[audiochan] add initial support (#8602)

docs/supportedsites.md

@@ -121,6 +121,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Albums, Artwork Listings, Challenges, Collections, Followed Users, individual Images, Likes, Search Results, User Profiles</td>
     <td></td>
 </tr>
+<tr id="audiochan" title="audiochan">
+    <td>Audiochan</td>
+    <td>https://audiochan.com/</td>
+    <td>Audios, Collections, User Profiles</td>
+    <td></td>
+</tr>
 <tr id="batoto" title="batoto">
     <td>BATO.TO</td>
     <td>https://bato.to/</td>

gallery_dl/extractor/__init__.py

@@ -29,6 +29,7 @@ modules = [
     "arena",
     "artstation",
     "aryion",
+    "audiochan",
     "batoto",
     "bbc",
     "behance",

gallery_dl/extractor/audiochan.py

@@ -0,0 +1,115 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2025 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://audiochan.com/"""
+
+from .common import Extractor, Message
+from .. import text
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?audiochan\.com"
+
+
+class AudiochanExtractor(Extractor):
+    """Base class for audiochan extractors"""
+    category = "audiochan"
+    root = "https://audiochan.com"
+    root_api = "https://api.audiochan.com"
+    directory_fmt = ("{category}", "{user[display_name]}")
+    filename_fmt = "{title} ({slug}).{extension}"
+    archive_fmt = "{audioFile[id]}"
+
+    def _init(self):
+        self.headers_api = {
+            "content-type"   : "application/json",
+            "Origin"         : self.root,
+            "Sec-Fetch-Dest" : "empty",
+            "Sec-Fetch-Mode" : "cors",
+            "Sec-Fetch-Site" : "same-site",
+        }
+        self.headers_dl = {
+            "Accept": "audio/webm,audio/ogg,audio/wav,audio/*;q=0.9,"
+                      "application/ogg;q=0.7,video/*;q=0.6,*/*;q=0.5",
+            #  "Range"          : "bytes=0-",
+            "Sec-Fetch-Dest" : "audio",
+            "Sec-Fetch-Mode" : "no-cors",
+            "Sec-Fetch-Site" : "same-site",
+            "Accept-Encoding": "identity",
+        }
+
+    def items(self):
+        for post in self.posts():
+            file = post["audioFile"]
+
+            post["_http_headers"] = self.headers_dl
+            post["date"] = self.parse_datetime_iso(file["created_at"])
+            post["date_updated"] = self.parse_datetime_iso(file["updated_at"])
+            post["tags"] = [f"{tag['category']}:{tag['name']}"
+                            for tag in post["tags"]]
+
+            yield Message.Directory, post
+            text.nameext_from_name(file["filename"], post)
+            yield Message.Url, file["url"] or file["stream_url"], post
+
+    def request_api(self, endpoint, params=None):
+        url = self.root_api + endpoint
+        return self.request_json(url, params=params, headers=self.headers_api)
+
+    def _pagination(self, endpoint, params):
+        params["page"] = 1
+        params["limit"] = "12"
+
+        while True:
+            data = self.request_api(endpoint, params)
+
+            yield from data["data"]
+
+            if not data["has_more"]:
+                break
+            params["page"] += 1
+
+
+class AudiochanAudioExtractor(AudiochanExtractor):
+    subcategory = "audio"
+    pattern = rf"{BASE_PATTERN}/a/(\w+)"
+    example = "https://audiochan.com/a/SLUG"
+
+    def posts(self):
+        audio = self.request_api("/audios/slug/" + self.groups[0])
+        audio["user"] = audio["credits"][0]["user"]
+        return (audio,)
+
+
+class AudiochanUserExtractor(AudiochanExtractor):
+    subcategory = "user"
+    pattern = rf"{BASE_PATTERN}/u/(\w+)"
+    example = "https://audiochan.com/u/USER"
+
+    def posts(self):
+        endpoint = "/users/" + self.groups[0]
+        self.kwdict["user"] = self.request_api(endpoint)["data"]
+
+        params = {
+            "sfw_only": "false",
+            "sort"    : "new",
+        }
+        return self._pagination(endpoint + "/audios", params)
+
+
+class AudiochanCollectionExtractor(AudiochanExtractor):
+    subcategory = "collection"
+    pattern = rf"{BASE_PATTERN}/c/(\w+)"
+    example = "https://audiochan.com/c/SLUG"
+
+    def posts(self):
+        slug = self.groups[0]
+        endpoint = "/collections/" + slug
+        self.kwdict["collection"] = col = self.request_api(endpoint)
+        col.pop("audios", None)
+
+        endpoint = f"/collections/slug/{slug}/items"
+        return self._pagination(endpoint, {})

scripts/supportedsites.py

@@ -245,6 +245,9 @@ SUBCATEGORY_MAP = {
         "artwork": "Artwork Listings",
         "collections": "",
     },
+    "audiochan": {
+        "audio": "Audios",
+    },
     "bilibili": {
         "user-articles-favorite": "User Article Favorites",
     },

test/results/audiochan.py

@@ -0,0 +1,39 @@
+# -*- 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 audiochan
+
+
+__tests__ = (
+{
+    "#url"     : "https://audiochan.com/a/pBP1V1ODEV2od9CjLu",
+    "#class"   : audiochan.AudiochanAudioExtractor,
+    "#pattern" : r"https://stream.audiochan.com/v\?token=YXVkaW9zL2Q4YjA1ZWEzLWU0ZGItNGU2NC05MzZiLTQzNmI3MmM4OTViMS9sOTBCOFI0ajhjS0NFSmNwa2kubXAz&exp=\d+&st=\w+",
+    "#count"   : 1,
+},
+
+{
+    "#url"     : "https://audiochan.com/u/lil_lovergirl",
+    "#class"   : audiochan.AudiochanUserExtractor,
+    "#pattern" : r"https://stream\.audiochan\.com/v\?token=\w+\&exp=\d+\&st=\w+",
+    "#count"   : 35,
+},
+
+{
+    "#url"     : "https://audiochan.com/c/qzrByaXAwTLVXRgC9m",
+    "#class"   : audiochan.AudiochanCollectionExtractor,
+    "#results" : (
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/l90B8R4j8cKCEJcpki.mp3",
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/IPI4XoXS1Z1Qn7oEiN.mp3",
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/6kwizqnvUHttvUkXm6.mp3",
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/zn81mtgXslfDd20Tu8.wav",
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/Q33gP6yAg8jEM1C4Ic.mp3",
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/Fwy5YxgK4zc7sQ9xx3.mp3",
+        "https://content.audiochan.com/audios/d8b05ea3-e4db-4e64-936b-436b72c895b1/P3YrtAdKVekYb3BTgy.mp3",
+    ),
+},
+
+)