[koharu] add 'gallery' and 'search' extractors (#5893, #4707)

docs/configuration.rst

@@ -2605,6 +2605,32 @@ Description
     the first in the list gets chosen (usually `mp3`).
 
 
+extractor.koharu.cbz
+--------------------
+Type
+    ``bool``
+Default
+    ``true``
+Description
+    Download each gallery as a single ``.cbz`` file.
+
+    Disabling this option causes a gallery
+    to be downloaded as individual image files.
+
+
+extractor.koharu.format
+-----------------------
+Type
+    ``string``
+Default
+    ``"original"``
+Description
+    Name of the image format to download.
+
+    | Available formats are
+    | ``"780"``, ``"980"``, ``"1280"``, ``"1600"``, ``"0"``/``"original"``
+
+
 extractor.lolisafe.domain
 -------------------------
 Type

docs/supportedsites.md

@@ -475,6 +475,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Soundtracks</td>
     <td></td>
 </tr>
+<tr>
+    <td>Koharu</td>
+    <td>https://koharu.to/</td>
+    <td>Galleries, Search Results</td>
+    <td></td>
+</tr>
 <tr>
     <td>Komikcast</td>
     <td>https://komikcast.lol/</td>

gallery_dl/extractor/__init__.py

@@ -85,6 +85,7 @@ modules = [
     "keenspot",
     "kemonoparty",
     "khinsider",
+    "koharu",
     "komikcast",
     "lensdump",
     "lexica",

gallery_dl/extractor/koharu.py

@@ -0,0 +1,146 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2024 Mike Fährmann
+#
+# 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://koharu.to/"""
+
+from .common import GalleryExtractor, Extractor, Message
+from .. import text, exception
+
+BASE_PATTERN = r"(?i)(?:https?://)?(?:koharu|anchira)\.to"
+
+
+class KoharuGalleryExtractor(GalleryExtractor):
+    """Extractor for koharu galleries"""
+    category = "koharu"
+    root = "https://koharu.to"
+    root_api = "https://api.koharu.to"
+    filename_fmt = "{num:>03}.{extension}"
+    directory_fmt = ("{category}", "{id} {title}")
+    archive_fmt = "{id}_{num}"
+    pattern = BASE_PATTERN + r"/(?:g|reader)/(\d+)/(\w+)"
+    example = "https://koharu.to/g/12345/67890abcde/"
+
+    def __init__(self, match):
+        GalleryExtractor.__init__(self, match)
+        self.gallery_url = None
+
+    def _init(self):
+        self.headers = {
+            "Accept" : "*/*",
+            "Referer": self.root + "/",
+            "Origin" : self.root,
+        }
+
+        self.fmt = self.config("format")
+        self.cbz = self.config("cbz", True)
+
+        if self.cbz:
+            self.filename_fmt = "{id} {title}.{extension}"
+            self.directory_fmt = ("{category}",)
+
+    def metadata(self, _):
+        url = "{}/books/detail/{}/{}".format(
+            self.root_api, self.groups[0], self.groups[1])
+        self.data = data = self.request(url, headers=self.headers).json()
+        data.pop("rels", None)
+        data.pop("thumbnails", None)
+        return data
+
+    def images(self, _):
+        data = self.data
+        fmt = self._select_format(data["data"])
+
+        url = "{}/books/data/{}/{}/{}/{}".format(
+            self.root_api,
+            data["id"], data["public_key"],
+            fmt["id"], fmt["public_key"],
+        )
+        params = {
+            "v": data["updated_at"],
+            "w": fmt["w"],
+        }
+
+        if self.cbz:
+            params["action"] = "dl"
+            base = self.request(
+                url, method="POST", params=params, headers=self.headers,
+            ).json()["base"]
+            url = "{}?v={}&w={}".format(base, data["updated_at"], fmt["w"])
+            info = text.nameext_from_url(base)
+            if not info["extension"]:
+                info["extension"] = "cbz"
+            return ((url, info),)
+
+        data = self.request(url, params=params, headers=self.headers).json()
+        base = data["base"]
+
+        results = []
+        for entry in data["entries"]:
+            dimensions = entry["dimensions"]
+            info = {"w": dimensions[0], "h": dimensions[1]}
+            results.append((base + entry["path"], info))
+        return results
+
+    def _select_format(self, formats):
+        if not self.fmt or self.fmt == "original":
+            fmtid = "0"
+        else:
+            fmtid = str(self.fmt)
+
+        try:
+            fmt = formats[fmtid]
+        except KeyError:
+            raise exception.NotFoundError("format")
+
+        fmt["w"] = fmtid
+        return fmt
+
+
+class KoharuSearchExtractor(Extractor):
+    """Extractor for koharu search results"""
+    category = "koharu"
+    subcategory = "search"
+    root = "https://koharu.to"
+    root_api = "https://api.koharu.to"
+    request_interval = (1.0, 2.0)
+    pattern = BASE_PATTERN + r"/\?([^#]*)"
+    example = "https://koharu.to/?s=QUERY"
+
+    def _init(self):
+        self.headers = {
+            "Accept" : "*/*",
+            "Referer": self.root + "/",
+            "Origin" : self.root,
+        }
+
+    def items(self):
+        url_api = self.root_api + "/books"
+        params = text.parse_query(self.groups[0])
+        params["page"] = text.parse_int(params.get("page"), 1)
+
+        while True:
+            data = self.request(
+                url_api, params=params, headers=self.headers).json()
+
+            try:
+                entries = data["entries"]
+            except KeyError:
+                return
+
+            for entry in entries:
+                url = "{}/g/{}/{}/".format(
+                    self.root, entry["id"], entry["public_key"])
+                entry["_extractor"] = KoharuGalleryExtractor
+                yield Message.Queue, url, entry
+
+            try:
+                if data["limit"] * data["page"] >= data["total"]:
+                    return
+            except Exception:
+                pass
+            params["page"] += 1

test/results/koharu.py

@@ -0,0 +1,60 @@
+# -*- 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 koharu
+
+
+__tests__ = (
+{
+    "#url"     : "https://koharu.to/g/14216/6c67076fdd45",
+    "#category": ("", "koharu", "gallery"),
+    "#class"   : koharu.KoharuGalleryExtractor,
+    "#pattern" : r"https://kisakisexo.xyz/download/59896/a4fbd1828229/f47639c6abaf1903dd69c36a3d961da84741a1831aa07a2906ce9c74156a5d75\?v=1721626410802&w=0",
+    "#count"   : 1,
+
+    "count"     : 1,
+    "created_at": 1721626410802,
+    "extension" : "cbz",
+    "filename"  : "f47639c6abaf1903dd69c36a3d961da84741a1831aa07a2906ce9c74156a5d75",
+    "id"        : 14216,
+    "num"       : 1,
+    "public_key": "6c67076fdd45",
+    "tags"      : list,
+    "title"     : "[Ouchi Kaeru] Summer Business (Comic Kairakuten 2024-08)",
+    "updated_at": 1721626410802,
+},
+
+{
+    "#url"     : "https://koharu.to/g/14216/6c67076fdd45",
+    "#category": ("", "koharu", "gallery"),
+    "#class"   : koharu.KoharuGalleryExtractor,
+    "#options" : {"cbz": False, "format": "780"},
+    "#pattern" : r"https://koharusexo.xyz/data/59905/2df9110af7f1/a7cbeca3fb9c83aa87582a8a74cc8f8ce1b9e9b434dc1af293628871642f42df/[0-9a-f]+/.+",
+    "#count"   : 22,
+
+},
+
+{
+    "#url"     : "https://anchira.to/g/14216/6c67076fdd45",
+    "#category": ("", "koharu", "gallery"),
+    "#class"   : koharu.KoharuGalleryExtractor,
+},
+
+{
+    "#url"     : "https://koharu.to/reader/14216/6c67076fdd45",
+    "#category": ("", "koharu", "gallery"),
+    "#class"   : koharu.KoharuGalleryExtractor,
+},
+
+{
+    "#url"     : "https://koharu.to/?s=tag:^beach$",
+    "#category": ("", "koharu", "search"),
+    "#class"   : koharu.KoharuSearchExtractor,
+    "#pattern" : koharu.KoharuGalleryExtractor.pattern,
+    "#count"   : ">= 50",
+},
+
+)