merge #7409: [pictoa] add support (#6683)

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>Albums, individual Images</td>
+    <td></td>
+</tr>
 <tr>
     <td>Piczel</td>
     <td>https://piczel.tv/</td>

gallery_dl/extractor/__init__.py

@@ -130,6 +130,7 @@ modules = [
     "philomena",
     "photovogue",
     "picarto",
+    "pictoa",
     "piczel",
     "pillowfort",
     "pinterest",

gallery_dl/extractor/pictoa.py

@@ -0,0 +1,78 @@
+# -*- 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
+
+BASE_PATTERN = r"(?:https?://)?(?:[\w]+\.)?pictoa\.com(?:\.de)?"
+
+
+class PictoaExtractor(Extractor):
+    """Base class for pictoa extractors"""
+    category = "pictoa"
+    root = "https://pictoa.com"
+    directory_fmt = ("{category}", "{album_id} {album_title}")
+    filename_fmt = "{id}.{extension}"
+    archive_fmt = "{id}"
+
+
+class PictoaImageExtractor(PictoaExtractor):
+    """Extractor for single images from pictoa.com"""
+    subcategory = "image"
+    pattern = BASE_PATTERN + r"/albums/(?:[\w-]+-)?(\d+)/(\d+)"
+    example = "https://www.pictoa.com/albums/NAME-12345/12345.html"
+
+    def items(self):
+        album_id, image_id = self.groups
+
+        url = "{}/albums/{}/{}.html".format(self.root, album_id, image_id)
+        page = self.request(url).text
+        album_title = text.extr(page, 'property="og:title" content="', '"')
+        image_url = text.extr(page, 'property="og:image" content="', '"')
+
+        data = {
+            "album_id"   : album_id,
+            "album_title": album_title.rpartition(" #")[0],
+            "id"         : 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"
+    pattern = BASE_PATTERN + r"/albums/(?:[\w-]+-)?(\d+).html"
+    example = "https://www.pictoa.com/albums/NAME-12345.html"
+
+    def items(self):
+        album_id = self.groups[0]
+        url = "{}/albums/{}.html".format(self.root, album_id)
+        page = self.request(url).text
+
+        album_data = {
+            "album_id"   : album_id,
+            "album_title": text.extr(page, "<h1>", "<"),
+            "tags"       : text.split_html(text.extr(
+                page, '<ol class="related-categories', '</ol>'))[1:],
+            "_extractor" : PictoaImageExtractor,
+        }
+
+        while True:
+            container = text.extr(page, '<main>', '<span id="flag" >')
+            for url in text.extract_iter(
+                    container, '<a rel="nofollow" href="', '"'):
+                yield Message.Queue, url, album_data
+
+            url = text.extr(page, '<link rel="next" href="', '"')
+            if not url:
+                break
+            page = self.request(url).text

test/results/pictoa.py

@@ -0,0 +1,72 @@
+# -*- 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",
+    "#class"  : pictoa.PictoaAlbumExtractor,
+    "#pattern": pictoa.PictoaImageExtractor.pattern,
+    "#count"  : 16,
+
+    "album_id"   : "3229225",
+    "album_title": "Anna Kendrick busty in a strapless red dress out in NYC",
+    "tags"       : ["Anna Kendrick", "Celebrity"],
+},
+
+{
+    "#url"    : "https://www.pictoa.com.de/albums/oscars-2020-red-carpet-4010403.html",
+    "#comment": "verify pagination works",
+    "#class"  : pictoa.PictoaAlbumExtractor,
+    "#pattern": pictoa.PictoaImageExtractor.pattern,
+    "#count"  : 182,
+
+    "album_id"   : "4010403",
+    "album_title": "Oscars 2020 Red Carpet",
+    "tags"       : ['Celebrity', 'Red'],
+},
+
+{
+    "#url"    : "https://it.pictoa.com/albums/carl-virkus-149024.html",
+    "#comment": "null tags",
+    "#class"  : pictoa.PictoaAlbumExtractor,
+    "#urls"   : "https://www.pictoa.com/albums/carl-virkus-149024/2221031.html",
+
+    "album_id"   : "149024",
+    "album_title": "Carl Virkus",
+    "tags"       : [],
+},
+
+{
+    "#url"  : "https://www.pictoa.com/albums/anna-kendrick-showing-cleavage-at-the-56th-annual-grammy-awards-3233172/75206264.html",
+    "#class": pictoa.PictoaImageExtractor,
+    "#urls" : "https://s1.pictoa.com/media/galleries/168/930/168930594a8750dfd3e/3233172594a8759dcc3a.jpg",
+
+    "album_id"   : "3233172",
+    "album_title": "Anna Kendrick showing cleavage at the 56th Annual GRAMMY Awards",
+    "extension"  : "jpg",
+    "filename"   : "3233172594a8759dcc3a",
+    "id"         : "75206264",
+    "url"        : "https://s1.pictoa.com/media/galleries/168/930/168930594a8750dfd3e/3233172594a8759dcc3a.jpg"
+},
+
+{
+    "#url"  : "https://nl.pictoa.com/albums/kandi-barbour-3840809/94038192.html",
+    "#class": pictoa.PictoaImageExtractor,
+    "#urls"        : "https://s2.pictoa.com/media/galleries/294/452/29445260009fa5b68e4/384080960009fb51e389.jpg",
+    "#sha1_content": "152595069016da89565eb3d8e73df835afd22e2c",
+
+    "album_id"   : "3840809",
+    "album_title": "Kandi Barbour",
+    "extension"  : "jpg",
+    "filename"   : "384080960009fb51e389",
+    "id"         : "94038192",
+    "url"        : "https://s2.pictoa.com/media/galleries/294/452/29445260009fa5b68e4/384080960009fb51e389.jpg",
+},
+
+)