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
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
{ lib
, stdenv
, botocore
, buildPythonPackage
, cryptography
, cssselect
, fetchPypi
, fetchpatch
, glibcLocales
, installShellFiles
, itemadapter
, itemloaders
, jmespath
, lxml
, parsel
, protego
, pydispatcher
, pyopenssl
, pytestCheckHook
, pythonOlder
, queuelib
, service-identity
, sybil
, testfixtures
, tldextract
, twisted
, w3lib
, zope_interface
}:
buildPythonPackage rec {
pname = "scrapy";
version = "2.6.1";
disabled = pythonOlder "3.6";
src = fetchPypi {
inherit version;
pname = "Scrapy";
sha256 = "56fd55a59d0f329ce752892358abee5a6b50b4fc55a40420ea317dc617553827";
};
nativeBuildInputs = [
installShellFiles
];
propagatedBuildInputs = [
cryptography
cssselect
itemadapter
itemloaders
lxml
parsel
protego
pydispatcher
pyopenssl
queuelib
service-identity
tldextract
twisted
w3lib
zope_interface
];
checkInputs = [
botocore
glibcLocales
jmespath
pytestCheckHook
sybil
testfixtures
];
LC_ALL = "en_US.UTF-8";
preCheck = ''
# Disable doctest plugin because it causes pytest to hang
substituteInPlace pytest.ini \
--replace "--doctest-modules" ""
'';
disabledTestPaths = [
"tests/test_proxy_connect.py"
"tests/test_utils_display.py"
"tests/test_command_check.py"
# Don't test the documentation
"docs"
];
disabledTests = [
# It's unclear if the failures are related to libxml2, https://github.com/NixOS/nixpkgs/pull/123890
"test_nested_css"
"test_nested_xpath"
"test_flavor_detection"
# Requires network access
"FTPFeedStorageTest"
"FeedExportTest"
"test_custom_asyncio_loop_enabled_true"
"test_custom_loop_asyncio"
"test_custom_loop_asyncio_deferred_signal"
"FileFeedStoragePreFeedOptionsTest" # https://github.com/scrapy/scrapy/issues/5157
"test_timeout_download_from_spider_nodata_rcvd"
# Fails with AssertionError
"test_peek_fifo"
"test_peek_one_element"
"test_peek_lifo"
"test_callback_kwargs"
] ++ lib.optionals stdenv.isDarwin [
"test_xmliter_encoding"
"test_download"
];
postInstall = ''
installManPage extras/scrapy.1
install -m 644 -D extras/scrapy_bash_completion $out/share/bash-completion/completions/scrapy
install -m 644 -D extras/scrapy_zsh_completion $out/share/zsh/site-functions/_scrapy
'';
pythonImportsCheck = [
"scrapy"
];
__darwinAllowLocalNetworking = true;
meta = with lib; {
description = "High-level web crawling and web scraping framework";
longDescription = ''
Scrapy is a fast high-level web crawling and web scraping framework, used to crawl
websites and extract structured data from their pages. It can be used for a wide
range of purposes, from data mining to monitoring and automated testing.
'';
homepage = "https://scrapy.org/";
changelog = "https://github.com/scrapy/scrapy/raw/${version}/docs/news.rst";
license = licenses.bsd3;
maintainers = with maintainers; [ drewkett marsam ];
platforms = platforms.unix;
};
}
|