InfoExtractor(object):
             }]
         last_info = None
         last_media = None
-        kv_rex = re.compile(
-            r'(?P<key>[a-zA-Z_-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)')
         for line in m3u8_doc.splitlines():
             if line.startswith('#EXT-X-STREAM-INF:'):
-                last_info = {}
-                for m in kv_rex.finditer(line):
-                    v = m.group('val')
-                    if v.startswith('"'):
-                        v = v[1:-1]
-                    last_info[m.group('key')] = v
+                last_info = parse_m3u8_attributes(line)
             elif line.startswith('#EXT-X-MEDIA:'):
-                last_media = {}
-                for m in kv_rex.finditer(line):
-                    v = m.group('val')
-                    if v.startswith('"'):
-                        v = v[1:-1]
-                    last_media[m.group('key')] = v
+                last_media = parse_m3u8_attributes(line)
             elif line.startswith('#') or not line.strip():
                 continue
             else:
@@ -1734,6 +1744,13 @@ class InfoExtractor(object):
     def _mark_watched(self, *args, **kwargs):
         raise NotImplementedError('This method must be implemented by subclasses')
 
+    def geo_verification_headers(self):
+        headers = {}
+        geo_verification_proxy = self._downloader.params.get('geo_verification_proxy')
+        if geo_verification_proxy:
+            headers['Ytdl-request-proxy'] = geo_verification_proxy
+        return headers
+
 
 class SearchInfoExtractor(InfoExtractor):
     """