2018-06-23 14:27:58 +01:00
|
|
|
{ stdenv, buildPythonPackage, fetchPypi, glibcLocales, mock, pytest, botocore,
|
2017-02-15 22:01:38 +00:00
|
|
|
testfixtures, pillow, six, twisted, w3lib, lxml, queuelib, pyopenssl,
|
2018-12-23 03:21:54 +00:00
|
|
|
service-identity, parsel, pydispatcher, cssselect, lib, fetchpatch }:
|
2017-02-15 22:01:38 +00:00
|
|
|
buildPythonPackage rec {
|
2018-07-22 11:20:29 +01:00
|
|
|
version = "1.5.1";
|
2018-06-23 14:27:58 +01:00
|
|
|
pname = "Scrapy";
|
2017-02-15 22:01:38 +00:00
|
|
|
|
2018-06-23 14:27:58 +01:00
|
|
|
checkInputs = [ glibcLocales mock pytest botocore testfixtures pillow ];
|
|
|
|
propagatedBuildInputs = [
|
|
|
|
six twisted w3lib lxml cssselect queuelib pyopenssl service-identity parsel pydispatcher
|
|
|
|
];
|
2017-02-15 22:01:38 +00:00
|
|
|
|
2018-12-23 03:21:54 +00:00
|
|
|
patches = [
|
|
|
|
# Scrapy is usually installed via pip where copying all
|
|
|
|
# permissions makes sense. In Nix the files copied are owned by
|
|
|
|
# root and readonly. As a consequence scrapy can't edit the
|
|
|
|
# project templates.
|
|
|
|
./permissions-fix.patch
|
|
|
|
# fix python37 issues. Remove with the next release
|
|
|
|
(fetchpatch {
|
|
|
|
url = https://github.com/scrapy/scrapy/commit/f4f39057cbbfa4daf66f82061e57101b88d88d05.patch;
|
|
|
|
sha256 = "1f761qkji362i20i5bzcxz44sihvl29prm02i5l2xyhgl1hp91hv";
|
|
|
|
})
|
|
|
|
];
|
2017-02-15 22:01:38 +00:00
|
|
|
|
2018-06-23 14:27:58 +01:00
|
|
|
LC_ALL="en_US.UTF-8";
|
2017-02-15 22:01:38 +00:00
|
|
|
|
2018-12-23 03:21:54 +00:00
|
|
|
# Ignore proxy tests because requires mitmproxy
|
|
|
|
# Ignore test_retry_dns_error because tries to resolve an invalid dns and weirdly fails with "Reactor was unclean"
|
|
|
|
# Ignore xml encoding test on darwin because lxml can't find encodings https://bugs.launchpad.net/lxml/+bug/707396
|
2018-06-23 14:27:58 +01:00
|
|
|
checkPhase = ''
|
2018-12-23 03:21:54 +00:00
|
|
|
pytest --ignore=tests/test_linkextractors_deprecated.py --ignore=tests/test_proxy_connect.py --deselect tests/test_crawl.py::CrawlTestCase::test_retry_dns_error ${lib.optionalString stdenv.isDarwin "--deselect tests/test_utils_iterators.py::LxmlXmliterTestCase::test_xmliter_encoding"}
|
2018-06-23 14:27:58 +01:00
|
|
|
'';
|
2017-02-15 22:01:38 +00:00
|
|
|
|
2018-06-23 14:27:58 +01:00
|
|
|
src = fetchPypi {
|
|
|
|
inherit pname version;
|
2018-07-22 11:20:29 +01:00
|
|
|
sha256 = "5a398bf6818f87dcc817c919408a195f19ba46414ae12f259119336cfa862bb6";
|
2018-06-23 14:27:58 +01:00
|
|
|
};
|
2017-02-15 22:01:38 +00:00
|
|
|
|
2018-12-23 03:21:54 +00:00
|
|
|
postInstall = ''
|
|
|
|
install -m 644 -D extras/scrapy.1 $out/share/man/man1/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
|
|
|
|
'';
|
|
|
|
|
2018-06-23 14:27:58 +01:00
|
|
|
meta = with lib; {
|
|
|
|
description = "A fast high-level web crawling and web scraping framework, used to crawl websites and extract structured data from their pages";
|
2018-06-29 20:06:39 +01:00
|
|
|
homepage = https://scrapy.org/;
|
2018-06-23 14:27:58 +01:00
|
|
|
license = licenses.bsd3;
|
2018-12-23 03:21:54 +00:00
|
|
|
maintainers = with maintainers; [ drewkett marsam ];
|
2018-06-23 14:27:58 +01:00
|
|
|
platforms = platforms.unix;
|
|
|
|
};
|
2017-02-15 22:01:38 +00:00
|
|
|
}
|