From 12f1e468e9f071e8f5c00921d0fbada460e41c57 Mon Sep 17 00:00:00 2001 From: Purva Udai Date: Sun, 13 Oct 2019 15:55:27 +0530 Subject: [PATCH 01/19] Issue #3731 --- scrapy/extensions/feedexport.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index ce2846eba..981efee55 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -199,9 +199,9 @@ class FeedExporter(object): def __init__(self, settings): self.settings = settings - self.urifmt = settings['FEED_URI'] - if not self.urifmt: + if not settings['FEED_URI']: raise NotConfigured + self.urifmt=str(settings['FEED_URI']) self.format = settings['FEED_FORMAT'].lower() self.export_encoding = settings['FEED_EXPORT_ENCODING'] self.storages = self._load_components('FEED_STORAGES') From 2ee38e8ddbac6841c8d2bb067ddc0ddba813151f Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 14:43:47 +0530 Subject: [PATCH 02/19] Added Pathlib.Path test --- tests/test_feedexport.py | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index f32ac2a4b..842e8d8c0 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -29,6 +29,8 @@ from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete, get from scrapy.utils.python import to_native_str from scrapy.utils.project import get_project_settings +from Pathlib import Path + class FileFeedStorageTest(unittest.TestCase): @@ -843,3 +845,17 @@ class FeedExportTest(unittest.TestCase): yield self.exported_data({}, settings) self.assertTrue(FromCrawlerCsvItemExporter.init_with_crawler) self.assertTrue(FromCrawlerFileFeedStorage.init_with_crawler) + + @defer.inlineCallbacks + def test_pathlib_uri(self): + tmpdir = tempfile.mkdtemp() + feed_uri = Path(tmpdir) / 'res' + settings = { + 'FEED_FORMAT': 'csv', + 'FEED_STORE_EMPTY': True, + 'FEED_URI': feed_uri, + } + + data = yield self.exported_no_data(settings) + self.assertEqual(data, b'') + shutil.rmtree(tmpdir, ignore_errors=True) \ No newline at end of file From ad96d6ef594c29e8648c3c3b310c42e8fcb210d3 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 14:53:59 +0530 Subject: [PATCH 03/19] Added Pathlib.Path test correctly --- tests/test_feedexport.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 842e8d8c0..664cfd6de 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -856,6 +856,6 @@ class FeedExportTest(unittest.TestCase): 'FEED_URI': feed_uri, } - data = yield self.exported_no_data(settings) - self.assertEqual(data, b'') - shutil.rmtree(tmpdir, ignore_errors=True) \ No newline at end of file + data = yield self.exported_no_data(settings) + self.assertEqual(data, b'') + shutil.rmtree(tmpdir, ignore_errors=True) \ No newline at end of file From 4226791481bb440b9542dda063d1b5ac920a8411 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 15:07:13 +0530 Subject: [PATCH 04/19] Added Pathlib.Path test --- requirements-py2.txt | 1 + requirements-py3.txt | 1 + 2 files changed, 2 insertions(+) diff --git a/requirements-py2.txt b/requirements-py2.txt index dde8d1c9c..42e057417 100644 --- a/requirements-py2.txt +++ b/requirements-py2.txt @@ -16,3 +16,4 @@ service_identity>=16.0.0 six>=1.10.0 Twisted>=16.0.0 zope.interface>=4.1.3 +pathlib2>=2.0 diff --git a/requirements-py3.txt b/requirements-py3.txt index 2c98e6f6d..77296b91b 100644 --- a/requirements-py3.txt +++ b/requirements-py3.txt @@ -16,3 +16,4 @@ lxml>=3.5.0 service_identity>=16.0.0 six>=1.10.0 zope.interface>=4.1.3 +pathlib2>=2.0 From 0b7d8a51b4dabeb4097f5fc2de396904f308c56d Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 15:12:53 +0530 Subject: [PATCH 05/19] Added Pathlib.Path test --- requirements-py2.txt | 2 +- requirements-py3.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/requirements-py2.txt b/requirements-py2.txt index 42e057417..2a0bb49d3 100644 --- a/requirements-py2.txt +++ b/requirements-py2.txt @@ -16,4 +16,4 @@ service_identity>=16.0.0 six>=1.10.0 Twisted>=16.0.0 zope.interface>=4.1.3 -pathlib2>=2.0 +pathlib==1.0.1 diff --git a/requirements-py3.txt b/requirements-py3.txt index 77296b91b..c57cff5da 100644 --- a/requirements-py3.txt +++ b/requirements-py3.txt @@ -16,4 +16,4 @@ lxml>=3.5.0 service_identity>=16.0.0 six>=1.10.0 zope.interface>=4.1.3 -pathlib2>=2.0 +pathlib==1.0.1 From a776554282aadc651f9e142aea9bc436f9f587a7 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 15:31:55 +0530 Subject: [PATCH 06/19] Added Pathlib.Path test --- tests/test_feedexport.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 664cfd6de..fcada3a45 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -29,7 +29,7 @@ from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete, get from scrapy.utils.python import to_native_str from scrapy.utils.project import get_project_settings -from Pathlib import Path +from pathlib import Path class FileFeedStorageTest(unittest.TestCase): From cd4c211f4b5c9d5716d0e49472a978c11d7351f8 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 15:38:06 +0530 Subject: [PATCH 07/19] Added Pathlib.Path test --- tests/test_feedexport.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index fcada3a45..f497bb32e 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -29,7 +29,7 @@ from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete, get from scrapy.utils.python import to_native_str from scrapy.utils.project import get_project_settings -from pathlib import Path +from pathlib2 import Path class FileFeedStorageTest(unittest.TestCase): From cd0964643879b5513807c8955c7e887c77624970 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 16:19:41 +0530 Subject: [PATCH 08/19] Added Pathlib.Path test --- requirements-py2.txt | 2 +- requirements-py3.txt | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/requirements-py2.txt b/requirements-py2.txt index 2a0bb49d3..42e057417 100644 --- a/requirements-py2.txt +++ b/requirements-py2.txt @@ -16,4 +16,4 @@ service_identity>=16.0.0 six>=1.10.0 Twisted>=16.0.0 zope.interface>=4.1.3 -pathlib==1.0.1 +pathlib2>=2.0 diff --git a/requirements-py3.txt b/requirements-py3.txt index c57cff5da..77296b91b 100644 --- a/requirements-py3.txt +++ b/requirements-py3.txt @@ -16,4 +16,4 @@ lxml>=3.5.0 service_identity>=16.0.0 six>=1.10.0 zope.interface>=4.1.3 -pathlib==1.0.1 +pathlib2>=2.0 From 7031e3a12422ae977448e7b338457f6c09af9b0e Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 16:31:14 +0530 Subject: [PATCH 09/19] Added Pathlib.Path test --- tests/test_feedexport.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index f497bb32e..c4bfdb4fe 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -850,10 +850,11 @@ class FeedExportTest(unittest.TestCase): def test_pathlib_uri(self): tmpdir = tempfile.mkdtemp() feed_uri = Path(tmpdir) / 'res' + res_uri = urljoin('file:', pathname2url(feed_uri)) settings = { 'FEED_FORMAT': 'csv', 'FEED_STORE_EMPTY': True, - 'FEED_URI': feed_uri, + 'FEED_URI': res_uri, } data = yield self.exported_no_data(settings) From 85f56a92f0c753dfa55012e647f425a6a3d23076 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 16:43:17 +0530 Subject: [PATCH 10/19] Added Pathlib.Path test --- tests/test_feedexport.py | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index c4bfdb4fe..17526716b 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -850,6 +850,7 @@ class FeedExportTest(unittest.TestCase): def test_pathlib_uri(self): tmpdir = tempfile.mkdtemp() feed_uri = Path(tmpdir) / 'res' + feed_uri=str(feeduri) res_uri = urljoin('file:', pathname2url(feed_uri)) settings = { 'FEED_FORMAT': 'csv', From 4184bac0687d55a442f599ebcfc913231a7c98e2 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 22 Oct 2019 16:57:14 +0530 Subject: [PATCH 11/19] Added Pathlib.Path test --- tests/test_feedexport.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 17526716b..8c0e5cd3d 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -850,7 +850,7 @@ class FeedExportTest(unittest.TestCase): def test_pathlib_uri(self): tmpdir = tempfile.mkdtemp() feed_uri = Path(tmpdir) / 'res' - feed_uri=str(feeduri) + feed_uri=str(feed_uri) res_uri = urljoin('file:', pathname2url(feed_uri)) settings = { 'FEED_FORMAT': 'csv', From 084a1cda6dfd94a3671d49c362db2ee6ea88a10d Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 15:41:00 +0530 Subject: [PATCH 12/19] Adding test --- tests/test_feedexport.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 8c0e5cd3d..16916f728 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -415,7 +415,7 @@ class FeedExportTest(unittest.TestCase): spider_cls.start_urls = [s.url('/')] yield runner.crawl(spider_cls) - with open(res_path, 'rb') as f: + with open(res_uri, 'rb') as f: content = f.read() finally: @@ -850,12 +850,12 @@ class FeedExportTest(unittest.TestCase): def test_pathlib_uri(self): tmpdir = tempfile.mkdtemp() feed_uri = Path(tmpdir) / 'res' - feed_uri=str(feed_uri) res_uri = urljoin('file:', pathname2url(feed_uri)) settings = { 'FEED_FORMAT': 'csv', 'FEED_STORE_EMPTY': True, - 'FEED_URI': res_uri, + 'FEED_URI': feed_uri, + 'FEED_URI_ISPATH' : True } data = yield self.exported_no_data(settings) From 0042c389eb2d44d017bc8af069c7dd7ebd9319bd Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 15:57:58 +0530 Subject: [PATCH 13/19] Adding test --- tests/test_feedexport.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 16916f728..275579959 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -855,7 +855,6 @@ class FeedExportTest(unittest.TestCase): 'FEED_FORMAT': 'csv', 'FEED_STORE_EMPTY': True, 'FEED_URI': feed_uri, - 'FEED_URI_ISPATH' : True } data = yield self.exported_no_data(settings) From 9e6e2dde2b7736278075d6a8268511a3bc44b8b5 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 16:10:37 +0530 Subject: [PATCH 14/19] Adding test --- tests/test_feedexport.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 275579959..b6e4a5449 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -415,7 +415,7 @@ class FeedExportTest(unittest.TestCase): spider_cls.start_urls = [s.url('/')] yield runner.crawl(spider_cls) - with open(res_uri, 'rb') as f: + with open(defaults['FEED_URI'], 'rb') as f: content = f.read() finally: From 970c3be1603483a61637b94afdb965eb24342744 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 18:34:15 +0530 Subject: [PATCH 15/19] Added Test --- scrapy/extensions/feedexport.py | 2 +- tests/test_feedexport.py | 7 ++++--- 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index 981efee55..8dacce459 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -201,7 +201,7 @@ class FeedExporter(object): self.settings = settings if not settings['FEED_URI']: raise NotConfigured - self.urifmt=str(settings['FEED_URI']) + self.urifmt = str(settings['FEED_URI']) self.format = settings['FEED_FORMAT'].lower() self.export_encoding = settings['FEED_EXPORT_ENCODING'] self.storages = self._load_components('FEED_STORAGES') diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index b6e4a5449..11d32bd14 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -407,6 +407,7 @@ class FeedExportTest(unittest.TestCase): defaults = { 'FEED_URI': res_uri, 'FEED_FORMAT': 'csv', + 'FEED_PATH': res_path } defaults.update(settings or {}) try: @@ -415,7 +416,7 @@ class FeedExportTest(unittest.TestCase): spider_cls.start_urls = [s.url('/')] yield runner.crawl(spider_cls) - with open(defaults['FEED_URI'], 'rb') as f: + with open(defaults['FEED_PATH'], 'rb') as f: content = f.read() finally: @@ -855,8 +856,8 @@ class FeedExportTest(unittest.TestCase): 'FEED_FORMAT': 'csv', 'FEED_STORE_EMPTY': True, 'FEED_URI': feed_uri, + 'FEED_PATH': feed_uri } - data = yield self.exported_no_data(settings) self.assertEqual(data, b'') - shutil.rmtree(tmpdir, ignore_errors=True) \ No newline at end of file + shutil.rmtree(tmpdir, ignore_errors=True) From 0c2dcd5092eccf08399f0838d86d598329cc3a28 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 18:35:50 +0530 Subject: [PATCH 16/19] Added Test --- requirements-py2.txt | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 requirements-py2.txt diff --git a/requirements-py2.txt b/requirements-py2.txt deleted file mode 100644 index 42e057417..000000000 --- a/requirements-py2.txt +++ /dev/null @@ -1,19 +0,0 @@ -parsel>=1.5.0 -PyDispatcher>=2.0.5 -w3lib>=1.17.0 -protego>=0.1.15 - -pyOpenSSL>=16.2.0 # Earlier versions fail with "AttributeError: module 'lib' has no attribute 'SSL_ST_INIT'" -queuelib>=1.4.2 # Earlier versions fail with "AttributeError: '...QueueTest' object has no attribute 'qpath'" -cryptography>=2.0 # Earlier versions would fail to install - -# Reference versions taken from -# https://packages.ubuntu.com/xenial/python/ -# https://packages.ubuntu.com/xenial/zope/ -cssselect>=0.9.1 -lxml>=3.5.0 -service_identity>=16.0.0 -six>=1.10.0 -Twisted>=16.0.0 -zope.interface>=4.1.3 -pathlib2>=2.0 From f39ff4945854fb5d98389fabfa2d2e5a059c0643 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 18:54:21 +0530 Subject: [PATCH 17/19] Added Test --- tests/test_feedexport.py | 1 - 1 file changed, 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 11d32bd14..9b07c2051 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -851,7 +851,6 @@ class FeedExportTest(unittest.TestCase): def test_pathlib_uri(self): tmpdir = tempfile.mkdtemp() feed_uri = Path(tmpdir) / 'res' - res_uri = urljoin('file:', pathname2url(feed_uri)) settings = { 'FEED_FORMAT': 'csv', 'FEED_STORE_EMPTY': True, From 50eaabe1fc540218f9f04197810367154eb3e102 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Mon, 11 Nov 2019 20:00:26 +0530 Subject: [PATCH 18/19] Added Test --- tests/test_feedexport.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 9b07c2051..2819f8f0b 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -416,7 +416,7 @@ class FeedExportTest(unittest.TestCase): spider_cls.start_urls = [s.url('/')] yield runner.crawl(spider_cls) - with open(defaults['FEED_PATH'], 'rb') as f: + with open(str(defaults['FEED_PATH']), 'rb') as f: content = f.read() finally: From 4b8b0345e58ee5990bd0c28205b5eb0b892680d1 Mon Sep 17 00:00:00 2001 From: purvaudai Date: Tue, 12 Nov 2019 18:17:15 +0530 Subject: [PATCH 19/19] Mades Changes as per review --- requirements-py3.txt | 1 - tests/test_feedexport.py | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/requirements-py3.txt b/requirements-py3.txt index 77296b91b..2c98e6f6d 100644 --- a/requirements-py3.txt +++ b/requirements-py3.txt @@ -16,4 +16,3 @@ lxml>=3.5.0 service_identity>=16.0.0 six>=1.10.0 zope.interface>=4.1.3 -pathlib2>=2.0 diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 2819f8f0b..1f46ac04a 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -29,7 +29,7 @@ from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete, get from scrapy.utils.python import to_native_str from scrapy.utils.project import get_project_settings -from pathlib2 import Path +from pathlib import Path class FileFeedStorageTest(unittest.TestCase):