[batoto] add 'domain' option (#7174)

allow legacy domains by default

docs/configuration.rst

@@ -1459,6 +1459,29 @@ Description
     * ``false``: Get posts from "Latest Updates" pages
 
 
+extractor.batoto.domain
+-----------------------
+Type
+    ``string``
+Default
+    ``"auto"``
+Example
+    ``"mangatoto.org"``
+Description
+    Specifies the domain used by ``batoto`` extractors.
+
+    ``"auto"`` | ``"url"``
+        Use the input URL's domain
+    ``"nolegacy"``
+        Use the input URL's domain
+        - replace legacy domains with ``"xbato.org"``
+    ``"nowarn"``
+        Use the input URL's domain
+        - do not warn about legacy domains
+    any ``string``
+        Use this domain
+
+
 extractor.bbc.width
 -------------------
 Type

docs/gallery-dl.conf

@@ -117,6 +117,10 @@
 
             "recursive": true
         },
+        "batoto":
+        {
+            "domain": "auto"
+        },
         "bbc":
         {
             "width": 1920

gallery_dl/extractor/batoto.py

@@ -54,11 +54,23 @@ class BatotoBase():
     """Base class for batoto extractors"""
     category = "batoto"
     root = "https://xbato.org"
+    _warn_legacy = True
 
-    def _init_root(self, match):
-        domain = match.group(1)
-        if domain not in LEGACY_DOMAINS:
-            self.root = "https://" + domain
+    def _init_root(self):
+        domain = self.config("domain")
+        if domain is None or domain in {"auto", "url"}:
+            domain = self.groups[0]
+            if domain in LEGACY_DOMAINS:
+                if self._warn_legacy:
+                    BatotoBase._warn_legacy = False
+                    self.log.warning("Legacy domain '%s'", domain)
+        elif domain == "nolegacy":
+            domain = self.groups[0]
+            if domain in LEGACY_DOMAINS:
+                domain = "xbato.org"
+        elif domain == "nowarn":
+            domain = self.groups[0]
+        self.root = "https://" + domain
 
     def request(self, url, **kwargs):
         kwargs["encoding"] = "utf-8"
@@ -72,10 +84,10 @@ class BatotoChapterExtractor(BatotoBase, ChapterExtractor):
     example = "https://xbato.org/title/12345-MANGA/54321"
 
     def __init__(self, match):
-        self._init_root(match)
-        self.chapter_id = match.group(2)
-        url = "{}/title/0/{}".format(self.root, self.chapter_id)
-        ChapterExtractor.__init__(self, match, url)
+        ChapterExtractor.__init__(self, match, False)
+        self._init_root()
+        self.chapter_id = self.groups[1]
+        self.gallery_url = "{}/title/0/{}".format(self.root, self.chapter_id)
 
     def metadata(self, page):
         extr = text.extract_from(page)
@@ -133,10 +145,10 @@ class BatotoMangaExtractor(BatotoBase, MangaExtractor):
     example = "https://xbato.org/title/12345-MANGA/"
 
     def __init__(self, match):
-        self._init_root(match)
-        self.manga_id = match.group(2) or match.group(3)
-        url = "{}/title/{}".format(self.root, self.manga_id)
-        MangaExtractor.__init__(self, match, url)
+        MangaExtractor.__init__(self, match, False)
+        self._init_root()
+        self.manga_id = self.groups[1] or self.groups[2]
+        self.manga_url = "{}/title/{}".format(self.root, self.manga_id)
 
     def chapters(self, page):
         extr = text.extract_from(page)

test/results/batoto.py

@@ -109,6 +109,7 @@ __tests__ = (
     "#url"     : "https://bato.to/title/113742-futsutsuka-na-akujo-de-wa-gozaimasu-ga-suuguu-chouso-torikae-den-official",
     "#category": ("", "batoto", "manga"),
     "#class"   : batoto.BatotoMangaExtractor,
+    "#options" : {"domain": "xbato.org"},
     "#count"   : ">= 21",
 
     "chapter"      : int,