From 07b8cd28aa84fb322a072467b49e2557d4aa3881 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Thu, 5 Dec 2019 14:48:31 +0100 Subject: [PATCH 1/9] =?UTF-8?q?Mark=20bandit=E2=80=99s=20402=20check=20as?= =?UTF-8?q?=20addressed=20by=20#4180=20(#4181)?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .bandit.yml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.bandit.yml b/.bandit.yml index cc7db3a66..243379b0b 100644 --- a/.bandit.yml +++ b/.bandit.yml @@ -8,7 +8,7 @@ skips: - B311 - B320 - B321 -- B402 +- B402 # https://github.com/scrapy/scrapy/issues/4180 - B403 - B404 - B406 From 02cdc53fb82e3cc5e51771180f1f79186b52670a Mon Sep 17 00:00:00 2001 From: Andrey Rahmatullin Date: Fri, 13 Dec 2019 18:04:05 +0500 Subject: [PATCH 2/9] Add a test for a CrawlerProcess script. (#4218) * Add a test for a CrawlerProcess script. * Add tests/CrawlerProcess to collect_ignore. * Remove an extra line. * Fix/improve conftest.py. --- conftest.py | 9 ++++++++- tests/CrawlerProcess/simple.py | 15 +++++++++++++++ tests/test_crawler.py | 20 ++++++++++++++++++++ 3 files changed, 43 insertions(+), 1 deletion(-) create mode 100644 tests/CrawlerProcess/simple.py diff --git a/conftest.py b/conftest.py index d54ce155c..d37c22436 100644 --- a/conftest.py +++ b/conftest.py @@ -1,12 +1,19 @@ +from pathlib import Path + import pytest +def _py_files(folder): + return (str(p) for p in Path(folder).rglob('*.py')) + + collect_ignore = [ # not a test, but looks like a test "scrapy/utils/testsite.py", + # contains scripts to be run by tests/test_crawler.py::CrawlerProcessSubprocess + *_py_files("tests/CrawlerProcess") ] - for line in open('tests/ignores.txt'): file_path = line.strip() if file_path and file_path[0] != '#': diff --git a/tests/CrawlerProcess/simple.py b/tests/CrawlerProcess/simple.py new file mode 100644 index 000000000..5f6f1ae30 --- /dev/null +++ b/tests/CrawlerProcess/simple.py @@ -0,0 +1,15 @@ +import scrapy +from scrapy.crawler import CrawlerProcess + + +class NoRequestsSpider(scrapy.Spider): + name = 'no_request' + + def start_requests(self): + return [] + + +process = CrawlerProcess(settings={}) + +process.crawl(NoRequestsSpider) +process.start() diff --git a/tests/test_crawler.py b/tests/test_crawler.py index 8eb2389e2..e37a2ff0e 100644 --- a/tests/test_crawler.py +++ b/tests/test_crawler.py @@ -1,4 +1,7 @@ import logging +import os +import subprocess +import sys import warnings from twisted.internet import defer @@ -14,6 +17,7 @@ from scrapy.utils.spider import DefaultSpider from scrapy.utils.misc import load_object from scrapy.extensions.throttle import AutoThrottle from scrapy.extensions import telnet +from scrapy.utils.test import get_testenv class BaseCrawlerTest(unittest.TestCase): @@ -245,3 +249,19 @@ class CrawlerRunnerHasSpider(unittest.TestCase): yield runner.crawl(NoRequestsSpider) self.assertEqual(runner.bootstrap_failed, True) + + +class CrawlerProcessSubprocess(unittest.TestCase): + script_dir = os.path.join(os.path.abspath(os.path.dirname(__file__)), 'CrawlerProcess') + + def run_script(self, script_name): + script_path = os.path.join(self.script_dir, script_name) + args = (sys.executable, script_path) + p = subprocess.Popen(args, env=get_testenv(), + stdout=subprocess.PIPE, stderr=subprocess.PIPE) + stdout, stderr = p.communicate() + return stderr.decode('utf-8') + + def test_simple(self): + log = self.run_script('simple.py') + self.assertIn('Spider closed (finished)', log) From b5c4c2cae89714479d6fbb5a497fe43d48d886bc Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Adri=C3=A1n=20Chaves?= Date: Fri, 13 Dec 2019 14:20:48 +0100 Subject: [PATCH 3/9] Keep 2 spaces between code and inline comments (#4195) --- pytest.ini | 35 +++++++++++++------------- scrapy/core/downloader/webclient.py | 2 +- scrapy/core/engine.py | 2 +- scrapy/core/scraper.py | 2 +- scrapy/exporters.py | 2 +- scrapy/settings/default_settings.py | 4 +-- scrapy/spiders/feed.py | 4 +-- scrapy/utils/console.py | 8 +++--- tests/test_command_fetch.py | 2 +- tests/test_downloader_handlers.py | 2 +- tests/test_engine.py | 1 - tests/test_http_request.py | 2 +- tests/test_pipeline_media.py | 6 ++--- tests/test_spidermiddleware_referer.py | 20 +++++++-------- tests/test_utils_defer.py | 8 +++--- tests/test_utils_spider.py | 13 ++++------ 16 files changed, 54 insertions(+), 59 deletions(-) diff --git a/pytest.ini b/pytest.ini index 33c34b8e8..1b23595c0 100644 --- a/pytest.ini +++ b/pytest.ini @@ -26,8 +26,8 @@ flake8-ignore = scrapy/http/__init__.py F401 # Issues pending a review: # extras - extras/qps-bench-server.py E261 E501 - extras/qpsclient.py E501 E261 E501 + extras/qps-bench-server.py E501 + extras/qpsclient.py E501 E501 # scrapy/commands scrapy/commands/__init__.py E128 E501 scrapy/commands/check.py E501 @@ -45,15 +45,15 @@ flake8-ignore = scrapy/contracts/__init__.py E501 W504 scrapy/contracts/default.py E502 E128 # scrapy/core - scrapy/core/engine.py E261 E501 E128 E127 E306 E502 + scrapy/core/engine.py E501 E128 E127 E306 E502 scrapy/core/scheduler.py E501 - scrapy/core/scraper.py E501 E306 E261 E128 W504 + scrapy/core/scraper.py E501 E306 E128 W504 scrapy/core/spidermw.py E501 E731 E502 E126 E226 scrapy/core/downloader/__init__.py E501 scrapy/core/downloader/contextfactory.py E501 E128 E126 scrapy/core/downloader/middleware.py E501 E502 scrapy/core/downloader/tls.py E501 E305 E241 - scrapy/core/downloader/webclient.py E731 E501 E261 E502 E128 E126 E226 + scrapy/core/downloader/webclient.py E731 E501 E502 E128 E126 E226 scrapy/core/downloader/handlers/__init__.py E501 scrapy/core/downloader/handlers/ftp.py E501 E305 E128 E127 scrapy/core/downloader/handlers/http10.py E501 @@ -102,7 +102,7 @@ flake8-ignore = scrapy/selector/unified.py E501 E111 # scrapy/settings scrapy/settings/__init__.py E501 - scrapy/settings/default_settings.py E501 E261 E114 E116 E226 + scrapy/settings/default_settings.py E501 E114 E116 E226 scrapy/settings/deprecated.py E501 # scrapy/spidermiddlewares scrapy/spidermiddlewares/httperror.py E501 @@ -112,17 +112,16 @@ flake8-ignore = # scrapy/spiders scrapy/spiders/__init__.py E501 E402 scrapy/spiders/crawl.py E501 - scrapy/spiders/feed.py E501 E261 + scrapy/spiders/feed.py E501 scrapy/spiders/sitemap.py E501 # scrapy/utils scrapy/utils/benchserver.py E501 scrapy/utils/conf.py E402 E502 E501 - scrapy/utils/console.py E261 E306 E305 + scrapy/utils/console.py E306 E305 scrapy/utils/datatypes.py E501 E226 scrapy/utils/decorators.py E501 scrapy/utils/defer.py E501 E128 scrapy/utils/deprecate.py E128 E501 E127 E502 - scrapy/utils/engine.py E261 scrapy/utils/gz.py E305 E501 W504 scrapy/utils/http.py F403 E226 scrapy/utils/httpobj.py E501 @@ -150,7 +149,7 @@ flake8-ignore = scrapy/crawler.py E501 scrapy/dupefilters.py E501 E202 scrapy/exceptions.py E501 - scrapy/exporters.py E501 E261 E226 + scrapy/exporters.py E501 E226 scrapy/interfaces.py E501 scrapy/item.py E501 E128 scrapy/link.py E501 @@ -171,7 +170,7 @@ flake8-ignore = tests/pipelines.py F841 E226 tests/spiders.py E501 E127 tests/test_closespider.py E501 E127 - tests/test_command_fetch.py E501 E261 + tests/test_command_fetch.py E501 tests/test_command_parse.py E501 E128 E303 E226 tests/test_command_shell.py E501 E128 tests/test_commands.py E128 E501 @@ -179,7 +178,7 @@ flake8-ignore = tests/test_crawl.py E501 E741 E265 tests/test_crawler.py F841 E306 E501 tests/test_dependencies.py F841 E501 E305 - tests/test_downloader_handlers.py E124 E127 E128 E225 E261 E265 E501 E502 E701 E126 E226 E123 + tests/test_downloader_handlers.py E124 E127 E128 E225 E265 E501 E502 E701 E126 E226 E123 tests/test_downloadermiddleware.py E501 tests/test_downloadermiddleware_ajaxcrawlable.py E501 tests/test_downloadermiddleware_cookies.py E731 E741 E501 E128 E303 E265 E126 @@ -194,13 +193,13 @@ flake8-ignore = tests/test_downloadermiddleware_robotstxt.py E501 tests/test_downloadermiddleware_stats.py E501 tests/test_dupefilters.py E221 E501 E741 W293 W291 E128 E124 - tests/test_engine.py E401 E501 E502 E128 E261 + tests/test_engine.py E401 E501 E502 E128 tests/test_exporters.py E501 E731 E306 E128 E124 tests/test_extension_telnet.py F841 tests/test_feedexport.py E501 F841 E241 tests/test_http_cookies.py E501 tests/test_http_headers.py E501 - tests/test_http_request.py E402 E501 E261 E127 E128 W293 E502 E128 E502 E126 E123 + tests/test_http_request.py E402 E501 E127 E128 W293 E502 E128 E502 E126 E123 tests/test_http_response.py E501 E301 E502 E128 E265 tests/test_item.py E701 E128 F841 E306 tests/test_link.py E501 @@ -212,7 +211,7 @@ flake8-ignore = tests/test_pipeline_crawl.py E131 E501 E128 E126 tests/test_pipeline_files.py E501 W293 E303 E272 E226 tests/test_pipeline_images.py F841 E501 E303 - tests/test_pipeline_media.py E501 E741 E731 E128 E261 E306 E502 + tests/test_pipeline_media.py E501 E741 E731 E128 E306 E502 tests/test_proxy_connect.py E501 E741 tests/test_request_cb_kwargs.py E501 tests/test_responsetypes.py E501 E305 @@ -224,12 +223,12 @@ flake8-ignore = tests/test_spidermiddleware_httperror.py E128 E501 E127 E121 tests/test_spidermiddleware_offsite.py E501 E128 E111 W293 tests/test_spidermiddleware_output_chain.py E501 W293 E226 - tests/test_spidermiddleware_referer.py E501 F841 E125 E201 E261 E124 E501 E241 E121 + tests/test_spidermiddleware_referer.py E501 F841 E125 E201 E124 E501 E241 E121 tests/test_squeues.py E501 E701 E741 tests/test_utils_conf.py E501 E303 E128 tests/test_utils_curl.py E501 tests/test_utils_datatypes.py E402 E501 E305 - tests/test_utils_defer.py E306 E261 E501 F841 E226 + tests/test_utils_defer.py E306 E501 F841 E226 tests/test_utils_deprecate.py F841 E306 E501 tests/test_utils_http.py E501 E502 E128 W504 tests/test_utils_iterators.py E501 E128 E129 E303 E241 @@ -240,7 +239,7 @@ flake8-ignore = tests/test_utils_response.py E501 tests/test_utils_signal.py E741 F841 E731 E226 tests/test_utils_sitemap.py E128 E501 E124 - tests/test_utils_spider.py E261 E305 + tests/test_utils_spider.py E305 tests/test_utils_template.py E305 tests/test_utils_url.py E501 E127 E305 E211 E125 E501 E226 E241 E126 E123 tests/test_webclient.py E501 E128 E122 E303 E402 E306 E226 E241 E123 E126 diff --git a/scrapy/core/downloader/webclient.py b/scrapy/core/downloader/webclient.py index 798346f19..f368c3bae 100644 --- a/scrapy/core/downloader/webclient.py +++ b/scrapy/core/downloader/webclient.py @@ -42,7 +42,7 @@ class ScrapyHTTPPageGetter(HTTPClient): delimiter = b'\n' def connectionMade(self): - self.headers = Headers() # bucket for response headers + self.headers = Headers() # bucket for response headers # Method command self.sendCommand(self.factory.method, self.factory.path) diff --git a/scrapy/core/engine.py b/scrapy/core/engine.py index fa913e528..829e69993 100644 --- a/scrapy/core/engine.py +++ b/scrapy/core/engine.py @@ -25,7 +25,7 @@ class Slot(object): def __init__(self, start_requests, close_if_idle, nextcall, scheduler): self.closing = False - self.inprogress = set() # requests in progress + self.inprogress = set() # requests in progress self.start_requests = iter(start_requests) self.close_if_idle = close_if_idle self.nextcall = nextcall diff --git a/scrapy/core/scraper.py b/scrapy/core/scraper.py index db463f989..b3d585cce 100644 --- a/scrapy/core/scraper.py +++ b/scrapy/core/scraper.py @@ -123,7 +123,7 @@ class Scraper(object): callback/errback""" assert isinstance(response, (Response, Failure)) - dfd = self._scrape2(response, request, spider) # returns spiders processed output + dfd = self._scrape2(response, request, spider) # returns spiders processed output dfd.addErrback(self.handle_spider_error, request, response, spider) dfd.addCallback(self.handle_spider_output, request, response, spider) return dfd diff --git a/scrapy/exporters.py b/scrapy/exporters.py index fcb55da67..5bf131312 100644 --- a/scrapy/exporters.py +++ b/scrapy/exporters.py @@ -199,7 +199,7 @@ class CsvItemExporter(BaseItemExporter): line_buffering=False, write_through=True, encoding=self.encoding, - newline='' # Windows needs this https://github.com/scrapy/scrapy/issues/3034 + newline='' # Windows needs this https://github.com/scrapy/scrapy/issues/3034 ) self.csv_writer = csv.writer(self.stream, **kwargs) self._headers_not_written = True diff --git a/scrapy/settings/default_settings.py b/scrapy/settings/default_settings.py index 5c9678c01..1e163e1fb 100644 --- a/scrapy/settings/default_settings.py +++ b/scrapy/settings/default_settings.py @@ -84,8 +84,8 @@ DOWNLOADER = 'scrapy.core.downloader.Downloader' DOWNLOADER_HTTPCLIENTFACTORY = 'scrapy.core.downloader.webclient.ScrapyHTTPClientFactory' DOWNLOADER_CLIENTCONTEXTFACTORY = 'scrapy.core.downloader.contextfactory.ScrapyClientContextFactory' DOWNLOADER_CLIENT_TLS_CIPHERS = 'DEFAULT' -DOWNLOADER_CLIENT_TLS_METHOD = 'TLS' # Use highest TLS/SSL protocol version supported by the platform, - # also allowing negotiation +# Use highest TLS/SSL protocol version supported by the platform, also allowing negotiation: +DOWNLOADER_CLIENT_TLS_METHOD = 'TLS' DOWNLOADER_CLIENT_TLS_VERBOSE_LOGGING = False DOWNLOADER_MIDDLEWARES = {} diff --git a/scrapy/spiders/feed.py b/scrapy/spiders/feed.py index 197812a26..c566f0236 100644 --- a/scrapy/spiders/feed.py +++ b/scrapy/spiders/feed.py @@ -100,8 +100,8 @@ class CSVFeedSpider(Spider): and the file's headers. """ - delimiter = None # When this is None, python's csv module's default delimiter is used - quotechar = None # When this is None, python's csv module's default quotechar is used + delimiter = None # When this is None, python's csv module's default delimiter is used + quotechar = None # When this is None, python's csv module's default quotechar is used headers = None def process_results(self, response, results): diff --git a/scrapy/utils/console.py b/scrapy/utils/console.py index 688e28c34..7eb40f0ce 100644 --- a/scrapy/utils/console.py +++ b/scrapy/utils/console.py @@ -47,7 +47,7 @@ def _embed_ptpython_shell(namespace={}, banner=''): def _embed_standard_shell(namespace={}, banner=''): """Start a standard python shell""" import code - try: # readline module is only available on unix systems + try: # readline module is only available on unix systems import readline except ImportError: pass @@ -72,9 +72,9 @@ def get_shell_embed_func(shells=None, known_shells=None): """Return the first acceptable shell-embed function from a given list of shell names. """ - if shells is None: # list, preference order of shells + if shells is None: # list, preference order of shells shells = DEFAULT_PYTHON_SHELLS.keys() - if known_shells is None: # available embeddable shells + if known_shells is None: # available embeddable shells known_shells = DEFAULT_PYTHON_SHELLS.copy() for shell in shells: if shell in known_shells: @@ -97,5 +97,5 @@ def start_python_console(namespace=None, banner='', shells=None): shell = get_shell_embed_func(shells) if shell is not None: shell(namespace=namespace, banner=banner) - except SystemExit: # raised when using exit() in python code.interact + except SystemExit: # raised when using exit() in python code.interact pass diff --git a/tests/test_command_fetch.py b/tests/test_command_fetch.py index 3fa3ed930..9d3c8fe73 100644 --- a/tests/test_command_fetch.py +++ b/tests/test_command_fetch.py @@ -29,6 +29,6 @@ class FetchTest(ProcessTest, SiteTest, unittest.TestCase): @defer.inlineCallbacks def test_headers(self): _, out, _ = yield self.execute([self.url('/text'), '--headers']) - out = out.replace(b'\r', b'') # required on win32 + out = out.replace(b'\r', b'') # required on win32 assert b'Server: TwistedWeb' in out, out assert b'Content-Type: text/plain' in out diff --git a/tests/test_downloader_handlers.py b/tests/test_downloader_handlers.py index 60124b93f..2db2417e8 100644 --- a/tests/test_downloader_handlers.py +++ b/tests/test_downloader_handlers.py @@ -349,7 +349,7 @@ class HttpTestCase(unittest.TestCase): return self.download_request(request, Spider('foo')).addCallback(_test) def test_payload(self): - body = b'1'*100 # PayloadResource requires body length to be 100 + body = b'1'*100 # PayloadResource requires body length to be 100 request = Request(self.getURL('payload'), method='POST', body=body) d = self.download_request(request, Spider('foo')) d.addCallback(lambda r: r.body) diff --git a/tests/test_engine.py b/tests/test_engine.py index 002c4e6bb..537df8d91 100644 --- a/tests/test_engine.py +++ b/tests/test_engine.py @@ -271,7 +271,6 @@ class EngineTest(unittest.TestCase): self.run.signals_catched[signals.spider_opened]) self.assertEqual({'spider': self.run.spider}, self.run.signals_catched[signals.spider_idle]) - self.run.signals_catched[signals.spider_closed].pop('spider_stats', None) # XXX: remove for scrapy 0.17 self.assertEqual({'spider': self.run.spider, 'reason': 'finished'}, self.run.signals_catched[signals.spider_closed]) diff --git a/tests/test_http_request.py b/tests/test_http_request.py index a98aa1e6f..57e7b457d 100644 --- a/tests/test_http_request.py +++ b/tests/test_http_request.py @@ -149,7 +149,7 @@ class RequestTest(unittest.TestCase): r2 = self.request_class(url="http://www.example.com/", body=b"") assert isinstance(r2.body, bytes) - self.assertEqual(r2.encoding, 'utf-8') # default encoding + self.assertEqual(r2.encoding, 'utf-8') # default encoding r3 = self.request_class(url="http://www.example.com/", body=u"Price: \xa3100", encoding='utf-8') assert isinstance(r3.body, bytes) diff --git a/tests/test_pipeline_media.py b/tests/test_pipeline_media.py index 0d23f51cc..1fcc5799e 100644 --- a/tests/test_pipeline_media.py +++ b/tests/test_pipeline_media.py @@ -238,10 +238,10 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): self.assertEqual(new_item['results'], [(True, rsp1), (False, fail)]) m = self.pipe._mockcalled # only once - self.assertEqual(m[0], 'get_media_requests') # first hook called + self.assertEqual(m[0], 'get_media_requests') # first hook called self.assertEqual(m.count('get_media_requests'), 1) self.assertEqual(m.count('item_completed'), 1) - self.assertEqual(m[-1], 'item_completed') # last hook called + self.assertEqual(m[-1], 'item_completed') # last hook called # twice, one per request self.assertEqual(m.count('media_to_download'), 2) # one to handle success and other for failure @@ -252,7 +252,7 @@ class MediaPipelineTestCase(BaseMediaPipelineTestCase): def test_get_media_requests(self): # returns single Request (without callback) req = Request('http://url') - item = dict(requests=req) # pass a single item + item = dict(requests=req) # pass a single item new_item = yield self.pipe.process_item(item, self.spider) assert new_item is item assert request_fingerprint(req) in self.info.downloaded diff --git a/tests/test_spidermiddleware_referer.py b/tests/test_spidermiddleware_referer.py index ecec6135d..7cc17600c 100644 --- a/tests/test_spidermiddleware_referer.py +++ b/tests/test_spidermiddleware_referer.py @@ -548,8 +548,8 @@ class TestReferrerOnRedirect(TestRefererMiddleware): (301, 'http://scrapytest.org/3'), (301, 'http://scrapytest.org/4'), ), - b'http://scrapytest.org/1', # expected initial referer - b'http://scrapytest.org/1', # expected referer for the redirection request + b'http://scrapytest.org/1', # expected initial referer + b'http://scrapytest.org/1', # expected referer for the redirection request ), ( 'https://scrapytest.org/1', 'https://scrapytest.org/2', @@ -609,8 +609,8 @@ class TestReferrerOnRedirectNoReferrer(TestReferrerOnRedirect): (301, 'http://scrapytest.org/3'), (301, 'http://scrapytest.org/4'), ), - None, # expected initial "Referer" - None, # expected "Referer" for the redirection request + None, # expected initial "Referer" + None, # expected "Referer" for the redirection request ), ( 'https://scrapytest.org/1', 'https://scrapytest.org/2', @@ -648,8 +648,8 @@ class TestReferrerOnRedirectSameOrigin(TestReferrerOnRedirect): (301, 'http://scrapytest.org/103'), (301, 'http://scrapytest.org/104'), ), - b'http://scrapytest.org/101', # expected initial "Referer" - b'http://scrapytest.org/101', # expected referer for the redirection request + b'http://scrapytest.org/101', # expected initial "Referer" + b'http://scrapytest.org/101', # expected referer for the redirection request ), ( 'https://scrapytest.org/201', 'https://scrapytest.org/202', @@ -757,8 +757,8 @@ class TestReferrerOnRedirectOriginWhenCrossOrigin(TestReferrerOnRedirect): (301, 'http://scrapytest.org/103'), (301, 'http://scrapytest.org/104'), ), - b'http://scrapytest.org/101', # expected initial referer - b'http://scrapytest.org/101', # expected referer for the redirection request + b'http://scrapytest.org/101', # expected initial referer + b'http://scrapytest.org/101', # expected referer for the redirection request ), ( 'https://scrapytest.org/201', 'https://scrapytest.org/202', @@ -827,8 +827,8 @@ class TestReferrerOnRedirectStrictOriginWhenCrossOrigin(TestReferrerOnRedirect): (301, 'http://scrapytest.org/103'), (301, 'http://scrapytest.org/104'), ), - b'http://scrapytest.org/101', # expected initial referer - b'http://scrapytest.org/101', # expected referer for the redirection request + b'http://scrapytest.org/101', # expected initial referer + b'http://scrapytest.org/101', # expected referer for the redirection request ), ( 'https://scrapytest.org/201', 'https://scrapytest.org/202', diff --git a/tests/test_utils_defer.py b/tests/test_utils_defer.py index 49c2befb5..dfbe71ae2 100644 --- a/tests/test_utils_defer.py +++ b/tests/test_utils_defer.py @@ -14,8 +14,8 @@ class MustbeDeferredTest(unittest.TestCase): return steps dfd = mustbe_deferred(_append, 1) - dfd.addCallback(self.assertEqual, [1, 2]) # it is [1] with maybeDeferred - steps.append(2) # add another value, that should be catched by assertEqual + dfd.addCallback(self.assertEqual, [1, 2]) # it is [1] with maybeDeferred + steps.append(2) # add another value, that should be catched by assertEqual return dfd def test_unfired_deferred(self): @@ -27,8 +27,8 @@ class MustbeDeferredTest(unittest.TestCase): return dfd dfd = mustbe_deferred(_append, 1) - dfd.addCallback(self.assertEqual, [1, 2]) # it is [1] with maybeDeferred - steps.append(2) # add another value, that should be catched by assertEqual + dfd.addCallback(self.assertEqual, [1, 2]) # it is [1] with maybeDeferred + steps.append(2) # add another value, that should be catched by assertEqual return dfd diff --git a/tests/test_utils_spider.py b/tests/test_utils_spider.py index edeeacc80..ee7d17062 100644 --- a/tests/test_utils_spider.py +++ b/tests/test_utils_spider.py @@ -1,20 +1,16 @@ import unittest + +from scrapy import Spider from scrapy.http import Request from scrapy.item import BaseItem from scrapy.utils.spider import iterate_spider_output, iter_spider_classes -from scrapy.spiders import CrawlSpider - -class MyBaseSpider(CrawlSpider): - pass # abstract spider - - -class MySpider1(MyBaseSpider): +class MySpider1(Spider): name = 'myspider1' -class MySpider2(MyBaseSpider): +class MySpider2(Spider): name = 'myspider2' @@ -35,5 +31,6 @@ class UtilsSpidersTestCase(unittest.TestCase): it = iter_spider_classes(tests.test_utils_spider) self.assertEqual(set(it), {MySpider1, MySpider2}) + if __name__ == "__main__": unittest.main() From e3a3ad4aaff6d07252bb4f65be4667e21070aea1 Mon Sep 17 00:00:00 2001 From: marc Date: Sat, 14 Dec 2019 10:34:31 +0100 Subject: [PATCH 4/9] remove reference to old (Python 2.7) environment --- docs/contributing.rst | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/contributing.rst b/docs/contributing.rst index 234c4bcee..eaaf86c29 100644 --- a/docs/contributing.rst +++ b/docs/contributing.rst @@ -229,7 +229,7 @@ You can also specify a comma-separated list of environmets, and use :ref:`tox’ parallel mode ` to run the tests on multiple environments in parallel:: - tox -e py27,py36 -p auto + tox -e py36,py38 -p auto To pass command-line options to :doc:`pytest `, add them after ``--`` in your call to :doc:`tox `. Using ``--`` overrides the From 1aab20e1cec9e2e9aac4ce9efd37b07811b8f7d6 Mon Sep 17 00:00:00 2001 From: marc Date: Sat, 14 Dec 2019 10:37:31 +0100 Subject: [PATCH 5/9] update copyright notice year --- docs/conf.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/conf.py b/docs/conf.py index 914d1d05f..5fdaa4e4c 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -50,7 +50,7 @@ master_doc = 'index' # General information about the project. project = u'Scrapy' -copyright = u'2008–2018, Scrapy developers' +copyright = u'2008–2020, Scrapy developers' # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the From a59bb279d18966e6a47f71d21c690598fc69678e Mon Sep 17 00:00:00 2001 From: marc Date: Sun, 15 Dec 2019 17:33:00 +0100 Subject: [PATCH 6/9] add year through code --- docs/conf.py | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/docs/conf.py b/docs/conf.py index 5fdaa4e4c..ed56c5cd1 100644 --- a/docs/conf.py +++ b/docs/conf.py @@ -12,6 +12,7 @@ # serve to show the default. import sys +from datetime import datetime from os import path # If your extensions are in another directory, add it here. If the directory @@ -49,8 +50,8 @@ source_suffix = '.rst' master_doc = 'index' # General information about the project. -project = u'Scrapy' -copyright = u'2008–2020, Scrapy developers' +project = 'Scrapy' +copyright = '2008–{}, Scrapy developers'.format(datetime.now().year) # The version info for the project you're documenting, acts as replacement for # |version| and |release|, also used in various other places throughout the @@ -194,8 +195,8 @@ htmlhelp_basename = 'Scrapydoc' # Grouping the document tree into LaTeX files. List of tuples # (source start file, target name, title, author, document class [howto/manual]). latex_documents = [ - ('index', 'Scrapy.tex', u'Scrapy Documentation', - u'Scrapy developers', 'manual'), + ('index', 'Scrapy.tex', 'Scrapy Documentation', + 'Scrapy developers', 'manual'), ] # The name of an image file (relative to this directory) to place at the top of From 5980d3bbff67d060a1a1b15372293ced972dbe8b Mon Sep 17 00:00:00 2001 From: Andrey Rakhmatullin Date: Tue, 10 Sep 2019 14:23:11 +0500 Subject: [PATCH 7/9] Add simple tests for pipelines. --- tests/test_pipelines.py | 71 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 71 insertions(+) create mode 100644 tests/test_pipelines.py diff --git a/tests/test_pipelines.py b/tests/test_pipelines.py new file mode 100644 index 000000000..bc53f5427 --- /dev/null +++ b/tests/test_pipelines.py @@ -0,0 +1,71 @@ +from twisted.internet import defer +from twisted.internet.defer import Deferred +from twisted.trial import unittest + +from scrapy import Spider, signals, Request +from scrapy.utils.test import get_crawler + +from tests.mockserver import MockServer + + +class SimplePipeline: + def process_item(self, item, spider): + item['pipeline_passed'] = True + return item + + +class DeferredPipeline: + def cb(self, item): + item['pipeline_passed'] = True + return item + + def process_item(self, item, spider): + d = Deferred() + d.addCallback(self.cb) + d.callback(item) + return d + + +class ItemSpider(Spider): + name = 'itemspider' + + def start_requests(self): + yield Request(self.mockserver.url('/status?n=200')) + + def parse(self, response): + return {'field': 42} + + +class PipelineTestCase(unittest.TestCase): + def setUp(self): + self.mockserver = MockServer() + self.mockserver.__enter__() + + def tearDown(self): + self.mockserver.__exit__(None, None, None) + + def _on_item_scraped(self, item): + self.assertIsInstance(item, dict) + self.assertTrue(item.get('pipeline_passed')) + self.items.append(item) + + def _create_crawler(self, pipeline_class): + settings = { + 'ITEM_PIPELINES': {__name__ + '.' + pipeline_class.__name__: 1}, + } + crawler = get_crawler(ItemSpider, settings) + crawler.signals.connect(self._on_item_scraped, signals.item_scraped) + self.items = [] + return crawler + + @defer.inlineCallbacks + def test_simple_pipeline(self): + crawler = self._create_crawler(SimplePipeline) + yield crawler.crawl(mockserver=self.mockserver) + self.assertEqual(len(self.items), 1) + + @defer.inlineCallbacks + def test_deferred_pipeline(self): + crawler = self._create_crawler(DeferredPipeline) + yield crawler.crawl(mockserver=self.mockserver) + self.assertEqual(len(self.items), 1) From 7d0096da6e37e508280e3af7388122bcdf0e3dcf Mon Sep 17 00:00:00 2001 From: apu <1173372284@qq.com> Date: Tue, 17 Dec 2019 09:47:01 +0800 Subject: [PATCH 8/9] Fix mail attachs tcmime *** (#4229) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit When the file name consists of alphanumeric characters, it is normal to receive the attachment name. However，However, problems will occur if the file name is changed to Chinese. This has nothing to do with the file type --- scrapy/mail.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/scrapy/mail.py b/scrapy/mail.py index 891bb5e09..9655b8114 100644 --- a/scrapy/mail.py +++ b/scrapy/mail.py @@ -73,8 +73,7 @@ class MailSender(object): part = MIMEBase(*mimetype.split('/')) part.set_payload(f.read()) Encoders.encode_base64(part) - part.add_header('Content-Disposition', 'attachment; filename="%s"' \ - % attach_name) + part.add_header('Content-Disposition', 'attachment', filename=attach_name) msg.attach(part) else: msg.set_payload(body) From 63cf5c75c850e48b6f267574e4a8f7ae3293deac Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Marc=20Hern=C3=A1ndez?= Date: Tue, 17 Dec 2019 13:53:15 +0100 Subject: [PATCH 9/9] Fix E502: backslash is redundant between brackets (#4238) --- pytest.ini | 40 +++++------ scrapy/cmdline.py | 4 +- scrapy/commands/fetch.py | 11 ++- scrapy/commands/startproject.py | 4 +- scrapy/contracts/default.py | 4 +- scrapy/core/downloader/handlers/s3.py | 4 +- scrapy/core/downloader/webclient.py | 6 +- scrapy/core/spidermw.py | 6 +- .../downloadermiddlewares/httpcompression.py | 5 +- scrapy/extensions/closespider.py | 6 +- scrapy/linkextractors/__init__.py | 3 +- scrapy/middleware.py | 4 +- scrapy/utils/conf.py | 2 +- tests/test_cmdline/__init__.py | 10 ++- tests/test_downloader_handlers.py | 72 ++++++++++--------- tests/test_downloadermiddleware_retry.py | 6 +- tests/test_engine.py | 4 +- tests/test_http_request.py | 34 +++++---- tests/test_http_response.py | 4 +- tests/test_utils_http.py | 8 +-- 20 files changed, 121 insertions(+), 116 deletions(-) diff --git a/pytest.ini b/pytest.ini index 1b23595c0..f088e10ef 100644 --- a/pytest.ini +++ b/pytest.ini @@ -33,45 +33,45 @@ flake8-ignore = scrapy/commands/check.py E501 scrapy/commands/crawl.py E501 scrapy/commands/edit.py E501 - scrapy/commands/fetch.py E401 E501 E128 E502 E731 + scrapy/commands/fetch.py E401 E501 E128 E731 scrapy/commands/genspider.py E128 E501 E502 scrapy/commands/parse.py E128 E501 E731 E226 scrapy/commands/runspider.py E501 scrapy/commands/settings.py E128 scrapy/commands/shell.py E128 E501 E502 - scrapy/commands/startproject.py E502 E127 E501 E128 + scrapy/commands/startproject.py E127 E501 E128 scrapy/commands/version.py E501 E128 # scrapy/contracts scrapy/contracts/__init__.py E501 W504 - scrapy/contracts/default.py E502 E128 + scrapy/contracts/default.py E128 # scrapy/core scrapy/core/engine.py E501 E128 E127 E306 E502 scrapy/core/scheduler.py E501 scrapy/core/scraper.py E501 E306 E128 W504 - scrapy/core/spidermw.py E501 E731 E502 E126 E226 + scrapy/core/spidermw.py E501 E731 E126 E226 scrapy/core/downloader/__init__.py E501 scrapy/core/downloader/contextfactory.py E501 E128 E126 scrapy/core/downloader/middleware.py E501 E502 scrapy/core/downloader/tls.py E501 E305 E241 - scrapy/core/downloader/webclient.py E731 E501 E502 E128 E126 E226 + scrapy/core/downloader/webclient.py E731 E501 E128 E126 E226 scrapy/core/downloader/handlers/__init__.py E501 scrapy/core/downloader/handlers/ftp.py E501 E305 E128 E127 scrapy/core/downloader/handlers/http10.py E501 scrapy/core/downloader/handlers/http11.py E501 - scrapy/core/downloader/handlers/s3.py E501 E502 E128 E126 + scrapy/core/downloader/handlers/s3.py E501 E128 E126 # scrapy/downloadermiddlewares scrapy/downloadermiddlewares/ajaxcrawl.py E501 E226 scrapy/downloadermiddlewares/decompression.py E501 scrapy/downloadermiddlewares/defaultheaders.py E501 scrapy/downloadermiddlewares/httpcache.py E501 E126 - scrapy/downloadermiddlewares/httpcompression.py E502 E128 + scrapy/downloadermiddlewares/httpcompression.py E501 E128 scrapy/downloadermiddlewares/httpproxy.py E501 scrapy/downloadermiddlewares/redirect.py E501 W504 scrapy/downloadermiddlewares/retry.py E501 E126 scrapy/downloadermiddlewares/robotstxt.py E501 scrapy/downloadermiddlewares/stats.py E501 # scrapy/extensions - scrapy/extensions/closespider.py E501 E502 E128 E123 + scrapy/extensions/closespider.py E501 E128 E123 scrapy/extensions/corestats.py E501 scrapy/extensions/feedexport.py E128 E501 scrapy/extensions/httpcache.py E128 E501 E303 @@ -88,10 +88,10 @@ flake8-ignore = scrapy/http/response/__init__.py E501 E128 W293 W291 scrapy/http/response/text.py E501 W293 E128 E124 # scrapy/linkextractors - scrapy/linkextractors/__init__.py E731 E502 E501 E402 + scrapy/linkextractors/__init__.py E731 E501 E402 scrapy/linkextractors/lxmlhtml.py E501 E731 E226 # scrapy/loader - scrapy/loader/__init__.py E501 E502 E128 + scrapy/loader/__init__.py E501 E128 scrapy/loader/processors.py E501 # scrapy/pipelines scrapy/pipelines/files.py E116 E501 E266 @@ -116,7 +116,7 @@ flake8-ignore = scrapy/spiders/sitemap.py E501 # scrapy/utils scrapy/utils/benchserver.py E501 - scrapy/utils/conf.py E402 E502 E501 + scrapy/utils/conf.py E402 E501 scrapy/utils/console.py E306 E305 scrapy/utils/datatypes.py E501 E226 scrapy/utils/decorators.py E501 @@ -145,7 +145,7 @@ flake8-ignore = # scrapy scrapy/__init__.py E402 E501 scrapy/_monkeypatches.py W293 - scrapy/cmdline.py E502 E501 + scrapy/cmdline.py E501 scrapy/crawler.py E501 scrapy/dupefilters.py E501 E202 scrapy/exceptions.py E501 @@ -155,7 +155,7 @@ flake8-ignore = scrapy/link.py E501 scrapy/logformatter.py E501 W293 scrapy/mail.py E402 E128 E501 E502 - scrapy/middleware.py E502 E128 E501 + scrapy/middleware.py E128 E501 scrapy/pqueues.py E501 scrapy/responsetypes.py E128 E501 E305 scrapy/robotstxt.py E501 @@ -178,7 +178,7 @@ flake8-ignore = tests/test_crawl.py E501 E741 E265 tests/test_crawler.py F841 E306 E501 tests/test_dependencies.py F841 E501 E305 - tests/test_downloader_handlers.py E124 E127 E128 E225 E265 E501 E502 E701 E126 E226 E123 + tests/test_downloader_handlers.py E124 E127 E128 E225 E265 E501 E701 E126 E226 E123 tests/test_downloadermiddleware.py E501 tests/test_downloadermiddleware_ajaxcrawlable.py E501 tests/test_downloadermiddleware_cookies.py E731 E741 E501 E128 E303 E265 E126 @@ -189,18 +189,18 @@ flake8-ignore = tests/test_downloadermiddleware_httpcompression.py E501 E251 E126 E123 tests/test_downloadermiddleware_httpproxy.py E501 E128 tests/test_downloadermiddleware_redirect.py E501 E303 E128 E306 E127 E305 - tests/test_downloadermiddleware_retry.py E501 E128 W293 E251 E502 E303 E126 + tests/test_downloadermiddleware_retry.py E501 E128 W293 E251 E303 E126 tests/test_downloadermiddleware_robotstxt.py E501 tests/test_downloadermiddleware_stats.py E501 tests/test_dupefilters.py E221 E501 E741 W293 W291 E128 E124 - tests/test_engine.py E401 E501 E502 E128 + tests/test_engine.py E401 E501 E128 tests/test_exporters.py E501 E731 E306 E128 E124 tests/test_extension_telnet.py F841 tests/test_feedexport.py E501 F841 E241 tests/test_http_cookies.py E501 tests/test_http_headers.py E501 - tests/test_http_request.py E402 E501 E127 E128 W293 E502 E128 E502 E126 E123 - tests/test_http_response.py E501 E301 E502 E128 E265 + tests/test_http_request.py E402 E501 E127 E128 W293 E128 E126 E123 + tests/test_http_response.py E501 E301 E128 E265 tests/test_item.py E701 E128 F841 E306 tests/test_link.py E501 tests/test_linkextractors.py E501 E128 E124 @@ -230,7 +230,7 @@ flake8-ignore = tests/test_utils_datatypes.py E402 E501 E305 tests/test_utils_defer.py E306 E501 F841 E226 tests/test_utils_deprecate.py F841 E306 E501 - tests/test_utils_http.py E501 E502 E128 W504 + tests/test_utils_http.py E501 E128 W504 tests/test_utils_iterators.py E501 E128 E129 E303 E241 tests/test_utils_log.py E741 E226 tests/test_utils_python.py E501 E303 E731 E701 E305 @@ -243,7 +243,7 @@ flake8-ignore = tests/test_utils_template.py E305 tests/test_utils_url.py E501 E127 E305 E211 E125 E501 E226 E241 E126 E123 tests/test_webclient.py E501 E128 E122 E303 E402 E306 E226 E241 E123 E126 - tests/test_cmdline/__init__.py E502 E501 + tests/test_cmdline/__init__.py E501 tests/test_settings/__init__.py E501 E128 tests/test_spiderloader/__init__.py E128 E501 tests/test_utils_misc/__init__.py E501 diff --git a/scrapy/cmdline.py b/scrapy/cmdline.py index 69e917004..ec78f7c91 100644 --- a/scrapy/cmdline.py +++ b/scrapy/cmdline.py @@ -67,7 +67,7 @@ def _pop_command_name(argv): def _print_header(settings, inproject): if inproject: - print("Scrapy %s - project: %s\n" % (scrapy.__version__, \ + print("Scrapy %s - project: %s\n" % (scrapy.__version__, settings['BOT_NAME'])) else: print("Scrapy %s - no active project\n" % scrapy.__version__) @@ -123,7 +123,7 @@ def execute(argv=None, settings=None): inproject = inside_project() cmds = _get_commands_dict(settings, inproject) cmdname = _pop_command_name(argv) - parser = optparse.OptionParser(formatter=optparse.TitledHelpFormatter(), \ + parser = optparse.OptionParser(formatter=optparse.TitledHelpFormatter(), conflict_handler='resolve') if not cmdname: _print_commands(settings, inproject) diff --git a/scrapy/commands/fetch.py b/scrapy/commands/fetch.py index 8a22ebabe..0e149941d 100644 --- a/scrapy/commands/fetch.py +++ b/scrapy/commands/fetch.py @@ -24,12 +24,11 @@ class Command(ScrapyCommand): def add_options(self, parser): ScrapyCommand.add_options(self, parser) - parser.add_option("--spider", dest="spider", - help="use this spider") - parser.add_option("--headers", dest="headers", action="store_true", \ - help="print response HTTP headers instead of body") - parser.add_option("--no-redirect", dest="no_redirect", action="store_true", \ - default=False, help="do not handle HTTP 3xx status codes and print response as-is") + parser.add_option("--spider", dest="spider", help="use this spider") + parser.add_option("--headers", dest="headers", action="store_true", + help="print response HTTP headers instead of body") + parser.add_option("--no-redirect", dest="no_redirect", action="store_true", + default=False, help="do not handle HTTP 3xx status codes and print response as-is") def _print_headers(self, headers, prefix): for key, values in headers.items(): diff --git a/scrapy/commands/startproject.py b/scrapy/commands/startproject.py index e65131ae8..b123e5c84 100644 --- a/scrapy/commands/startproject.py +++ b/scrapy/commands/startproject.py @@ -43,8 +43,8 @@ class Command(ScrapyCommand): return False if not re.search(r'^[_a-zA-Z]\w*$', project_name): - print('Error: Project names must begin with a letter and contain'\ - ' only\nletters, numbers and underscores') + print('Error: Project names must begin with a letter and contain' + ' only\nletters, numbers and underscores') elif _module_exists(project_name): print('Error: Module %r already exists' % project_name) else: diff --git a/scrapy/contracts/default.py b/scrapy/contracts/default.py index e0d425874..3002fc702 100644 --- a/scrapy/contracts/default.py +++ b/scrapy/contracts/default.py @@ -86,8 +86,8 @@ class ReturnsContract(Contract): else: expected = '%s..%s' % (self.min_bound, self.max_bound) - raise ContractFail("Returned %s %s, expected %s" % \ - (occurrences, self.obj_name, expected)) + raise ContractFail("Returned %s %s, expected %s" % + (occurrences, self.obj_name, expected)) class ScrapesContract(Contract): diff --git a/scrapy/core/downloader/handlers/s3.py b/scrapy/core/downloader/handlers/s3.py index e2a07bdef..d6fbd54ee 100644 --- a/scrapy/core/downloader/handlers/s3.py +++ b/scrapy/core/downloader/handlers/s3.py @@ -32,8 +32,8 @@ def _get_boto_connection(): class S3DownloadHandler(object): - def __init__(self, settings, aws_access_key_id=None, aws_secret_access_key=None, \ - httpdownloadhandler=HTTPDownloadHandler, **kw): + def __init__(self, settings, aws_access_key_id=None, aws_secret_access_key=None, + httpdownloadhandler=HTTPDownloadHandler, **kw): if not aws_access_key_id: aws_access_key_id = settings['AWS_ACCESS_KEY_ID'] diff --git a/scrapy/core/downloader/webclient.py b/scrapy/core/downloader/webclient.py index f368c3bae..fc796e8bb 100644 --- a/scrapy/core/downloader/webclient.py +++ b/scrapy/core/downloader/webclient.py @@ -88,9 +88,9 @@ class ScrapyHTTPPageGetter(HTTPClient): if self.factory.url.startswith(b'https'): self.transport.stopProducing() - self.factory.noPage(\ - defer.TimeoutError("Getting %s took longer than %s seconds." % \ - (self.factory.url, self.factory.timeout))) + self.factory.noPage( + defer.TimeoutError("Getting %s took longer than %s seconds." % + (self.factory.url, self.factory.timeout))) class ScrapyHTTPClientFactory(HTTPClientFactory): diff --git a/scrapy/core/spidermw.py b/scrapy/core/spidermw.py index e2ade8256..097a374bf 100644 --- a/scrapy/core/spidermw.py +++ b/scrapy/core/spidermw.py @@ -44,7 +44,7 @@ class SpiderMiddlewareManager(MiddlewareManager): try: result = method(response=response, spider=spider) if result is not None: - raise _InvalidOutput('Middleware {} must return None or raise an exception, got {}' \ + raise _InvalidOutput('Middleware {} must return None or raise an exception, got {}' .format(fname(method), type(result))) except _InvalidOutput: raise @@ -69,7 +69,7 @@ class SpiderMiddlewareManager(MiddlewareManager): elif result is None: continue else: - raise _InvalidOutput('Middleware {} must return None or an iterable, got {}' \ + raise _InvalidOutput('Middleware {} must return None or an iterable, got {}' .format(fname(method), type(result))) return _failure @@ -103,7 +103,7 @@ class SpiderMiddlewareManager(MiddlewareManager): if _isiterable(result): result = evaluate_iterable(result, method_index) else: - raise _InvalidOutput('Middleware {} must return an iterable, got {}' \ + raise _InvalidOutput('Middleware {} must return an iterable, got {}' .format(fname(method), type(result))) return chain(result, recovered) diff --git a/scrapy/downloadermiddlewares/httpcompression.py b/scrapy/downloadermiddlewares/httpcompression.py index 203dee42d..65b652953 100644 --- a/scrapy/downloadermiddlewares/httpcompression.py +++ b/scrapy/downloadermiddlewares/httpcompression.py @@ -37,8 +37,9 @@ class HttpCompressionMiddleware(object): if content_encoding: encoding = content_encoding.pop() decoded_body = self._decode(response.body, encoding.lower()) - respcls = responsetypes.from_args(headers=response.headers, \ - url=response.url, body=decoded_body) + respcls = responsetypes.from_args( + headers=response.headers, url=response.url, body=decoded_body + ) kwargs = dict(cls=respcls, body=decoded_body) if issubclass(respcls, TextResponse): # force recalculating the encoding until we make sure the diff --git a/scrapy/extensions/closespider.py b/scrapy/extensions/closespider.py index 9ccf356ec..afb2ed049 100644 --- a/scrapy/extensions/closespider.py +++ b/scrapy/extensions/closespider.py @@ -54,9 +54,9 @@ class CloseSpider(object): self.crawler.engine.close_spider(spider, 'closespider_pagecount') def spider_opened(self, spider): - self.task = reactor.callLater(self.close_on['timeout'], \ - self.crawler.engine.close_spider, spider, \ - reason='closespider_timeout') + self.task = reactor.callLater(self.close_on['timeout'], + self.crawler.engine.close_spider, spider, + reason='closespider_timeout') def item_scraped(self, item, spider): self.counter['itemcount'] += 1 diff --git a/scrapy/linkextractors/__init__.py b/scrapy/linkextractors/__init__.py index 4a3e74fbe..bc65f41cc 100644 --- a/scrapy/linkextractors/__init__.py +++ b/scrapy/linkextractors/__init__.py @@ -44,8 +44,7 @@ IGNORED_EXTENSIONS = [ _re_type = type(re.compile("", 0)) _matches = lambda url, regexs: any(r.search(url) for r in regexs) -_is_valid_url = lambda url: url.split('://', 1)[0] in {'http', 'https', \ - 'file', 'ftp'} +_is_valid_url = lambda url: url.split('://', 1)[0] in {'http', 'https', 'file', 'ftp'} class FilteringLinkExtractor(object): diff --git a/scrapy/middleware.py b/scrapy/middleware.py index 1cfd8a782..53fa435bb 100644 --- a/scrapy/middleware.py +++ b/scrapy/middleware.py @@ -65,8 +65,8 @@ class MiddlewareManager(object): return process_chain(self.methods[methodname], obj, *args) def _process_chain_both(self, cb_methodname, eb_methodname, obj, *args): - return process_chain_both(self.methods[cb_methodname], \ - self.methods[eb_methodname], obj, *args) + return process_chain_both(self.methods[cb_methodname], + self.methods[eb_methodname], obj, *args) def open_spider(self, spider): return self._process_parallel('open_spider', spider) diff --git a/scrapy/utils/conf.py b/scrapy/utils/conf.py index 7a15e77ff..23306ca28 100644 --- a/scrapy/utils/conf.py +++ b/scrapy/utils/conf.py @@ -37,7 +37,7 @@ def build_component_list(compdict, custom=None, convert=update_classpath): """Fail if a value in the components dict is not a real number or None.""" for name, value in compdict.items(): if value is not None and not isinstance(value, numbers.Real): - raise ValueError('Invalid value {} for component {}, please provide ' \ + raise ValueError('Invalid value {} for component {}, please provide ' 'a real number or None instead'.format(value, name)) # BEGIN Backward compatibility for old (base, custom) call signature diff --git a/tests/test_cmdline/__init__.py b/tests/test_cmdline/__init__.py index 909ea90e0..da99a6be8 100644 --- a/tests/test_cmdline/__init__.py +++ b/tests/test_cmdline/__init__.py @@ -25,17 +25,15 @@ class CmdlineTest(unittest.TestCase): return comm.decode(encoding) def test_default_settings(self): - self.assertEqual(self._execute('settings', '--get', 'TEST1'), \ - 'default') + self.assertEqual(self._execute('settings', '--get', 'TEST1'), 'default') def test_override_settings_using_set_arg(self): - self.assertEqual(self._execute('settings', '--get', 'TEST1', '-s', 'TEST1=override'), \ - 'override') + self.assertEqual(self._execute('settings', '--get', 'TEST1', '-s', + 'TEST1=override'), 'override') def test_override_settings_using_envvar(self): self.env['SCRAPY_TEST1'] = 'override' - self.assertEqual(self._execute('settings', '--get', 'TEST1'), \ - 'override') + self.assertEqual(self._execute('settings', '--get', 'TEST1'), 'override') def test_profiling(self): path = tempfile.mkdtemp() diff --git a/tests/test_downloader_handlers.py b/tests/test_downloader_handlers.py index 2db2417e8..82d7b18d6 100644 --- a/tests/test_downloader_handlers.py +++ b/tests/test_downloader_handlers.py @@ -800,8 +800,8 @@ class S3TestCase(unittest.TestCase): req = Request('s3://johnsmith/photos/puppy.jpg', headers={'Date': date}) with self._mocked_date(date): httpreq = self.download_request(req, self.spider) - self.assertEqual(httpreq.headers['Authorization'], \ - b'AWS 0PN5J17HBGZHT7JJ3X82:xXjDGYUmKxnwqr5KXNPGldn5LbA=') + self.assertEqual(httpreq.headers['Authorization'], + b'AWS 0PN5J17HBGZHT7JJ3X82:xXjDGYUmKxnwqr5KXNPGldn5LbA=') def test_request_signing2(self): # puts an object into the johnsmith bucket. @@ -813,21 +813,22 @@ class S3TestCase(unittest.TestCase): }) with self._mocked_date(date): httpreq = self.download_request(req, self.spider) - self.assertEqual(httpreq.headers['Authorization'], \ - b'AWS 0PN5J17HBGZHT7JJ3X82:hcicpDDvL9SsO6AkvxqmIWkmOuQ=') + self.assertEqual(httpreq.headers['Authorization'], + b'AWS 0PN5J17HBGZHT7JJ3X82:hcicpDDvL9SsO6AkvxqmIWkmOuQ=') def test_request_signing3(self): # lists the content of the johnsmith bucket. date = 'Tue, 27 Mar 2007 19:42:41 +0000' - req = Request('s3://johnsmith/?prefix=photos&max-keys=50&marker=puppy', \ - method='GET', headers={ - 'User-Agent': 'Mozilla/5.0', - 'Date': date, - }) + req = Request( + 's3://johnsmith/?prefix=photos&max-keys=50&marker=puppy', + method='GET', headers={ + 'User-Agent': 'Mozilla/5.0', + 'Date': date, + }) with self._mocked_date(date): httpreq = self.download_request(req, self.spider) - self.assertEqual(httpreq.headers['Authorization'], \ - b'AWS 0PN5J17HBGZHT7JJ3X82:jsRt/rhG+Vtp88HrYL706QhE4w4=') + self.assertEqual(httpreq.headers['Authorization'], + b'AWS 0PN5J17HBGZHT7JJ3X82:jsRt/rhG+Vtp88HrYL706QhE4w4=') def test_request_signing4(self): # fetches the access control policy sub-resource for the 'johnsmith' bucket. @@ -836,8 +837,8 @@ class S3TestCase(unittest.TestCase): method='GET', headers={'Date': date}) with self._mocked_date(date): httpreq = self.download_request(req, self.spider) - self.assertEqual(httpreq.headers['Authorization'], \ - b'AWS 0PN5J17HBGZHT7JJ3X82:thdUi9VAkzhkniLj96JIrOPGi0g=') + self.assertEqual(httpreq.headers['Authorization'], + b'AWS 0PN5J17HBGZHT7JJ3X82:thdUi9VAkzhkniLj96JIrOPGi0g=') def test_request_signing5(self): try: @@ -850,11 +851,11 @@ class S3TestCase(unittest.TestCase): # deletes an object from the 'johnsmith' bucket using the # path-style and Date alternative. date = 'Tue, 27 Mar 2007 21:20:27 +0000' - req = Request('s3://johnsmith/photos/puppy.jpg', \ - method='DELETE', headers={ - 'Date': date, - 'x-amz-date': 'Tue, 27 Mar 2007 21:20:26 +0000', - }) + req = Request( + 's3://johnsmith/photos/puppy.jpg', method='DELETE', headers={ + 'Date': date, + 'x-amz-date': 'Tue, 27 Mar 2007 21:20:26 +0000', + }) with self._mocked_date(date): httpreq = self.download_request(req, self.spider) # botocore does not override Date with x-amz-date @@ -864,25 +865,26 @@ class S3TestCase(unittest.TestCase): def test_request_signing6(self): # uploads an object to a CNAME style virtual hosted bucket with metadata. date = 'Tue, 27 Mar 2007 21:06:08 +0000' - req = Request('s3://static.johnsmith.net:8080/db-backup.dat.gz', \ - method='PUT', headers={ - 'User-Agent': 'curl/7.15.5', - 'Host': 'static.johnsmith.net:8080', - 'Date': date, - 'x-amz-acl': 'public-read', - 'content-type': 'application/x-download', - 'Content-MD5': '4gJE4saaMU4BqNR0kLY+lw==', - 'X-Amz-Meta-ReviewedBy': 'joe@johnsmith.net,jane@johnsmith.net', - 'X-Amz-Meta-FileChecksum': '0x02661779', - 'X-Amz-Meta-ChecksumAlgorithm': 'crc32', - 'Content-Disposition': 'attachment; filename=database.dat', - 'Content-Encoding': 'gzip', - 'Content-Length': '5913339', - }) + req = Request( + 's3://static.johnsmith.net:8080/db-backup.dat.gz', + method='PUT', headers={ + 'User-Agent': 'curl/7.15.5', + 'Host': 'static.johnsmith.net:8080', + 'Date': date, + 'x-amz-acl': 'public-read', + 'content-type': 'application/x-download', + 'Content-MD5': '4gJE4saaMU4BqNR0kLY+lw==', + 'X-Amz-Meta-ReviewedBy': 'joe@johnsmith.net,jane@johnsmith.net', + 'X-Amz-Meta-FileChecksum': '0x02661779', + 'X-Amz-Meta-ChecksumAlgorithm': 'crc32', + 'Content-Disposition': 'attachment; filename=database.dat', + 'Content-Encoding': 'gzip', + 'Content-Length': '5913339', + }) with self._mocked_date(date): httpreq = self.download_request(req, self.spider) - self.assertEqual(httpreq.headers['Authorization'], \ - b'AWS 0PN5J17HBGZHT7JJ3X82:C0FlOtU8Ylb9KDTpZqYkZPX91iI=') + self.assertEqual(httpreq.headers['Authorization'], + b'AWS 0PN5J17HBGZHT7JJ3X82:C0FlOtU8Ylb9KDTpZqYkZPX91iI=') def test_request_signing7(self): # ensure that spaces are quoted properly before signing diff --git a/tests/test_downloadermiddleware_retry.py b/tests/test_downloadermiddleware_retry.py index 51b79b6c3..e09d66086 100644 --- a/tests/test_downloadermiddleware_retry.py +++ b/tests/test_downloadermiddleware_retry.py @@ -165,12 +165,12 @@ class MaxRetryTimesTest(unittest.TestCase): # SETTINGS: meta(max_retry_times) = 4 meta_max_retry_times = 4 - req = Request(self.invalid_url, meta= \ - {'max_retry_times': meta_max_retry_times, 'dont_retry': True}) + req = Request(self.invalid_url, meta={ + 'max_retry_times': meta_max_retry_times, 'dont_retry': True + }) self._test_retry(req, DNSLookupError('foo'), 0) - def _test_retry(self, req, exception, max_retry_times): for i in range(0, max_retry_times): diff --git a/tests/test_engine.py b/tests/test_engine.py index 537df8d91..a48b63025 100644 --- a/tests/test_engine.py +++ b/tests/test_engine.py @@ -91,8 +91,8 @@ def start_test_site(debug=False): port = reactor.listenTCP(0, server.Site(r), interface="127.0.0.1") if debug: - print("Test server running at http://localhost:%d/ - hit Ctrl-C to finish." \ - % port.getHost().port) + print("Test server running at http://localhost:%d/ - hit Ctrl-C to finish." + % port.getHost().port) return port diff --git a/tests/test_http_request.py b/tests/test_http_request.py index 57e7b457d..e30417b30 100644 --- a/tests/test_http_request.py +++ b/tests/test_http_request.py @@ -622,8 +622,9 @@ class FormRequestTest(RequestTest): """) - req = self.request_class.from_response(response, formdata={'two': '2'}, \ - clickdata={'name': 'clickable2'}) + req = self.request_class.from_response( + response, formdata={'two': '2'}, clickdata={'name': 'clickable2'} + ) fs = _qs(req) self.assertEqual(fs[b'clickable2'], [b'clicked2']) self.assertFalse(b'clickable1' in fs, fs) @@ -671,8 +672,9 @@ class FormRequestTest(RequestTest): """) - req = self.request_class.from_response(response, \ - clickdata={u'name': u'clickable', u'value': u'clicked2'}) + req = self.request_class.from_response( + response, clickdata={u'name': u'clickable', u'value': u'clicked2'} + ) fs = _qs(req) self.assertEqual(fs[b'clickable'], [b'clicked2']) self.assertEqual(fs[b'one'], [b'clicked1']) @@ -686,8 +688,9 @@ class FormRequestTest(RequestTest): """) - req = self.request_class.from_response(response, \ - clickdata={u'name': u'price in \u00a3'}) + req = self.request_class.from_response( + response, clickdata={u'name': u'price in \u00a3'} + ) fs = _qs(req, to_unicode=True) self.assertTrue(fs[u'price in \u00a3']) @@ -700,8 +703,9 @@ class FormRequestTest(RequestTest): """, encoding='latin1') - req = self.request_class.from_response(response, \ - clickdata={u'name': u'price in \u00a5'}) + req = self.request_class.from_response( + response, clickdata={u'name': u'price in \u00a5'} + ) fs = _qs(req, to_unicode=True, encoding='latin1') self.assertTrue(fs[u'price in \u00a5']) @@ -716,8 +720,9 @@ class FormRequestTest(RequestTest): """) - req = self.request_class.from_response(response, formname='form2', \ - clickdata={u'name': u'clickable'}) + req = self.request_class.from_response( + response, formname='form2', clickdata={u'name': u'clickable'} + ) fs = _qs(req) self.assertEqual(fs[b'clickable'], [b'clicked2']) self.assertEqual(fs[b'field2'], [b'value2']) @@ -725,8 +730,9 @@ class FormRequestTest(RequestTest): def test_from_response_override_clickable(self): response = _buildresponse('''
''') - req = self.request_class.from_response(response, \ - formdata={'clickme': 'two'}, clickdata={'name': 'clickme'}) + req = self.request_class.from_response( + response, formdata={'clickme': 'two'}, clickdata={'name': 'clickme'} + ) fs = _qs(req) self.assertEqual(fs[b'clickme'], [b'two']) @@ -853,7 +859,7 @@ class FormRequestTest(RequestTest):
""") - self.assertRaises(IndexError, self.request_class.from_response, \ + self.assertRaises(IndexError, self.request_class.from_response, response, formname="form3", formnumber=2) def test_from_response_formid_exists(self): @@ -907,7 +913,7 @@ class FormRequestTest(RequestTest):
""") - self.assertRaises(IndexError, self.request_class.from_response, \ + self.assertRaises(IndexError, self.request_class.from_response, response, formid="form3", formnumber=2) def test_from_response_select(self): diff --git a/tests/test_http_response.py b/tests/test_http_response.py index 79bb745cc..960ecea3e 100644 --- a/tests/test_http_response.py +++ b/tests/test_http_response.py @@ -316,8 +316,8 @@ class TextResponseTest(BaseResponseTest): assert u'SUFFIX' in r.text, repr(r.text) # Do not destroy html tags due to encoding bugs - r = self.response_class("http://example.com", encoding='utf-8', \ - body=b'\xf0value') + r = self.response_class("http://example.com", encoding='utf-8', + body=b'\xf0value') assert u'value' in r.text, repr(r.text) # FIXME: This test should pass once we stop using BeautifulSoup's UnicodeDammit in TextResponse diff --git a/tests/test_utils_http.py b/tests/test_utils_http.py index f9af4bf87..2fac3da1f 100644 --- a/tests/test_utils_http.py +++ b/tests/test_utils_http.py @@ -13,7 +13,7 @@ class ChunkedTest(unittest.TestCase): chunked_body += "8\r\n" + "sequence\r\n" chunked_body += "0\r\n\r\n" body = decode_chunked_transfer(chunked_body) - self.assertEqual(body, \ - "This is the data in the first chunk\r\n" + - "and this is the second one\r\n" + - "consequence") + self.assertEqual(body, + "This is the data in the first chunk\r\n" + + "and this is the second one\r\n" + + "consequence")