[wikimedia] generalize (#1443)

- support mediawiki.org - support mariowiki.com (#3660) - combine code into a single extractor (use prefix as subcategory) - handle non-wiki instances - unescape titles
2024-01-18 15:36:16 +01:00
parent 89066844f4
commit ea553a1d55
14 changed files with 126 additions and 47 deletions
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -1484,55 +1484,67 @@ Consider all listed sites to potentially be NSFW.
 <tr>
    <td>Wikipedia</td>
    <td>https://www.wikipedia.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wiktionary</td>
    <td>https://www.wiktionary.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikiquote</td>
    <td>https://www.wikiquote.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikibooks</td>
    <td>https://www.wikibooks.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikisource</td>
    <td>https://www.wikisource.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikinews</td>
    <td>https://www.wikinews.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikiversity</td>
    <td>https://www.wikiversity.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikispecies</td>
    <td>https://species.wikimedia.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
    <td></td>
 </tr>
 <tr>
    <td>Wikimedia Commons</td>
    <td>https://commons.wikimedia.org/</td>
-    <td>Articles, Categories</td>
+    <td>Articles</td>
+    <td></td>
+</tr>
+<tr>
+    <td>MediaWiki</td>
+    <td>https://www.mediawiki.org/</td>
+    <td>Articles</td>
+    <td></td>
+</tr>
+<tr>
+    <td>Super Mario Wiki</td>
+    <td>https://www.mariowiki.com/</td>
+    <td>Articles</td>
    <td></td>
 </tr>

--- a/gallery_dl/extractor/wikimedia.py
+++ b/gallery_dl/extractor/wikimedia.py
@@ -7,7 +7,7 @@
 # it under the terms of the GNU General Public License version 2 as
 # published by the Free Software Foundation.

-"""Extractors for Wikimedia and Wikipedia"""
+"""Extractors for Wikimedia sites"""

 from .common import BaseExtractor, Message
 from .. import text
@@ -22,7 +22,41 @@ class WikimediaExtractor(BaseExtractor):

    def __init__(self, match):
        BaseExtractor.__init__(self, match)
-        self.title = match.group(match.lastindex)
+        path = match.group(match.lastindex)
+
+        if path.startswith("wiki/"):
+            path = path[5:]
+            self.api_path = "/w/api.php"
+        else:
+            self.api_path = "/api.php"
+
+        pre, sep, _ = path.partition(":")
+        prefix = pre.lower() if sep else None
+
+        self.title = path = text.unquote(path)
+        self.subcategory = prefix
+
+        if prefix == "category":
+            self.params = {
+                "generator": "categorymembers",
+                "gcmtitle" : path,
+                "gcmtype"  : "file",
+            }
+        else:
+            self.params = {
+                "generator": "images",
+                "titles"   : path,
+            }
+
+    def _init(self):
+        api_path = self.config_instance("api-path")
+        if api_path:
+            if api_path[0] == "/":
+                self.api_url = self.root + api_path
+            else:
+                self.api_url = api_path
+        else:
+            self.api_url = self.root + self.api_path

    def items(self):
        for info in self._pagination(self.params):
@@ -51,9 +85,14 @@ class WikimediaExtractor(BaseExtractor):
        https://opendata.stackexchange.com/questions/13381
        """

-        url = self.root + "/w/api.php"
+        url = self.api_url
        params["action"] = "query"
        params["format"] = "json"
+        params["prop"] = "imageinfo"
+        params["iiprop"] = (
+            "timestamp|user|userid|comment|canonicaltitle|url|size|"
+            "sha1|mime|metadata|commonmetadata|extmetadata|bitdepth"
+        )

        while True:
            data = self.request(url, params=params).json()
@@ -109,36 +148,19 @@ BASE_PATTERN = WikimediaExtractor.update({
        "root": "https://commons.wikimedia.org",
        "pattern": r"commons\.wikimedia\.org",
    },
+    "mediawiki": {
+        "root": "https://www.mediawiki.org",
+        "pattern": r"(?:www\.)?mediawiki\.org",
+    },
+    "mariowiki": {
+        "root": "https://www.mariowiki.com",
+        "pattern": r"(?:www\.)?mariowiki\.com",
+    },
 })


 class WikimediaArticleExtractor(WikimediaExtractor):
    """Extractor for wikimedia articles"""
    subcategory = "article"
-    pattern = BASE_PATTERN + r"/wiki/(?!Category:)([^/?#]+)"
+    pattern = BASE_PATTERN + r"/(?!static/)([^?#]+)"
    example = "https://en.wikipedia.org/wiki/TITLE"
-
-    def _init(self):
-        self.params = {
-            "generator": "images",
-            "titles"   : self.title,
-            "prop"     : "imageinfo",
-            "iiprop": "timestamp|user|userid|comment|canonicaltitle|url|size|"
-                      "sha1|mime|metadata|commonmetadata|extmetadata|bitdepth",
-        }
-
-
-class WikimediaCategoryExtractor(WikimediaExtractor):
-    subcategory = "category"
-    pattern = BASE_PATTERN + r"/wiki/(Category:[^/?#]+)"
-    example = "https://commons.wikimedia.org/wiki/Category:NAME"
-
-    def _init(self):
-        self.params = {
-            "generator": "categorymembers",
-            "gcmtitle" : self.title,
-            "gcmtype"  : "file",
-            "prop"     : "imageinfo",
-            "iiprop": "timestamp|user|userid|comment|canonicaltitle|url|size|"
-                      "sha1|mime|metadata|commonmetadata|extmetadata|bitdepth",
-        }
--- a/scripts/supportedsites.py
+++ b/scripts/supportedsites.py
@@ -88,7 +88,9 @@ CATEGORY_MAP = {
    "mangapark"      : "MangaPark",
    "mangaread"      : "MangaRead",
    "mangasee"       : "MangaSee",
+    "mariowiki"      : "Super Mario Wiki",
    "mastodon.social": "mastodon.social",
+    "mediawiki"      : "MediaWiki",
    "micmicidol"     : "MIC MIC IDOL",
    "myhentaigallery": "My Hentai Gallery",
    "myportfolio"    : "Adobe Portfolio",
--- a/test/results/mariowiki.py
+++ b/test/results/mariowiki.py
@@ -0,0 +1,19 @@
+# -*- 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.mariowiki.com/Rabbit",
+    "#category": ("wikimedia", "wikibooks", "article"),
+    "#class"   : wikimedia.WikimediaArticleExtractor,
+    "#pattern" : r"https://mario\.wiki\.gallery/images/.+",
+    "#count"   : range(20, 50),
+},
+
+)
--- a/test/results/mediawiki.py
+++ b/test/results/mediawiki.py
@@ -0,0 +1,24 @@
+# -*- 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.mediawiki.org/wiki/Help:Navigation",
+    "#category": ("wikimedia", "mediawiki", "help"),
+    "#class"   : wikimedia.WikimediaArticleExtractor,
+    "#urls"    : (
+        "https://upload.wikimedia.org/wikipedia/commons/e/ec/OOjs_UI_icon_information-progressive.svg",
+        "https://upload.wikimedia.org/wikipedia/commons/6/62/PD-icon.svg",
+        "https://upload.wikimedia.org/wikipedia/commons/0/0e/Vector_Sidebar.png",
+        "https://upload.wikimedia.org/wikipedia/commons/7/77/Vector_page_tabs.png",
+        "https://upload.wikimedia.org/wikipedia/commons/6/6e/Vector_user_links.png",
+    ),
+},
+
+)
--- a/test/results/wikibooks.py
+++ b/test/results/wikibooks.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wikibooks.org/wiki/Category:Title",
    "#category": ("wikimedia", "wikibooks", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikimediacommons.py
+++ b/test/results/wikimediacommons.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://commons.wikimedia.org/wiki/Category:Network_maps_of_the_Paris_Metro",
    "#category": ("wikimedia", "wikimediacommons", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikinews.py
+++ b/test/results/wikinews.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wikinews.org/wiki/Category:Title",
    "#category": ("wikimedia", "wikinews", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikipedia.py
+++ b/test/results/wikipedia.py
@@ -47,7 +47,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wikipedia.org/wiki/Category:Physics",
    "#category": ("wikimedia", "wikipedia", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikiquote.py
+++ b/test/results/wikiquote.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wikiquote.org/wiki/Category:Title",
    "#category": ("wikimedia", "wikiquote", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikisource.py
+++ b/test/results/wikisource.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wikisource.org/wiki/Category:Title",
    "#category": ("wikimedia", "wikisource", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikispecies.py
+++ b/test/results/wikispecies.py
@@ -19,7 +19,7 @@ __tests__ = (
 {
    "#url"     : "https://species.wikimedia.org/wiki/Category:Names",
    "#category": ("wikimedia", "wikispecies", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wikiversity.py
+++ b/test/results/wikiversity.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wikiversity.org/wiki/Category:Title",
    "#category": ("wikimedia", "wikiversity", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )
--- a/test/results/wiktionary.py
+++ b/test/results/wiktionary.py
@@ -17,7 +17,7 @@ __tests__ = (
 {
    "#url"     : "https://en.wiktionary.org/wiki/Category:Words",
    "#category": ("wikimedia", "wiktionary", "category"),
-    "#class"   : wikimedia.WikimediaCategoryExtractor,
+    "#class"   : wikimedia.WikimediaArticleExtractor,
 },

 )