[lynxchan] add generic extractors for lynxchan imageboards (#3394)

* [lynxchan] add generic extractors for lynxchan imageboards

includes kohlchan.net, endchan.org:wq

* [lynxchan] set pop default to empty tuple

* Apply suggestions from code review

Co-authored-by: Mike Fährmann <mike_faehrmann@web.de>

docs/supportedsites.md

@@ -433,12 +433,6 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Soundtracks</td>
     <td></td>
 </tr>
-<tr>
-    <td>Kohlchan</td>
-    <td>https://kohlchan.net/</td>
-    <td>Boards, Threads</td>
-    <td></td>
-</tr>
 <tr>
     <td>Komikcast</td>
     <td>https://komikcast.site/</td>
@@ -1046,6 +1040,22 @@ Consider all sites to be NSFW unless otherwise known.
     <td></td>
 </tr>
 
+<tr>
+    <td colspan="4"><strong>LynxChan Imageboards</strong></td>
+</tr>
+<tr>
+    <td>Kohlchan</td>
+    <td>https://kohlchan.net/</td>
+    <td>Boards, Threads</td>
+    <td></td>
+</tr>
+<tr>
+    <td>Endchan</td>
+    <td>https://endchan.org/</td>
+    <td>Boards, Threads</td>
+    <td></td>
+</tr>
+
 <tr>
     <td colspan="4"><strong>Nijie Instances</strong></td>
 </tr>

gallery_dl/extractor/__init__.py

@@ -74,12 +74,12 @@ modules = [
     "keenspot",
     "kemonoparty",
     "khinsider",
-    "kohlchan",
     "komikcast",
     "lightroom",
     "lineblog",
     "livedoor",
     "luscious",
+    "lynxchan",
     "mangadex",
     "mangafox",
     "mangahere",

gallery_dl/extractor/kohlchan.py

@@ -1,78 +0,0 @@
-# -*- 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.
-
-"""Extractors for https://kohlchan.net/"""
-
-from .common import Extractor, Message
-from .. import text
-import itertools
-
-
-class KohlchanThreadExtractor(Extractor):
-    """Extractor for Kohlchan threads"""
-    category = "kohlchan"
-    subcategory = "thread"
-    directory_fmt = ("{category}", "{boardUri}",
-                     "{threadId} {subject|message[:50]}")
-    filename_fmt = "{postId}{num:?-//} {filename}.{extension}"
-    archive_fmt = "{boardUri}_{postId}_{num}"
-    pattern = r"(?:https?://)?kohlchan\.net/([^/?#]+)/res/(\d+)"
-    test = ("https://kohlchan.net/a/res/4594.html", {
-        "pattern": r"https://kohlchan\.net/\.media/[0-9a-f]{64}(\.\w+)?$",
-        "count": ">= 80",
-    })
-
-    def __init__(self, match):
-        Extractor.__init__(self, match)
-        self.board, self.thread = match.groups()
-
-    def items(self):
-        url = "https://kohlchan.net/{}/res/{}.json".format(
-            self.board, self.thread)
-        thread = self.request(url).json()
-        thread["postId"] = thread["threadId"]
-        posts = thread.pop("posts")
-
-        yield Message.Directory, thread
-
-        for post in itertools.chain((thread,), posts):
-            files = post.pop("files", ())
-            if files:
-                thread.update(post)
-                for num, file in enumerate(files):
-                    file.update(thread)
-                    file["num"] = num
-                    url = "https://kohlchan.net" + file["path"]
-                    text.nameext_from_url(file["originalName"], file)
-                    yield Message.Url, url, file
-
-
-class KohlchanBoardExtractor(Extractor):
-    """Extractor for Kohlchan boards"""
-    category = "kohlchan"
-    subcategory = "board"
-    pattern = (r"(?:https?://)?kohlchan\.net"
-               r"/([^/?#]+)/(?:(?:catalog|\d+)\.html)?$")
-    test = (
-        ("https://kohlchan.net/a/", {
-            "pattern": KohlchanThreadExtractor.pattern,
-            "count": ">= 100",
-        }),
-        ("https://kohlchan.net/a/2.html"),
-        ("https://kohlchan.net/a/catalog.html"),
-    )
-
-    def __init__(self, match):
-        Extractor.__init__(self, match)
-        self.board = match.group(1)
-
-    def items(self):
-        url = "https://kohlchan.net/{}/catalog.json".format(self.board)
-        for thread in self.request(url).json():
-            url = "https://kohlchan.net/{}/res/{}.html".format(
-                self.board, thread["threadId"])
-            thread["_extractor"] = KohlchanThreadExtractor
-            yield Message.Queue, url, thread

gallery_dl/extractor/lynxchan.py

@@ -0,0 +1,104 @@
+# -*- 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.
+
+"""Extractors for LynxChan Imageboards"""
+
+from .common import BaseExtractor, Message
+from .. import text
+import itertools
+
+
+class LynxchanExtractor(BaseExtractor):
+    """Base class for LynxChan extractors"""
+    basecategory = "lynxchan"
+
+
+BASE_PATTERN = LynxchanExtractor.update({
+    "kohlchan": {
+        "root": "https://kohlchan.net",
+        "pattern": r"kohlchan\.net"
+    },
+    "endchan": {
+        "root": None,
+        "pattern": r"endchan\.(?:org|net|gg)",
+    },
+})
+
+
+class LynxchanThreadExtractor(LynxchanExtractor):
+    """Extractor for LynxChan threads"""
+    subcategory = "thread"
+    directory_fmt = ("{category}", "{boardUri}",
+                     "{threadId} {subject|message[:50]}")
+    filename_fmt = "{postId}{num:?-//} {filename}.{extension}"
+    archive_fmt = "{boardUri}_{postId}_{num}"
+    pattern = BASE_PATTERN + r"/([^/?#]+)/res/(\d+)"
+    test = (
+        ("https://kohlchan.net/a/res/4594.html", {
+            "pattern": r"https://kohlchan\.net/\.media/[0-9a-f]{64}(\.\w+)?$",
+            "count": ">= 80",
+        }),
+        ("https://endchan.org/yuri/res/193483.html", {
+            "pattern": r"https://endchan\.org/\.media/[^.]+(\.\w+)?$",
+            "count"  : ">= 19",
+        }),
+        ("https://endchan.org/yuri/res/33621.html"),
+    )
+
+    def __init__(self, match):
+        LynxchanExtractor.__init__(self, match)
+        index = match.lastindex
+        self.board = match.group(index-1)
+        self.thread = match.group(index)
+
+    def items(self):
+        url = "{}/{}/res/{}.json".format(self.root, self.board, self.thread)
+        thread = self.request(url).json()
+        thread["postId"] = thread["threadId"]
+        posts = thread.pop("posts", ())
+
+        yield Message.Directory, thread
+        for post in itertools.chain((thread,), posts):
+            files = post.pop("files", ())
+            if files:
+                thread.update(post)
+                for num, file in enumerate(files):
+                    file.update(thread)
+                    file["num"] = num
+                    url = self.root + file["path"]
+                    text.nameext_from_url(file["originalName"], file)
+                    yield Message.Url, url, file
+
+
+class LynxchanBoardExtractor(LynxchanExtractor):
+    """Extractor for LynxChan boards"""
+    subcategory = "board"
+    pattern = BASE_PATTERN + r"/([^/?#]+)(?:/index|/catalog|/\d+|/?$)"
+    test = (
+        ("https://kohlchan.net/a/", {
+            "pattern": LynxchanThreadExtractor.pattern,
+            "count": ">= 100",
+        }),
+        ("https://kohlchan.net/a/2.html"),
+        ("https://kohlchan.net/a/catalog.html"),
+        ("https://endchan.org/yuri/", {
+            "pattern": LynxchanThreadExtractor.pattern,
+            "count"  : ">= 9",
+        }),
+        ("https://endchan.org/yuri/catalog.html"),
+    )
+
+    def __init__(self, match):
+        LynxchanExtractor.__init__(self, match)
+        self.board = match.group(match.lastindex)
+
+    def items(self):
+        url = "{}/{}/catalog.json".format(self.root, self.board)
+        for thread in self.request(url).json():
+            url = "{}/{}/res/{}.html".format(
+                self.root, self.board, thread["threadId"])
+            thread["_extractor"] = LynxchanThreadExtractor
+            yield Message.Queue, url, thread

scripts/supportedsites.py

@@ -251,6 +251,7 @@ BASE_MAP = {
     "gelbooru_v01": "Gelbooru Beta 0.1.11",
     "gelbooru_v02": "Gelbooru Beta 0.2",
     "lolisafe"    : "lolisafe and chibisafe",
+    "lynxchan"    : "LynxChan Imageboards",
     "moebooru"    : "Moebooru and MyImouto",
     "vichan"      : "vichan Imageboards",
 }