From f34210828062e5c7a481cce7d06d029d52ae6409 Mon Sep 17 00:00:00 2001
From: nunonda <nuhonda42@gmail.com>
Date: Wed, 23 Apr 2025 17:37:40 -0700
Subject: [PATCH] Adding in a first pass at a pictoa extractor

Adds support for galleries and individual Images
---
 docs/supportedsites.md           |   6 ++
 gallery_dl/extractor/__init__.py |   1 +
 gallery_dl/extractor/pictoa.py   | 110 +++++++++++++++++++++++++++++++
 test/results/pictoa.py           |  49 ++++++++++++++
 4 files changed, 166 insertions(+)
 create mode 100644 gallery_dl/extractor/pictoa.py
 create mode 100644 test/results/pictoa.py

diff --git a/docs/supportedsites.md b/docs/supportedsites.md
index 95dd34ec..1e3e66d3 100644
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -691,6 +691,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Galleries</td>
     <td></td>
 </tr>
+<tr>
+    <td>Pictoa</td>
+    <td>https://pictoa.com/</td>
+    <td>Galleries, individual Images</td>
+    <td></td>
+</tr>
 <tr>
     <td>Piczel</td>
     <td>https://piczel.tv/</td>
diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py
index d0476c9a..6dd978ea 100644
--- a/gallery_dl/extractor/__init__.py
+++ b/gallery_dl/extractor/__init__.py
@@ -129,6 +129,7 @@ modules = [
     "pexels",
     "philomena",
     "photovogue",
+    "pictoa",
     "picarto",
     "piczel",
     "pillowfort",
diff --git a/gallery_dl/extractor/pictoa.py b/gallery_dl/extractor/pictoa.py
new file mode 100644
index 00000000..14991114
--- /dev/null
+++ b/gallery_dl/extractor/pictoa.py
@@ -0,0 +1,110 @@
+# -*- 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://pictoa.com/"""
+
+from .common import Extractor, Message
+from .. import text
+import re
+
+BASE_PATTERN = r"(?:https?://)?(?:[\w]+\.)?pictoa\.com(?:\.de)?"
+
+class PictoaExtractor(Extractor):
+    """Base class for pictoa extractors"""
+    category = "pictoa"
+    root = "https://pictoa.com"
+
+class PictoaImageExtractor(PictoaExtractor):
+    """Extractor for single images from pictoa.com"""
+    subcategory = "image"
+    pattern = BASE_PATTERN + r"/albums/([^/\.?#]+)/([^/\.?#]+).html"
+    filename_fmt = "{id}.{extension}"
+    directory_fmt = ("{category}", "{album[id]}")
+    archive_fmt = "{image_id}"
+    example = "https://www.pictoa.com/albums/name-2693203/12345.html"
+
+    def __init__(self, match):
+        PictoaExtractor.__init__(self, match)
+        self.album_id = match.group(1)
+        self.image_id = match.group(2)
+
+    def items(self):
+        url = f"{self.root}/albums/{self.album_id}/{self.image_id}.html"
+        page = self.request(url).text
+        container = text.extract(page, '<div id="player"', "</div>")[0]
+        album_title = text.extract(page, '<meta name="keywords" content="', '"')[0]
+        image_url = text.extract(container, 'src="', '"')[0]
+        data = {
+            "album": {
+                "id": self.album_id,
+                "title": album_title,
+            },
+            "image_id": self.image_id,
+            "id": self.image_id,
+            "url": image_url,
+        }
+        text.nameext_from_url(image_url, data)
+        yield Message.Directory, data
+        yield Message.Url, image_url, data
+
+class PictoaAlbumExtractor(PictoaExtractor):
+    """Extractor for image albums from pictoa.com"""
+    subcategory = "album"
+    directory_fmt = ("{category}", "{album[id]} {album[title]}")
+    archive_fmt = "{album[id]}_{id}"
+    pattern = BASE_PATTERN + r"/albums/([^/\.?#]+).html"
+    example = "https://www.pictoa.com/albums/name-2693203.html"
+
+    def __init__(self, match):
+        PictoaExtractor.__init__(self, match)
+        self.album_id = match.group(1)
+
+    def items(self):
+        url = f"{self.root}/albums/{self.album_id}.html"
+        page = self.request(url).text
+        title = text.extract(page, '<h1>', '</h1>')[0]
+
+        # grab the id out of the title (handiest place to get it)
+        htmltitle = text.extract(page, '<title>', '</title>')[0]
+        album_id = text.extract(htmltitle, '#', ' ')[0]
+
+        # tags
+        taghunk = text.extract(page, '<ol class="related-categories bt"', '</ol>')
+        tags = re.compile(r"\s<li><a href=\".*\">([\d\w ]+)</a>").findall(taghunk[0])
+
+        album_data = {
+            "album": {
+                "id": album_id,
+                "title": title
+            },
+            "date": None,
+            "title": title,
+            "tags": tags,
+        }
+        yield Message.Directory, album_data
+
+        # paginate through the pages
+        pagination = text.extract(page, '<ul class="pagination"', '</ul>')[0]
+        findall = re.compile(self.pattern).findall
+        pages = findall(pagination)
+
+        # run a quick dedupe
+        page_set = {self.album_id: page}
+        for i in pages:
+            if i not in page_set:
+                page_set[i] = self.request(f"{self.root}/albums/{i}.html").text
+
+        for id, page in page_set.items():
+            # we'll use the span#flag as the ending token for the
+            # galleries portion of the page.
+            image_container = text.extract(page, '<main>', '<span id="flag" >')[0]
+            for url in text.extract_iter(image_container, '<a rel="nofollow" href="', '"'):
+                data = {
+                    "url": url,
+                    "album_id": album_id,
+                    "_extractor": PictoaImageExtractor
+                }
+                data.update(album_data)
+                yield Message.Queue, url, data
diff --git a/test/results/pictoa.py b/test/results/pictoa.py
new file mode 100644
index 00000000..ebe31cd9
--- /dev/null
+++ b/test/results/pictoa.py
@@ -0,0 +1,49 @@
+# -*- 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 pictoa
+
+__tests__ = (
+{
+    "#url"     : "https://www.pictoa.com/albums/anna-kendrick-busty-in-a-strapless-red-dress-out-in-nyc-3229225.html",
+    "#category": ("", "pictoa", "album"),
+    "#class"   : pictoa.PictoaAlbumExtractor,
+    "#pattern" : r"https://?(?:[\w]+\.)?pictoa\.com/albums/[\w-]+/[\d]+.html",
+    "#count"   : 16,
+    "album_id" : "3229225",
+    "date"     : None,
+    "title"    : "Anna Kendrick busty in a strapless red dress out in NYC",
+    "tags"     : ["Anna Kendrick", "Celebrity"]
+},
+{
+    # verify pagination works
+    "#url"     : "https://www.pictoa.com/albums/oscars-2020-red-carpet-4010403.html",
+    "#category": ("", "pictoa", "album"),
+    "#class"   : pictoa.PictoaAlbumExtractor,
+    "#pattern" : r"https://?(?:[\w]+\.)?pictoa\.com/albums/[\w-]+/[\d]+.html",
+    "#count"   : 182,
+    "album_id" : "4010403",
+    "date"     : None,
+    "title"    : "Oscars 2020 Red Carpet",
+    "tags"     : ['Celebrity', 'Red']
+},
+{
+    # null tags
+    "#url"     : "https://www.pictoa.com/albums/carl-virkus-149024.html",
+    "#category": ("", "pictoa", "album"),
+    "#class"   : pictoa.PictoaAlbumExtractor,
+    "#count"   : 1,
+    "album_id" : "149024",
+    "tags"     : []
+},
+{
+    "#url"     : "https://www.pictoa.com/albums/anna-kendrick-showing-cleavage-at-the-56th-annual-grammy-awards-3233172/75206264.html",
+    "#category": ("", "pictoa", "image"),
+    "#class"   : pictoa.PictoaImageExtractor,
+    "#pattern" : r"https://s1.pictoa.com/media/galleries/168/930/[\w\d]+/[\w\d]+.jpg",
+    "id"       : "75206264",
+},
+)