[exhentai] implement 'tags' option (#2117)

allow splitting tags into categories,
e.g. 'tags_parody', 'tags_group', etc.

gallery_dl/extractor/exhentai.py

@@ -11,6 +11,7 @@
 from .common import Extractor, Message
 from .. import text, util, exception
 from ..cache import cache
+import collections
 import itertools
 import math
 
@@ -227,6 +228,13 @@ class ExhentaiGalleryExtractor(ExhentaiExtractor):
         if self.config("metadata", False):
             data.update(self.metadata_from_api())
             data["date"] = text.parse_timestamp(data["posted"])
+        if self.config("tags", False):
+            tags = collections.defaultdict(list)
+            for tag in data["tags"]:
+                type, _, value = tag.partition(":")
+                tags[type].append(value)
+            for type, values in tags.items():
+                data["tags_" + type] = values
         return data
 
     def metadata_from_page(self, page):

test/results/exhentai.py

@@ -13,7 +13,7 @@ __tests__ = (
     "#url"     : "https://exhentai.org/g/1200119/d55c44d3d0/",
     "#category": ("", "exhentai", "gallery"),
     "#class"   : exhentai.ExhentaiGalleryExtractor,
-    "#options"     : {"original": False},
+    "#options"     : {"original": False, "tags": True},
     "#sha1_content": [
         "2c68cff8a7ca540a78c36fdbf5fbae0260484f87",
         "e9891a4c017ed0bb734cd1efba5cd03f594d31ff",
@@ -40,6 +40,10 @@ __tests__ = (
         "group:seventh lowlife",
         "other:sample",
     ],
+    "tags_parody" : ["komi-san wa komyushou desu."],
+    "tags_character": ["shouko komi"],
+    "tags_group"  : ["seventh lowlife"],
+    "tags_other"  : ["sample"],
     "thumb"       : "https://s.exhentai.org/t/ce/0a/ce0a5bcb583229a9b07c0f83bcb1630ab1350640-624622-736-1036-jpg_250.jpg",
     "title"       : "C93 [Seventh_Lowlife] Komi-san ha Tokidoki Daitan desu (Komi-san wa Komyushou desu) [Sample]",
     "title_jpn"   : "(C93) [Comiketjack (わ！)] 古見さんは、時々大胆です。 (古見さんは、コミュ症です。) [見本]",