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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
|
# -*- 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://desktopography.net/"""
from .common import Extractor, Message
from .. import text
BASE_PATTERN = r"(?:https?://)?desktopography\.net"
class DesktopographyExtractor(Extractor):
"""Base class for desktopography extractors"""
category = "desktopography"
archive_fmt = "{filename}"
root = "https://desktopography.net"
class DesktopographySiteExtractor(DesktopographyExtractor):
"""Extractor for all desktopography exhibitions """
subcategory = "site"
pattern = BASE_PATTERN + r"/$"
example = "https://desktopography.net/"
def items(self):
page = self.request(self.root).text
data = {"_extractor": DesktopographyExhibitionExtractor}
for exhibition_year in text.extract_iter(
page,
'<a href="https://desktopography.net/exhibition-',
'/">'):
url = self.root + "/exhibition-" + exhibition_year + "/"
yield Message.Queue, url, data
class DesktopographyExhibitionExtractor(DesktopographyExtractor):
"""Extractor for a yearly desktopography exhibition"""
subcategory = "exhibition"
pattern = BASE_PATTERN + r"/exhibition-([^/?#]+)/"
example = "https://desktopography.net/exhibition-2020/"
def __init__(self, match):
DesktopographyExtractor.__init__(self, match)
self.year = match[1]
def items(self):
url = f"{self.root}/exhibition-{self.year}/"
base_entry_url = "https://desktopography.net/portfolios/"
page = self.request(url).text
data = {
"_extractor": DesktopographyEntryExtractor,
"year": self.year,
}
for entry_url in text.extract_iter(
page,
'<a class="overlay-background" href="' + base_entry_url,
'">'):
url = base_entry_url + entry_url
yield Message.Queue, url, data
class DesktopographyEntryExtractor(DesktopographyExtractor):
"""Extractor for all resolutions of a desktopography wallpaper"""
subcategory = "entry"
pattern = BASE_PATTERN + r"/portfolios/([\w-]+)"
example = "https://desktopography.net/portfolios/NAME/"
def __init__(self, match):
DesktopographyExtractor.__init__(self, match)
self.entry = match[1]
def items(self):
url = f"{self.root}/portfolios/{self.entry}"
page = self.request(url).text
entry_data = {"entry": self.entry}
yield Message.Directory, entry_data
for image_data in text.extract_iter(
page,
'<a target="_blank" href="https://desktopography.net',
'">'):
path, _, filename = image_data.partition(
'" class="wallpaper-button" download="')
text.nameext_from_url(filename, entry_data)
yield Message.Url, self.root + path, entry_data
|
