[wikimedia] combine most wikimedia.org sites (#1443)

add wikidata.org and wikivoyage.org

docs/supportedsites.md

@@ -124,7 +124,7 @@ Consider all listed sites to potentially be NSFW.
 <tr>
     <td>Bluesky</td>
     <td>https://bsky.app/</td>
-    <td>Likes, Media Files, Posts, Replies, User Profiles</td>
+    <td>Feeds, Followed Users, Likes, Lists, Media Files, Posts, Replies, User Profiles</td>
     <td>Supported</td>
 </tr>
 <tr>
@@ -1470,44 +1470,8 @@ Consider all listed sites to potentially be NSFW.
     <td colspan="4"><strong>Wikimedia Instances</strong></td>
 </tr>
 <tr>
-    <td>Wikipedia</td>
+    <td>Wikimedia</td>
-    <td>https://www.wikipedia.org/</td>
+    <td>https://www.wikimedia.org/</td>
-    <td>Articles</td>
-    <td></td>
-</tr>
-<tr>
-    <td>Wiktionary</td>
-    <td>https://www.wiktionary.org/</td>
-    <td>Articles</td>
-    <td></td>
-</tr>
-<tr>
-    <td>Wikiquote</td>
-    <td>https://www.wikiquote.org/</td>
-    <td>Articles</td>
-    <td></td>
-</tr>
-<tr>
-    <td>Wikibooks</td>
-    <td>https://www.wikibooks.org/</td>
-    <td>Articles</td>
-    <td></td>
-</tr>
-<tr>
-    <td>Wikisource</td>
-    <td>https://www.wikisource.org/</td>
-    <td>Articles</td>
-    <td></td>
-</tr>
-<tr>
-    <td>Wikinews</td>
-    <td>https://www.wikinews.org/</td>
-    <td>Articles</td>
-    <td></td>
-</tr>
-<tr>
-    <td>Wikiversity</td>
-    <td>https://www.wikiversity.org/</td>
     <td>Articles</td>
     <td></td>
 </tr>

gallery_dl/extractor/wikimedia.py

@@ -25,7 +25,9 @@ class WikimediaExtractor(BaseExtractor):
         BaseExtractor.__init__(self, match)
         path = match.group(match.lastindex)
 
-        if self.category == "fandom":
+        if self.category == "wikimedia":
+            self.category = self.root.split(".")[-2]
+        elif self.category == "fandom":
             self.category = \
                 "fandom-" + self.root.partition(".")[0].rpartition("/")[2]
 
@@ -119,39 +121,12 @@ class WikimediaExtractor(BaseExtractor):
 
 
 BASE_PATTERN = WikimediaExtractor.update({
-    "wikipedia": {
+    "wikimedia": {
         "root": None,
-        "pattern": r"[a-z]{2,}\.wikipedia\.org",
+        "pattern": r"[a-z]{2,}\."
-        "api-path": "/w/api.php",
+                   r"wik(?:i(?:pedia|quote|books|source|news|versity|data"
-    },
+                   r"|voyage)|tionary)"
-    "wiktionary": {
+                   r"\.org",
-        "root": None,
-        "pattern": r"[a-z]{2,}\.wiktionary\.org",
-        "api-path": "/w/api.php",
-    },
-    "wikiquote": {
-        "root": None,
-        "pattern": r"[a-z]{2,}\.wikiquote\.org",
-        "api-path": "/w/api.php",
-    },
-    "wikibooks": {
-        "root": None,
-        "pattern": r"[a-z]{2,}\.wikibooks\.org",
-        "api-path": "/w/api.php",
-    },
-    "wikisource": {
-        "root": None,
-        "pattern": r"[a-z]{2,}\.wikisource\.org",
-        "api-path": "/w/api.php",
-    },
-    "wikinews": {
-        "root": None,
-        "pattern": r"[a-z]{2,}\.wikinews\.org",
-        "api-path": "/w/api.php",
-    },
-    "wikiversity": {
-        "root": None,
-        "pattern": r"[a-z]{2,}\.wikiversity\.org",
         "api-path": "/w/api.php",
     },
     "wikispecies": {

scripts/supportedsites.py

@@ -325,7 +325,8 @@ BASE_MAP = {
 }
 
 URL_MAP = {
-    "blogspot": "https://www.blogger.com/",
+    "blogspot" : "https://www.blogger.com/",
+    "wikimedia": "https://www.wikimedia.org/",
 }
 
 _OAUTH = '<a href="https://github.com/mikf/gallery-dl#oauth">OAuth</a>'

test/results/wikidata.py

@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+from gallery_dl.extractor import wikimedia
+
+
+__tests__ = (
+{
+    "#url"     : "https://www.wikidata.org/wiki/Title",
+    "#category": ("wikimedia", "wikidata", "article"),
+    "#class"   : wikimedia.WikimediaArticleExtractor,
+},
+
+{
+    "#url"     : "https://en.wikidata.org/wiki/Category:Title",
+    "#category": ("wikimedia", "wikidata", "category"),
+    "#class"   : wikimedia.WikimediaArticleExtractor,
+},
+
+)

test/results/wikivoyage.py

@@ -0,0 +1,23 @@
+# -*- coding: utf-8 -*-
+
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2 as
+# published by the Free Software Foundation.
+
+from gallery_dl.extractor import wikimedia
+
+
+__tests__ = (
+{
+    "#url"     : "https://www.wikivoyage.org/wiki/Title",
+    "#category": ("wikimedia", "wikivoyage", "article"),
+    "#class"   : wikimedia.WikimediaArticleExtractor,
+},
+
+{
+    "#url"     : "https://en.wikivoyage.org/wiki/Category:Title",
+    "#category": ("wikimedia", "wikivoyage", "category"),
+    "#class"   : wikimedia.WikimediaArticleExtractor,
+},
+
+)