Add field `webpage_url_domain`

Closes #1311

diff --git a/README.md b/README.md
index 4fec2c8b46b7c483fb4de006f27460adb5f65fb5..ba4588c55d1038129034cd2e8cc15dc74cbb38bc 100644 (file)
--- a/README.md
+++ b/README.md
@@ -1137,6 +1137,8 @@ # OUTPUT TEMPLATE
  - `playlist_uploader` (string): Full name of the playlist uploader
  - `playlist_uploader_id` (string): Nickname or id of the playlist uploader
  - `webpage_url` (string): A URL to the video webpage which if given to yt-dlp should allow to get the same result again
+ - `webpage_url_basename` (string): The basename of the webpage URL
+ - `webpage_url_domain` (string): The domain of the webpage URL
  - `original_url` (string): The URL given by the user (or same as `webpage_url` for playlist entries)
 
 Available for the video that belongs to some logical chapter or section:

diff --git a/yt_dlp/YoutubeDL.py b/yt_dlp/YoutubeDL.py
index 698ad98a1718fa310321bf93e23d53febc902cb8..39fd2e1fd7ab527241806607b1b31dba03fb879d 100644 (file)
--- a/yt_dlp/YoutubeDL.py
+++ b/yt_dlp/YoutubeDL.py
@@ -70,6 +70,7 @@
     format_field,
     formatSeconds,
     GeoRestrictedError,
+    get_domain,
     HEADRequest,
     int_or_none,
     iri_to_uri,
@@ -1424,6 +1425,7 @@ def add_default_extra_info(self, ie_result, ie, url):
                 'webpage_url': url,
                 'original_url': url,
                 'webpage_url_basename': url_basename(url),
+                'webpage_url_domain': get_domain(url),
             })
         if ie is not None:
             self.add_extra_info(ie_result, {
@@ -1548,6 +1550,7 @@ def _fixup(r):
                     'extractor': ie_result['extractor'],
                     'webpage_url': ie_result['webpage_url'],
                     'webpage_url_basename': url_basename(ie_result['webpage_url']),
+                    'webpage_url_domain': get_domain(ie_result['webpage_url']),
                     'extractor_key': ie_result['extractor_key'],
                 })
                 return r
@@ -1709,6 +1712,7 @@ def get_entry(i):
                 'extractor': ie_result['extractor'],
                 'webpage_url': ie_result['webpage_url'],
                 'webpage_url_basename': url_basename(ie_result['webpage_url']),
+                'webpage_url_domain': get_domain(ie_result['webpage_url']),
                 'extractor_key': ie_result['extractor_key'],
             }