[sxypix] add support (#4507 #8391 #8574)

* Add support for sxypix.com
* update & simplify
    - text.extract -> text.extr
    - self.request().json() -> self.request_json()
    - use self.groups
    - remove __init__
    - list comprehension
* update test results

---------

Co-authored-by: Mike Fährmann <[email protected]>

Author: MyFinalBellyache

docs/supportedsites.md

@@ -1009,6 +1009,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Posts, User Profiles</td>
     <td>Supported</td>
 </tr>
+<tr id="sxypix" title="sxypix">
+    <td>Sxypix</td>
+    <td>https://sxypix.com/</td>
+    <td>Galleries</td>
+    <td></td>
+</tr>
 <tr id="tapas" title="tapas">
     <td>Tapas</td>
     <td>https://tapas.io/</td>

gallery_dl/extractor/__init__.py

@@ -192,6 +192,7 @@
     "speakerdeck",
     "steamgriddb",
     "subscribestar",
+    "sxypix",
     "szurubooru",
     "tapas",
     "tcbscans",

gallery_dl/extractor/sxypix.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.
+
+"""Extractors for https://sxypix.com/"""
+
+from .common import GalleryExtractor
+from .. import text
+
+
+class SxypixGalleryExtractor(GalleryExtractor):
+    """Extractor for image galleries from sxypix.com"""
+    category = "sxypix"
+    root = "https://sxypix.com"
+    pattern = r"(?:https?://)?(?:www\.)?sxypix\.com(/w/(\w+))"
+    example = "https://sxypix.com/w/2bbaf1b24a5863d0e73436619bbaa7ee"
+
+    def metadata(self, page):
+        return {
+            "gallery_id": self.groups[1],
+            "title": text.unescape(text.extr(
+                page, '<meta name="keywords" content="', '"')),
+        }
+
+    def images(self, page):
+        data = {
+            "aid"  : text.extr(page, "data-aid='", "'"),
+            "ghash": text.extr(page, "data-ghash='", "'"),
+        }
+        gallery = self.request_json(
+            "https://sxypix.com/php/gall.php", method="POST", data=data)
+
+        base = "https://x."
+        return [
+            (base + text.extr(entry, "data-src='//.", "'"), None)
+            for entry in gallery["r"]
+        ]

test/results/sxypix.py

@@ -0,0 +1,25 @@
+# -*- 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 sxypix
+
+
+__tests__ = (
+{
+    "#url"     : "https://sxypix.com/w/c42ec529474789f812dd8ba26103855f",
+    "#category": ("", "sxypix", "gallery"),
+    "#class"   : sxypix.SxypixGalleryExtractor,
+    "#count"   : 35,
+
+    "count"     : 35,
+    "num"       : range(1, 35),
+    "filename"  : "hash:md5",
+    "extension" : "webp",
+    "gallery_id": "c42ec529474789f812dd8ba26103855f",
+    "title"     : "#MommysBoy - Penny Barber - Coddling Her Boy",
+},
+
+)