[architizer] add 'project' extractor (#1369)

docs/supportedsites.md

@@ -67,6 +67,12 @@ Consider all sites to be NSFW unless otherwise known.
     <td>Galleries</td>
     <td></td>
 </tr>
+<tr>
+    <td>Architizer</td>
+    <td>https://architizer.com/</td>
+    <td>Projects</td>
+    <td></td>
+</tr>
 <tr>
     <td>ArtStation</td>
     <td>https://www.artstation.com/</td>

gallery_dl/extractor/__init__.py

@@ -17,6 +17,7 @@
     "8kun",
     "8muses",
     "adultempire",
+    "architizer",
     "artstation",
     "aryion",
     "bcy",

gallery_dl/extractor/architizer.py

@@ -0,0 +1,74 @@
+# -*- coding: utf-8 -*-
+
+# Copyright 2021 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://architizer.com/"""
+
+from .common import GalleryExtractor
+from .. import text
+
+
+class ArchitizerProjectExtractor(GalleryExtractor):
+    """Extractor for project pages on architizer.com"""
+    category = "architizer"
+    subcategory = "project"
+    root = "https://architizer.com"
+    directory_fmt = ("{category}", "{firm}", "{title}")
+    filename_fmt = "{filename}.{extension}"
+    archive_fmt = "{gid}_{num}"
+    pattern = r"(?:https?://)?architizer\.com/projects/([^/?#]+)"
+    test = ("https://architizer.com/projects/house-lo/", {
+        "pattern": r"https://architizer-prod\.imgix\.net/media/mediadata"
+                   r"/uploads/.+\.jpg$",
+        "keyword": {
+            "count": 27,
+            "description": str,
+            "firm": "Atelier Lina Bellovicova",
+            "gid": "225496",
+            "location": "Czechia",
+            "num": int,
+            "size": "1000 sqft - 3000 sqft",
+            "slug": "house-lo",
+            "status": "Built",
+            "subcategory": "project",
+            "title": "House LO",
+            "type": "Residential › Private House",
+            "year": "2018",
+        },
+    })
+
+    def __init__(self, match):
+        url = "{}/projects/{}/".format(self.root, match.group(1))
+        GalleryExtractor.__init__(self, match, url)
+
+    def metadata(self, page):
+        extr = text.extract_from(page)
+        return {
+            "title"      : extr("data-name='", "'"),
+            "slug"       : extr("data-slug='", "'"),
+            "gid"        : extr("data-gid='", "'").rpartition(".")[2],
+            "firm"       : extr("data-firm-leaders-str='", "'"),
+            "location"   : extr("<h2>", "<").strip(),
+            "type"       : text.unescape(text.remove_html(extr(
+                '<div class="title">Type</div>', '<br'))),
+            "status"     : text.remove_html(extr(
+                '<div class="title">STATUS</div>', '</')),
+            "year"       : text.remove_html(extr(
+                '<div class="title">YEAR</div>', '</')),
+            "size"       : text.remove_html(extr(
+                '<div class="title">SIZE</div>', '</')),
+            "description": text.unescape(extr(
+                '<span class="copy js-copy">', '</span></div>')
+                .replace("<br />", "\n")),
+        }
+
+    def images(self, page):
+        return [
+            (url, None)
+            for url in text.extract_iter(
+                page, "property='og:image:secure_url' content='", "?")
+        ]