1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
|
# -*- coding: utf-8 -*-
# Copyright 2021-2025 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://architizer.com/"""
from .common import GalleryExtractor, Extractor, Message
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/([^/?#]+)"
example = "https://architizer.com/projects/NAME/"
def __init__(self, match):
url = f"{self.root}/projects/{match[1]}/"
GalleryExtractor.__init__(self, match, url)
def metadata(self, page):
extr = text.extract_from(page)
extr('id="Pages"', "")
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="', "?")
]
class ArchitizerFirmExtractor(Extractor):
"""Extractor for all projects of a firm"""
category = "architizer"
subcategory = "firm"
root = "https://architizer.com"
pattern = r"(?:https?://)?architizer\.com/firms/([^/?#]+)"
example = "https://architizer.com/firms/NAME/"
def __init__(self, match):
Extractor.__init__(self, match)
self.firm = match[1]
def items(self):
url = url = f"{self.root}/firms/{self.firm}/?requesting_merlin=pages"
page = self.request(url).text
data = {"_extractor": ArchitizerProjectExtractor}
for project in text.extract_iter(page, '<a href="/projects/', '"'):
if not project.startswith("q/"):
url = f"{self.root}/projects/{project}"
yield Message.Queue, url, data
|
