[danbooru] provide 'tags' as list (#4942)

keep the old 'tag_string' values around, similar to sankaku

a lot of repeat code ...
would be a lot less bad if "".split(" ") returned an empty list

gallery_dl/extractor/danbooru.py

@@ -72,6 +72,25 @@ class DanbooruExtractor(BaseExtractor):
             post["date"] = text.parse_datetime(
                 post["created_at"], "%Y-%m-%dT%H:%M:%S.%f%z")
 
+            post["tags"] = (
+                post["tag_string"].split(" ")
+                if post["tag_string"] else ())
+            post["tags_artist"] = (
+                post["tag_string_artist"].split(" ")
+                if post["tag_string_artist"] else ())
+            post["tags_character"] = (
+                post["tag_string_character"].split(" ")
+                if post["tag_string_character"] else ())
+            post["tags_copyright"] = (
+                post["tag_string_copyright"].split(" ")
+                if post["tag_string_copyright"] else ())
+            post["tags_general"] = (
+                post["tag_string_general"].split(" ")
+                if post["tag_string_general"] else ())
+            post["tags_meta"] = (
+                post["tag_string_meta"].split(" ")
+                if post["tag_string_meta"] else ())
+
             if post["extension"] == "zip":
                 if self.ugoira:
                     post["frames"] = self._ugoira_frames(post)

test/results/danbooru.py

@@ -75,7 +75,132 @@ __tests__ = (
     "#class"   : danbooru.DanbooruPostExtractor,
     "#sha1_content": "5e255713cbf0a8e0801dc423563c34d896bb9229",
 
+    "approver_id": None,
+    "bit_flags": 0,
+    "created_at": "2008-08-12T00:46:05.385-04:00",
     "date": "dt:2008-08-12 04:46:05",
+    "down_score": 0,
+    "extension": "jpg",
+    "fav_count": 9,
+    "file_ext": "jpg",
+    "file_size": 358232,
+    "file_url": "https://cdn.donmai.us/original/ac/8e/ac8e3b92ea328ce9cf7211e69c905bf9.jpg",
+    "filename": "ac8e3b92ea328ce9cf7211e69c905bf9",
+    "has_active_children": False,
+    "has_children": False,
+    "has_large": True,
+    "has_visible_children": False,
+    "id": 294929,
+    "image_height": 687,
+    "image_width": 895,
+    "is_banned": False,
+    "is_deleted": False,
+    "is_flagged": False,
+    "is_pending": False,
+    "large_file_url": "https://cdn.donmai.us/sample/ac/8e/sample-ac8e3b92ea328ce9cf7211e69c905bf9.jpg",
+    "last_comment_bumped_at": None,
+    "last_commented_at": None,
+    "last_noted_at": None,
+    "md5": "ac8e3b92ea328ce9cf7211e69c905bf9",
+    "media_asset": dict,
+    "parent_id": None,
+    "pixiv_id": 1129835,
+    "preview_file_url": "https://cdn.donmai.us/180x180/ac/8e/ac8e3b92ea328ce9cf7211e69c905bf9.jpg",
+    "rating": "s",
+    "score": 1,
+    "source": "https://i.pximg.net/img-original/img/2008/07/09/16/10/23/1129835_p0.jpg",
+    "subcategory": "post",
+    "tag_count": 32,
+    "tag_count_artist": 1,
+    "tag_count_character": 3,
+    "tag_count_copyright": 3,
+    "tag_count_general": 23,
+    "tag_count_meta": 2,
+    "tag_string": "2boys bat_(animal) batman batman_(series) black_bodysuit bodysuit bonocho brown_eyes closed_mouth collared_shirt commentary_request copyright_name dc_comics expressionless facepaint glasgow_smile heath_ledger joker_(dc) male_focus multiple_boys outline outstretched_arm parted_lips photoshop_(medium) pink_shirt shirt sketch smile the_dark_knight upper_body white_outline wing_collar",
+    "tag_string_artist": "bonocho",
+    "tag_string_character": "batman heath_ledger joker_(dc)",
+    "tag_string_copyright": "batman_(series) dc_comics the_dark_knight",
+    "tag_string_general": "2boys bat_(animal) black_bodysuit bodysuit brown_eyes closed_mouth collared_shirt copyright_name expressionless facepaint glasgow_smile male_focus multiple_boys outline outstretched_arm parted_lips pink_shirt shirt sketch smile upper_body white_outline wing_collar",
+    "tag_string_meta": "commentary_request photoshop_(medium)",
+    "tags": [
+        "2boys",
+        "bat_(animal)",
+        "batman",
+        "batman_(series)",
+        "black_bodysuit",
+        "bodysuit",
+        "bonocho",
+        "brown_eyes",
+        "closed_mouth",
+        "collared_shirt",
+        "commentary_request",
+        "copyright_name",
+        "dc_comics",
+        "expressionless",
+        "facepaint",
+        "glasgow_smile",
+        "heath_ledger",
+        "joker_(dc)",
+        "male_focus",
+        "multiple_boys",
+        "outline",
+        "outstretched_arm",
+        "parted_lips",
+        "photoshop_(medium)",
+        "pink_shirt",
+        "shirt",
+        "sketch",
+        "smile",
+        "the_dark_knight",
+        "upper_body",
+        "white_outline",
+        "wing_collar",
+    ],
+    "tags_artist": [
+        "bonocho",
+    ],
+    "tags_character": [
+        "batman",
+        "heath_ledger",
+        "joker_(dc)",
+    ],
+    "tags_copyright": [
+        "batman_(series)",
+        "dc_comics",
+        "the_dark_knight",
+    ],
+    "tags_general": [
+        "2boys",
+        "bat_(animal)",
+        "black_bodysuit",
+        "bodysuit",
+        "brown_eyes",
+        "closed_mouth",
+        "collared_shirt",
+        "copyright_name",
+        "expressionless",
+        "facepaint",
+        "glasgow_smile",
+        "male_focus",
+        "multiple_boys",
+        "outline",
+        "outstretched_arm",
+        "parted_lips",
+        "pink_shirt",
+        "shirt",
+        "sketch",
+        "smile",
+        "upper_body",
+        "white_outline",
+        "wing_collar",
+    ],
+    "tags_meta": [
+        "commentary_request",
+        "photoshop_(medium)",
+    ],
+    "up_score": range(1, 5),
+    "updated_at": "2022-07-11T23:42:31.881-04:00",
+    "uploader_id": 67005,
 },
 
 {