Move scrapy to its own module and add patch to fix broken permission code.

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 so

  scrapy startproject

fails.

2 files changed, 66 insertions, 0 deletions

diff --git a/pkgs/development/python-modules/scrapy/default.nix b/pkgs/development/python-modules/scrapy/default.nix
new file mode 100644
index 00000000000..8f3b2ef74b2
--- /dev/null
+++ b/pkgs/development/python-modules/scrapy/default.nix
@@ -0,0 +1,38 @@
+{ buildPythonPackage, fetchurl, glibcLocales, mock, pytest, botocore,
+  testfixtures, pillow, six, twisted, w3lib, lxml, queuelib, pyopenssl,
+  service-identity, parsel, pydispatcher, cssselect, lib }:
+buildPythonPackage rec {
+    name = "Scrapy-${version}";
+    version = "1.3.1";
+
+    buildInputs = [ glibcLocales mock pytest botocore testfixtures pillow ];
+    propagatedBuildInputs = [
+      six twisted w3lib lxml cssselect queuelib pyopenssl service-identity parsel pydispatcher
+    ];
+
+    # Scrapy is usually installed via pip where copying all
+    # permissions makes sense. In Nix the files copied are owned by
+    # root and readonly. As a consequence scrapy can't edit the
+    # project templates.
+    patches = [ ./permissions-fix.patch ];
+
+    LC_ALL="en_US.UTF-8";
+
+    checkPhase = ''
+      py.test --ignore=tests/test_linkextractors_deprecated.py --ignore=tests/test_proxy_connect.py
+      # The ignored tests require mitmproxy, which depends on protobuf, but it's disabled on Python3
+    '';
+
+    src = fetchurl {
+      url = "mirror://pypi/S/Scrapy/${name}.tar.gz";
+      sha256 = "0s5qkxwfq842maxjd2j82ldp4dyb70kla3z5rr56z0p7ig53cbvk";
+    };
+
+    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";
+      homepage = "http://scrapy.org/";
+      license = licenses.bsd3;
+      maintainers = with maintainers; [ drewkett ];
+      platforms = platforms.linux;
+    };
+}
diff --git a/pkgs/development/python-modules/scrapy/permissions-fix.patch b/pkgs/development/python-modules/scrapy/permissions-fix.patch
new file mode 100644
index 00000000000..5ea5269c799
--- /dev/null
+++ b/pkgs/development/python-modules/scrapy/permissions-fix.patch
@@ -0,0 +1,28 @@
+diff --git a/scrapy/commands/startproject.py b/scrapy/commands/startproject.py
+index 5941066..89f8edb 100644
+--- a/scrapy/commands/startproject.py
++++ b/scrapy/commands/startproject.py
+@@ -4,7 +4,7 @@ import os
+ import string
+ from importlib import import_module
+ from os.path import join, exists, abspath
+-from shutil import ignore_patterns, move, copy2, copystat
++from shutil import ignore_patterns, move, copyfile, copystat
+ 
+ import scrapy
+ from scrapy.commands import ScrapyCommand
+@@ -76,8 +76,7 @@ class Command(ScrapyCommand):
+             if os.path.isdir(srcname):
+                 self._copytree(srcname, dstname)
+             else:
+-                copy2(srcname, dstname)
+-        copystat(src, dst)
++                copyfile(srcname, dstname)
+ 
+     def run(self, args, opts):
+         if len(args) not in (1, 2):
+@@ -118,4 +117,3 @@ class Command(ScrapyCommand):
+         _templates_base_dir = self.settings['TEMPLATES_DIR'] or \
+             join(scrapy.__path__[0], 'templates')
+         return join(_templates_base_dir, 'project')
+-