From 5a55c4269d3389df4e486657caa58985f8e37e5b Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Thu, 31 Jan 2019 17:20:29 -0200 Subject: [PATCH 01/15] Adding GCSFeedStorage --- scrapy/extensions/feedexport.py | 26 ++++++++++++++++++ tests/test_feedexport.py | 48 ++++++++++++++++++++++++++++++++- 2 files changed, 73 insertions(+), 1 deletion(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index 22ebf3b3f..00d5d8025 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -146,6 +146,32 @@ class S3FeedStorage(BlockingFeedStorage): key.close() + +class GCSFeedStorage(BlockingFeedStorage): + + project_id = None + bucket_name = None + blob_name = None + + def __init__(self, uri, project_id): + self.project_id = project_id + u = urlparse(uri) + self.bucket_name = u.hostname + self.blob_name = u.path[1:] # remove first "/" + + @classmethod + def from_crawler(cls, crawler, uri): + return cls(uri, crawler.settings['GCS_PROJECT_ID']) + + def _store_in_thread(self, file): + file.seek(0) + from google.cloud.storage import Client + client = Client(project=self.project_id) + bucket = client.get_bucket(self.bucket_name) + blob = bucket.blob(self.blob_name) + blob.upload_from_file(file) + + class FTPFeedStorage(BlockingFeedStorage): def __init__(self, uri): diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index e46c8c14e..f3c499b3f 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -21,7 +21,7 @@ from w3lib.url import path_to_file_uri import scrapy from scrapy.exporters import CsvItemExporter from scrapy.extensions.feedexport import ( - IFeedStorage, FileFeedStorage, FTPFeedStorage, + IFeedStorage, FileFeedStorage, FTPFeedStorage, GCSFeedStorage, S3FeedStorage, StdoutFeedStorage, BlockingFeedStorage) from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete, get_crawler @@ -187,6 +187,52 @@ class S3FeedStorageTest(unittest.TestCase): self.assertEqual(content, expected_content) +class GCSFeedStorageTest(unittest.TestCase): + + @mock.patch('scrapy.conf.settings', + new={'GCS_PROJECT_ID': 'conf_id' }, create=True) + def test_parse_settings(self): + try: + from google.cloud.storage import Client + except ImportError: + raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") + + settings = {'GCS_PROJECT_ID': '123' } + crawler = get_crawler(settings_dict=settings) + storage = GCSFeedStorage.from_crawler(crawler, 'gcs://mybucket/export.csv') + assert storage.project_id == '123' + assert storage.bucket_name == 'mybucket' + assert storage.blob_name == 'export.csv' + + @defer.inlineCallbacks + def test_store(self): + try: + from google.cloud.storage import Client, Bucket, Blob + except ImportError: + raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") + + uri = 'gcs://mybucket/export.csv' + project_id = 'myproject-123' + with mock.patch('google.cloud.storage.Client') as m: + client_mock = mock.create_autospec(Client) + m.return_value = client_mock + + bucket_mock = mock.create_autospec(Bucket) + client_mock.get_bucket.return_value = bucket_mock + + blob_mock = mock.create_autospec(Blob) + bucket_mock.blob.return_value = blob_mock + + f = mock.Mock() + storage = GCSFeedStorage(uri, project_id) + yield storage.store(f) + + f.seek.assert_called_once_with(0) + m.assert_called_once_with(project=project_id) + client_mock.get_bucket.assert_called_once_with('mybucket') + bucket_mock.blob.assert_called_once_with('export.csv') + blob_mock.upload_from_file.assert_called_once_with(f) + class StdoutFeedStorageTest(unittest.TestCase): @defer.inlineCallbacks From a4059851e7b6c8d712b2bc73dbff99be2d569d21 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Thu, 31 Jan 2019 18:29:15 -0200 Subject: [PATCH 02/15] Refactoring tests --- scrapy/utils/test.py | 16 ++++++++++++++++ tests/test_feedexport.py | 15 +++++---------- 2 files changed, 21 insertions(+), 10 deletions(-) diff --git a/scrapy/utils/test.py b/scrapy/utils/test.py index 4b935c51b..84eae97a7 100644 --- a/scrapy/utils/test.py +++ b/scrapy/utils/test.py @@ -7,6 +7,7 @@ import os from importlib import import_module from twisted.trial.unittest import SkipTest +from tests import mock from scrapy.exceptions import NotConfigured from scrapy.utils.boto import is_botocore @@ -91,3 +92,18 @@ def assert_samelines(testcase, text1, text2, msg=None): line endings between platforms """ testcase.assertEqual(text1.splitlines(), text2.splitlines(), msg) + +def mock_google_cloud_storage(): + """Creates autospec mocks for google-cloud-storage Client, Bucket and Blob + classes and set their proper return values. + """ + from google.cloud.storage import Client, Bucket, Blob + client_mock = mock.create_autospec(Client) + + bucket_mock = mock.create_autospec(Bucket) + client_mock.get_bucket.return_value = bucket_mock + + blob_mock = mock.create_autospec(Blob) + bucket_mock.blob.return_value = blob_mock + + return (client_mock, bucket_mock, blob_mock) \ No newline at end of file diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index f3c499b3f..6d23c68c3 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -24,7 +24,8 @@ from scrapy.extensions.feedexport import ( IFeedStorage, FileFeedStorage, FTPFeedStorage, GCSFeedStorage, S3FeedStorage, StdoutFeedStorage, BlockingFeedStorage) -from scrapy.utils.test import assert_aws_environ, get_s3_content_and_delete, get_crawler +from scrapy.utils.test import (assert_aws_environ, get_s3_content_and_delete, + get_crawler, mock_google_cloud_storage) from scrapy.utils.python import to_native_str @@ -207,22 +208,16 @@ class GCSFeedStorageTest(unittest.TestCase): @defer.inlineCallbacks def test_store(self): try: - from google.cloud.storage import Client, Bucket, Blob + from google.cloud.storage import Client except ImportError: raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") uri = 'gcs://mybucket/export.csv' project_id = 'myproject-123' - with mock.patch('google.cloud.storage.Client') as m: - client_mock = mock.create_autospec(Client) + (client_mock, bucket_mock, blob_mock) = mock_google_cloud_storage() + with mock.patch('google.cloud.storage.Client') as m: m.return_value = client_mock - bucket_mock = mock.create_autospec(Bucket) - client_mock.get_bucket.return_value = bucket_mock - - blob_mock = mock.create_autospec(Blob) - bucket_mock.blob.return_value = blob_mock - f = mock.Mock() storage = GCSFeedStorage(uri, project_id) yield storage.store(f) From 1bb6c4154c43d03d00147d810147c4f3c807505e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 8 Feb 2019 09:04:01 -0200 Subject: [PATCH 03/15] Turning into instance attributes --- scrapy/extensions/feedexport.py | 4 ---- 1 file changed, 4 deletions(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index 00d5d8025..a81f44045 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -149,10 +149,6 @@ class S3FeedStorage(BlockingFeedStorage): class GCSFeedStorage(BlockingFeedStorage): - project_id = None - bucket_name = None - blob_name = None - def __init__(self, uri, project_id): self.project_id = project_id u = urlparse(uri) From fc6809b024dc25663432b6c0c5780021a827ea20 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 8 Feb 2019 09:08:54 -0200 Subject: [PATCH 04/15] Add gcs schema to FEED_STORAGES_BASE --- scrapy/settings/default_settings.py | 1 + 1 file changed, 1 insertion(+) diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 3734a0a58..1a12f35a3 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -145,6 +145,7 @@ FEED_STORAGES_BASE = { 'stdout': 'scrapy.extensions.feedexport.StdoutFeedStorage', 's3': 'scrapy.extensions.feedexport.S3FeedStorage', 'ftp': 'scrapy.extensions.feedexport.FTPFeedStorage', + 'gcs': 'scrapy.extensions.feedexport.GCSFeedStorage', } FEED_EXPORTERS = {} FEED_EXPORTERS_BASE = { From 4a53de165a53433a9a2a8cc4db34e5507c47fbd5 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 8 Feb 2019 09:09:56 -0200 Subject: [PATCH 05/15] Sorted schemas alphabetically --- scrapy/extensions/feedexport.py | 1 - scrapy/settings/default_settings.py | 4 ++-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index a81f44045..8347b42ca 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -146,7 +146,6 @@ class S3FeedStorage(BlockingFeedStorage): key.close() - class GCSFeedStorage(BlockingFeedStorage): def __init__(self, uri, project_id): diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 1a12f35a3..8769c01ba 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -142,10 +142,10 @@ FEED_STORAGES = {} FEED_STORAGES_BASE = { '': 'scrapy.extensions.feedexport.FileFeedStorage', 'file': 'scrapy.extensions.feedexport.FileFeedStorage', - 'stdout': 'scrapy.extensions.feedexport.StdoutFeedStorage', - 's3': 'scrapy.extensions.feedexport.S3FeedStorage', 'ftp': 'scrapy.extensions.feedexport.FTPFeedStorage', 'gcs': 'scrapy.extensions.feedexport.GCSFeedStorage', + 's3': 'scrapy.extensions.feedexport.S3FeedStorage', + 'stdout': 'scrapy.extensions.feedexport.StdoutFeedStorage', } FEED_EXPORTERS = {} FEED_EXPORTERS_BASE = { From 2bbbd02bda368c2f052f3aa38f99498a632328bb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 8 Feb 2019 09:45:10 -0200 Subject: [PATCH 06/15] Adding an option to set ACL while uploading the blob to GCS --- scrapy/extensions/feedexport.py | 11 ++++++++--- scrapy/settings/default_settings.py | 2 ++ tests/test_feedexport.py | 10 ++++++---- 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index 8347b42ca..fbbf9bb97 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -148,15 +148,20 @@ class S3FeedStorage(BlockingFeedStorage): class GCSFeedStorage(BlockingFeedStorage): - def __init__(self, uri, project_id): + def __init__(self, uri, project_id, acl): self.project_id = project_id + self.acl = acl u = urlparse(uri) self.bucket_name = u.hostname self.blob_name = u.path[1:] # remove first "/" @classmethod def from_crawler(cls, crawler, uri): - return cls(uri, crawler.settings['GCS_PROJECT_ID']) + return cls( + uri, + crawler.settings['GCS_PROJECT_ID'], + crawler.settings['FEED_STORAGE_GCS_ACL'] + ) def _store_in_thread(self, file): file.seek(0) @@ -164,7 +169,7 @@ class GCSFeedStorage(BlockingFeedStorage): client = Client(project=self.project_id) bucket = client.get_bucket(self.bucket_name) blob = bucket.blob(self.blob_name) - blob.upload_from_file(file) + blob.upload_from_file(file, predefined_acl=self.acl) class FTPFeedStorage(BlockingFeedStorage): diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 8769c01ba..5d2862980 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -159,6 +159,8 @@ FEED_EXPORTERS_BASE = { } FEED_EXPORT_INDENT = 0 +FEED_STORAGE_GCS_ACL = None + FILES_STORE_S3_ACL = 'private' FILES_STORE_GCS_ACL = '' diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 6d23c68c3..5cbca6d28 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -191,17 +191,18 @@ class S3FeedStorageTest(unittest.TestCase): class GCSFeedStorageTest(unittest.TestCase): @mock.patch('scrapy.conf.settings', - new={'GCS_PROJECT_ID': 'conf_id' }, create=True) + new={'GCS_PROJECT_ID': 'conf_id', 'FEED_STORAGE_GCS_ACL': None }, create=True) def test_parse_settings(self): try: from google.cloud.storage import Client except ImportError: raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") - settings = {'GCS_PROJECT_ID': '123' } + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': 'publicRead' } crawler = get_crawler(settings_dict=settings) storage = GCSFeedStorage.from_crawler(crawler, 'gcs://mybucket/export.csv') assert storage.project_id == '123' + assert storage.acl == 'publicRead' assert storage.bucket_name == 'mybucket' assert storage.blob_name == 'export.csv' @@ -214,19 +215,20 @@ class GCSFeedStorageTest(unittest.TestCase): uri = 'gcs://mybucket/export.csv' project_id = 'myproject-123' + acl = 'publicRead' (client_mock, bucket_mock, blob_mock) = mock_google_cloud_storage() with mock.patch('google.cloud.storage.Client') as m: m.return_value = client_mock f = mock.Mock() - storage = GCSFeedStorage(uri, project_id) + storage = GCSFeedStorage(uri, project_id, acl) yield storage.store(f) f.seek.assert_called_once_with(0) m.assert_called_once_with(project=project_id) client_mock.get_bucket.assert_called_once_with('mybucket') bucket_mock.blob.assert_called_once_with('export.csv') - blob_mock.upload_from_file.assert_called_once_with(f) + blob_mock.upload_from_file.assert_called_once_with(f, predefined_acl=acl) class StdoutFeedStorageTest(unittest.TestCase): From cb5f800b0f7029d2bf2e09e9bc1391078c133a92 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 8 Feb 2019 11:26:33 -0200 Subject: [PATCH 07/15] Adding documentation about Google Cloud Storage Feed Export --- docs/topics/feed-exports.rst | 22 ++++++++++++++++++++++ docs/topics/settings.rst | 18 ++++++++++++++++++ scrapy/settings/default_settings.py | 2 ++ 3 files changed, 42 insertions(+) diff --git a/docs/topics/feed-exports.rst b/docs/topics/feed-exports.rst index b64dbfbfd..efb63b0ba 100644 --- a/docs/topics/feed-exports.rst +++ b/docs/topics/feed-exports.rst @@ -185,6 +185,27 @@ passed through the following settings: * :setting:`AWS_ACCESS_KEY_ID` * :setting:`AWS_SECRET_ACCESS_KEY` +.. _topics-feed-storage-gcs: + +Google Cloud Storage (GCS) +-------------------------- + +The feeds are stored on `Google Cloud Storage`_. + + * URI scheme: ``gcs`` + * Example URIs: + + * ``gcs://mybucket/path/to/export.csv`` + + * Required external libraries: `google-cloud-storage `_. + +For more information about authentication, please refer to `Google Cloud documentation `_. + +You can set a *Project ID* and *Access Control List (ACL)* through the following settings: + + * :setting:`FEED_STORAGE_GCS_ACL` + * :setting:`GCS_PROJECT_ID` + .. _topics-feed-storage-stdout: Standard output @@ -366,3 +387,4 @@ format in :setting:`FEED_EXPORTERS`. E.g., to disable the built-in CSV exporter .. _Amazon S3: https://aws.amazon.com/s3/ .. _boto: https://github.com/boto/boto .. _botocore: https://github.com/boto/botocore +.. _Google Cloud Storage: https://cloud.google.com/storage/ \ No newline at end of file diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst index 0ac26a9bd..90ae8fd93 100644 --- a/docs/topics/settings.rst +++ b/docs/topics/settings.rst @@ -749,6 +749,14 @@ The Feed Temp dir allows you to set a custom folder to save crawler temporary files before uploading with :ref:`FTP feed storage ` and :ref:`Amazon S3 `. +.. setting:: FEED_STORAGE_GCS_ACL + +FEED_STORAGE_GCS_ACL +-------------------- + +The Access Control List (ACL) used when storing items to :ref:`Google Cloud Storage `. +For more information on how to set this value, please refer to `Google Cloud documentation `_. + .. setting:: FTP_PASSIVE_MODE FTP_PASSIVE_MODE @@ -786,6 +794,15 @@ Default: ``"anonymous"`` The username to use for FTP connections when there is no ``"ftp_user"`` in ``Request`` meta. +.. setting:: GCS_PROJECT_ID + +GCS_PROJECT_ID +----------------- + +Default: ``None`` + +The Project ID that will be used when storing data on `Google Cloud Storage`_. + .. setting:: ITEM_PIPELINES ITEM_PIPELINES @@ -1371,3 +1388,4 @@ case to see how to enable and use them. .. _Amazon web services: https://aws.amazon.com/ .. _breadth-first order: https://en.wikipedia.org/wiki/Breadth-first_search .. _depth-first order: https://en.wikipedia.org/wiki/Depth-first_search +.. _Google Cloud Storage: https://cloud.google.com/storage/ \ No newline at end of file diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 5d2862980..c17e94a64 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -168,6 +168,8 @@ FTP_USER = 'anonymous' FTP_PASSWORD = 'guest' FTP_PASSIVE_MODE = True +GCS_PROJECT_ID = None + HTTPCACHE_ENABLED = False HTTPCACHE_DIR = 'httpcache' HTTPCACHE_IGNORE_MISSING = False From 0bb3d8ca93cf68e0ef231ee734f8a1a3c4075a72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Wed, 27 Feb 2019 18:41:01 -0300 Subject: [PATCH 08/15] Updating Google Cloud Storage scheme to gs instead of gcs --- docs/topics/feed-exports.rst | 4 ++-- scrapy/settings/default_settings.py | 2 +- tests/test_feedexport.py | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/topics/feed-exports.rst b/docs/topics/feed-exports.rst index efb63b0ba..0957a5997 100644 --- a/docs/topics/feed-exports.rst +++ b/docs/topics/feed-exports.rst @@ -192,10 +192,10 @@ Google Cloud Storage (GCS) The feeds are stored on `Google Cloud Storage`_. - * URI scheme: ``gcs`` + * URI scheme: ``gs`` * Example URIs: - * ``gcs://mybucket/path/to/export.csv`` + * ``gs://mybucket/path/to/export.csv`` * Required external libraries: `google-cloud-storage `_. diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index c17e94a64..50fcd1d0a 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -143,7 +143,7 @@ FEED_STORAGES_BASE = { '': 'scrapy.extensions.feedexport.FileFeedStorage', 'file': 'scrapy.extensions.feedexport.FileFeedStorage', 'ftp': 'scrapy.extensions.feedexport.FTPFeedStorage', - 'gcs': 'scrapy.extensions.feedexport.GCSFeedStorage', + 'gs': 'scrapy.extensions.feedexport.GCSFeedStorage', 's3': 'scrapy.extensions.feedexport.S3FeedStorage', 'stdout': 'scrapy.extensions.feedexport.StdoutFeedStorage', } diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 5cbca6d28..41df7d7af 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -200,7 +200,7 @@ class GCSFeedStorageTest(unittest.TestCase): settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': 'publicRead' } crawler = get_crawler(settings_dict=settings) - storage = GCSFeedStorage.from_crawler(crawler, 'gcs://mybucket/export.csv') + storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') assert storage.project_id == '123' assert storage.acl == 'publicRead' assert storage.bucket_name == 'mybucket' From 2cb4dc32052c306568206f0997de4b4e53069efd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Fri, 22 Mar 2019 09:50:11 -0300 Subject: [PATCH 09/15] Mentioning to use JSON API for ACLs --- docs/topics/settings.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/topics/settings.rst b/docs/topics/settings.rst index 90ae8fd93..fcdf31cac 100644 --- a/docs/topics/settings.rst +++ b/docs/topics/settings.rst @@ -755,7 +755,7 @@ FEED_STORAGE_GCS_ACL -------------------- The Access Control List (ACL) used when storing items to :ref:`Google Cloud Storage `. -For more information on how to set this value, please refer to `Google Cloud documentation `_. +For more information on how to set this value, please refer to the column *JSON API* in `Google Cloud documentation `_. .. setting:: FTP_PASSIVE_MODE @@ -1388,4 +1388,4 @@ case to see how to enable and use them. .. _Amazon web services: https://aws.amazon.com/ .. _breadth-first order: https://en.wikipedia.org/wiki/Breadth-first_search .. _depth-first order: https://en.wikipedia.org/wiki/Depth-first_search -.. _Google Cloud Storage: https://cloud.google.com/storage/ \ No newline at end of file +.. _Google Cloud Storage: https://cloud.google.com/storage/ From 110bc92e6b9c9c3ce1775a9ca1487df42a80d219 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?J=C3=BAlio=20C=C3=A9sar=20Batista?= Date: Thu, 29 Aug 2019 11:10:00 -0300 Subject: [PATCH 10/15] Fix default value of FEED_STORAGE_GCS_ACL --- scrapy/extensions/feedexport.py | 2 +- scrapy/settings/default_settings.py | 2 +- tests/test_feedexport.py | 18 ++++++++++++++++++ 3 files changed, 20 insertions(+), 2 deletions(-) diff --git a/scrapy/extensions/feedexport.py b/scrapy/extensions/feedexport.py index fbbf9bb97..1e982c684 100644 --- a/scrapy/extensions/feedexport.py +++ b/scrapy/extensions/feedexport.py @@ -160,7 +160,7 @@ class GCSFeedStorage(BlockingFeedStorage): return cls( uri, crawler.settings['GCS_PROJECT_ID'], - crawler.settings['FEED_STORAGE_GCS_ACL'] + crawler.settings['FEED_STORAGE_GCS_ACL'] or None ) def _store_in_thread(self, file): diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 50fcd1d0a..45257a61c 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -159,7 +159,7 @@ FEED_EXPORTERS_BASE = { } FEED_EXPORT_INDENT = 0 -FEED_STORAGE_GCS_ACL = None +FEED_STORAGE_GCS_ACL = '' FILES_STORE_S3_ACL = 'private' FILES_STORE_GCS_ACL = '' diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index 41df7d7af..69f144d07 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -206,6 +206,24 @@ class GCSFeedStorageTest(unittest.TestCase): assert storage.bucket_name == 'mybucket' assert storage.blob_name == 'export.csv' + @mock.patch('scrapy.conf.settings', + new={'GCS_PROJECT_ID': 'conf_id', 'FEED_STORAGE_GCS_ACL': '' }, create=True) + def test_parse_empty_acl(self): + try: + from google.cloud.storage import Client + except ImportError: + raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") + + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': '' } + crawler = get_crawler(settings_dict=settings) + storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') + assert storage.acl is None + + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': None } + crawler = get_crawler(settings_dict=settings) + storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') + assert storage.acl is None + @defer.inlineCallbacks def test_store(self): try: From 7025c18b159f1ce14b5732dc7d262efbdc72cf5e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Mon, 10 Feb 2020 19:43:23 +0100 Subject: [PATCH 11/15] Clear line of spaces --- docs/topics/feed-exports.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/topics/feed-exports.rst b/docs/topics/feed-exports.rst index 9f837221e..8dc08710f 100644 --- a/docs/topics/feed-exports.rst +++ b/docs/topics/feed-exports.rst @@ -184,7 +184,7 @@ passed through the following settings: * :setting:`AWS_ACCESS_KEY_ID` * :setting:`AWS_SECRET_ACCESS_KEY` - + You can also define a custom ACL for exported feeds using this setting: * :setting:`FEED_STORAGE_S3_ACL` From 73e88d036c72aa628af50371aace4cfce7e286e0 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Wed, 12 Feb 2020 17:17:38 +0100 Subject: [PATCH 12/15] Import mock from unittest --- scrapy/utils/test.py | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/scrapy/utils/test.py b/scrapy/utils/test.py index 4ff6d73a5..00002c303 100644 --- a/scrapy/utils/test.py +++ b/scrapy/utils/test.py @@ -2,14 +2,13 @@ This module contains some assorted functions used in tests """ -from __future__ import absolute_import -from posixpath import split import asyncio import os +from posixpath import split +from unittest import mock from importlib import import_module from twisted.trial.unittest import SkipTest -from tests import mock from scrapy.exceptions import NotConfigured from scrapy.utils.boto import is_botocore From e1be078eaa17a8df72716932fde07e225f79745f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Wed, 12 Feb 2020 17:38:06 +0100 Subject: [PATCH 13/15] Fix Flake8-reported issues --- scrapy/utils/test.py | 2 ++ tests/test_feedexport.py | 27 ++++++++++++++------------- 2 files changed, 16 insertions(+), 13 deletions(-) diff --git a/scrapy/utils/test.py b/scrapy/utils/test.py index 00002c303..7442a2f33 100644 --- a/scrapy/utils/test.py +++ b/scrapy/utils/test.py @@ -120,12 +120,14 @@ def assert_samelines(testcase, text1, text2, msg=None): """ testcase.assertEqual(text1.splitlines(), text2.splitlines(), msg) + def get_from_asyncio_queue(value): q = asyncio.Queue() getter = q.get() q.put_nowait(value) return getter + def mock_google_cloud_storage(): """Creates autospec mocks for google-cloud-storage Client, Bucket and Blob classes and set their proper return values. diff --git a/tests/test_feedexport.py b/tests/test_feedexport.py index d97b199fe..2b299503b 100644 --- a/tests/test_feedexport.py +++ b/tests/test_feedexport.py @@ -25,9 +25,13 @@ from scrapy.extensions.feedexport import ( IFeedStorage, FileFeedStorage, FTPFeedStorage, GCSFeedStorage, S3FeedStorage, StdoutFeedStorage, BlockingFeedStorage) -from scrapy.utils.test import (assert_aws_environ, get_s3_content_and_delete, - get_crawler, mock_google_cloud_storage) from scrapy.utils.python import to_unicode +from scrapy.utils.test import ( + assert_aws_environ, + get_s3_content_and_delete, + get_crawler, + mock_google_cloud_storage, +) class FileFeedStorageTest(unittest.TestCase): @@ -362,15 +366,13 @@ class S3FeedStorageTest(unittest.TestCase): class GCSFeedStorageTest(unittest.TestCase): - @mock.patch('scrapy.conf.settings', - new={'GCS_PROJECT_ID': 'conf_id', 'FEED_STORAGE_GCS_ACL': None }, create=True) def test_parse_settings(self): try: - from google.cloud.storage import Client + from google.cloud.storage import Client # noqa except ImportError: raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") - settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': 'publicRead' } + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': 'publicRead'} crawler = get_crawler(settings_dict=settings) storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') assert storage.project_id == '123' @@ -378,20 +380,18 @@ class GCSFeedStorageTest(unittest.TestCase): assert storage.bucket_name == 'mybucket' assert storage.blob_name == 'export.csv' - @mock.patch('scrapy.conf.settings', - new={'GCS_PROJECT_ID': 'conf_id', 'FEED_STORAGE_GCS_ACL': '' }, create=True) def test_parse_empty_acl(self): try: - from google.cloud.storage import Client + from google.cloud.storage import Client # noqa except ImportError: raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") - settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': '' } + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': ''} crawler = get_crawler(settings_dict=settings) storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') assert storage.acl is None - settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': None } + settings = {'GCS_PROJECT_ID': '123', 'FEED_STORAGE_GCS_ACL': None} crawler = get_crawler(settings_dict=settings) storage = GCSFeedStorage.from_crawler(crawler, 'gs://mybucket/export.csv') assert storage.acl is None @@ -399,7 +399,7 @@ class GCSFeedStorageTest(unittest.TestCase): @defer.inlineCallbacks def test_store(self): try: - from google.cloud.storage import Client + from google.cloud.storage import Client # noqa except ImportError: raise unittest.SkipTest("GCSFeedStorage requires google-cloud-storage") @@ -407,7 +407,7 @@ class GCSFeedStorageTest(unittest.TestCase): project_id = 'myproject-123' acl = 'publicRead' (client_mock, bucket_mock, blob_mock) = mock_google_cloud_storage() - with mock.patch('google.cloud.storage.Client') as m: + with mock.patch('google.cloud.storage.Client') as m: m.return_value = client_mock f = mock.Mock() @@ -420,6 +420,7 @@ class GCSFeedStorageTest(unittest.TestCase): bucket_mock.blob.assert_called_once_with('export.csv') blob_mock.upload_from_file.assert_called_once_with(f, predefined_acl=acl) + class StdoutFeedStorageTest(unittest.TestCase): @defer.inlineCallbacks From b99fe4aa4c35ff8f5c2355a09988ddb1e90d6b70 Mon Sep 17 00:00:00 2001 From: Eugenio Lacuesta Date: Fri, 19 Jun 2020 21:41:15 -0300 Subject: [PATCH 14/15] Add google-cloud-storage to the 'pinned' tox environment --- tox.ini | 1 + 1 file changed, 1 insertion(+) diff --git a/tox.ini b/tox.ini index 4c790158d..d28eab131 100644 --- a/tox.ini +++ b/tox.ini @@ -76,6 +76,7 @@ deps = -rtests/requirements-py3.txt # Extras botocore==1.3.23 + google-cloud-storage==1.29.0 Pillow==3.4.2 [testenv:extra-deps] From cfd039aeb6d46f7c120edd82ce06d6b9f4f8e7db Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Mon, 22 Jun 2020 19:28:33 +0200 Subject: [PATCH 15/15] Remove a duplicate GCS_PROJECT_ID reference target --- docs/topics/media-pipeline.rst | 1 - 1 file changed, 1 deletion(-) diff --git a/docs/topics/media-pipeline.rst b/docs/topics/media-pipeline.rst index 01de3dedb..096618648 100644 --- a/docs/topics/media-pipeline.rst +++ b/docs/topics/media-pipeline.rst @@ -204,7 +204,6 @@ For self-hosting you also might feel the need not to use SSL and not to verify S Google Cloud Storage --------------------- -.. setting:: GCS_PROJECT_ID .. setting:: FILES_STORE_GCS_ACL .. setting:: IMAGES_STORE_GCS_ACL