From 4075e1eadd0a9e83356d18b9ca73090e4a0bc770 Mon Sep 17 00:00:00 2001 From: Eugenio Lacuesta Date: Mon, 23 Nov 2020 15:07:56 -0300 Subject: [PATCH 1/4] Remove deprecated modules (utils.http/markup/multipart) --- pytest.ini | 3 --- scrapy/utils/http.py | 36 ------------------------------------ scrapy/utils/markup.py | 14 -------------- scrapy/utils/multipart.py | 15 --------------- 4 files changed, 68 deletions(-) delete mode 100644 scrapy/utils/http.py delete mode 100644 scrapy/utils/markup.py delete mode 100644 scrapy/utils/multipart.py diff --git a/pytest.ini b/pytest.ini index 1c95f715a..d4deeb57c 100644 --- a/pytest.ini +++ b/pytest.ini @@ -36,8 +36,5 @@ flake8-ignore = scrapy/spiders/__init__.py E402 F401 # Issues pending a review: - scrapy/utils/http.py F403 - scrapy/utils/markup.py F403 - scrapy/utils/multipart.py F403 scrapy/utils/url.py F403 F405 tests/test_loader.py E741 diff --git a/scrapy/utils/http.py b/scrapy/utils/http.py deleted file mode 100644 index ceb3f0509..000000000 --- a/scrapy/utils/http.py +++ /dev/null @@ -1,36 +0,0 @@ -""" -Transitional module for moving to the w3lib library. - -For new code, always import from w3lib.http instead of this module -""" - -import warnings - -from scrapy.exceptions import ScrapyDeprecationWarning -from scrapy.utils.decorators import deprecated -from w3lib.http import * # noqa: F401 - - -warnings.warn("Module `scrapy.utils.http` is deprecated, " - "Please import from `w3lib.http` instead.", - ScrapyDeprecationWarning, stacklevel=2) - - -@deprecated -def decode_chunked_transfer(chunked_body): - """Parsed body received with chunked transfer encoding, and return the - decoded body. - - For more info see: - https://en.wikipedia.org/wiki/Chunked_transfer_encoding - - """ - body, h, t = '', '', chunked_body - while t: - h, t = t.split('\r\n', 1) - if h == '0': - break - size = int(h, 16) - body += t[:size] - t = t[size + 2:] - return body diff --git a/scrapy/utils/markup.py b/scrapy/utils/markup.py deleted file mode 100644 index 9728c542a..000000000 --- a/scrapy/utils/markup.py +++ /dev/null @@ -1,14 +0,0 @@ -""" -Transitional module for moving to the w3lib library. - -For new code, always import from w3lib.html instead of this module -""" -import warnings - -from scrapy.exceptions import ScrapyDeprecationWarning -from w3lib.html import * # noqa: F401 - - -warnings.warn("Module `scrapy.utils.markup` is deprecated. " - "Please import from `w3lib.html` instead.", - ScrapyDeprecationWarning, stacklevel=2) diff --git a/scrapy/utils/multipart.py b/scrapy/utils/multipart.py deleted file mode 100644 index 5dcf791b8..000000000 --- a/scrapy/utils/multipart.py +++ /dev/null @@ -1,15 +0,0 @@ -""" -Transitional module for moving to the w3lib library. - -For new code, always import from w3lib.form instead of this module -""" -import warnings - -from scrapy.exceptions import ScrapyDeprecationWarning -from w3lib.form import * # noqa: F401 - - -warnings.warn("Module `scrapy.utils.multipart` is deprecated. " - "If you're using `encode_multipart` function, please use " - "`urllib3.filepost.encode_multipart_formdata` instead", - ScrapyDeprecationWarning, stacklevel=2) From 51ca4d0138e5c9cf637074f59c839ff9b5839db6 Mon Sep 17 00:00:00 2001 From: Eugenio Lacuesta Date: Mon, 23 Nov 2020 15:47:08 -0300 Subject: [PATCH 2/4] Remove deprecated scrapy.utils.gz.is_gzipped function --- scrapy/utils/gz.py | 15 +----------- tests/test_utils_gz.py | 55 ++++++++++++------------------------------ 2 files changed, 16 insertions(+), 54 deletions(-) diff --git a/scrapy/utils/gz.py b/scrapy/utils/gz.py index 11d433cf5..76156a4b8 100644 --- a/scrapy/utils/gz.py +++ b/scrapy/utils/gz.py @@ -1,7 +1,6 @@ +import struct from gzip import GzipFile from io import BytesIO -import re -import struct from scrapy.utils.decorators import deprecated @@ -42,17 +41,5 @@ def gunzip(data): return b''.join(output_list) -_is_gzipped = re.compile(br'^application/(x-)?gzip\b', re.I).search -_is_octetstream = re.compile(br'^(application|binary)/octet-stream\b', re.I).search - - -@deprecated -def is_gzipped(response): - """Return True if the response is gzipped, or False otherwise""" - ctype = response.headers.get('Content-Type', b'') - cenc = response.headers.get('Content-Encoding', b'').lower() - return _is_gzipped(ctype) or _is_octetstream(ctype) and cenc in (b'gzip', b'x-gzip') - - def gzip_magic_number(response): return response.body[:3] == b'\x1f\x8b\x08' diff --git a/tests/test_utils_gz.py b/tests/test_utils_gz.py index 7148185f4..4943731cb 100644 --- a/tests/test_utils_gz.py +++ b/tests/test_utils_gz.py @@ -3,10 +3,11 @@ from os.path import join from w3lib.encoding import html_to_unicode -from scrapy.utils.gz import gunzip, is_gzipped -from scrapy.http import Response, Headers +from scrapy.utils.gz import gunzip, gzip_magic_number +from scrapy.http import Response from tests import tests_datadir + SAMPLEDIR = join(tests_datadir, 'compressed') @@ -14,8 +15,12 @@ class GunzipTest(unittest.TestCase): def test_gunzip_basic(self): with open(join(SAMPLEDIR, 'feed-sample1.xml.gz'), 'rb') as f: - text = gunzip(f.read()) - self.assertEqual(len(text), 9950) + r1 = Response("http://www.example.com", body=f.read()) + self.assertTrue(gzip_magic_number(r1)) + + r2 = Response("http://www.example.com", body=gunzip(r1.body)) + self.assertFalse(gzip_magic_number(r2)) + self.assertEqual(len(r2.body), 9950) def test_gunzip_truncated(self): with open(join(SAMPLEDIR, 'truncated-crc-error.gz'), 'rb') as f: @@ -28,46 +33,16 @@ class GunzipTest(unittest.TestCase): def test_gunzip_truncated_short(self): with open(join(SAMPLEDIR, 'truncated-crc-error-short.gz'), 'rb') as f: - text = gunzip(f.read()) - assert text.endswith(b'') + r1 = Response("http://www.example.com", body=f.read()) + self.assertTrue(gzip_magic_number(r1)) - def test_is_x_gzipped_right(self): - hdrs = Headers({"Content-Type": "application/x-gzip"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) - - def test_is_gzipped_right(self): - hdrs = Headers({"Content-Type": "application/gzip"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) - - def test_is_gzipped_not_quite(self): - hdrs = Headers({"Content-Type": "application/gzippppp"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertFalse(is_gzipped(r1)) - - def test_is_gzipped_case_insensitive(self): - hdrs = Headers({"Content-Type": "Application/X-Gzip"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) - - hdrs = Headers({"Content-Type": "application/X-GZIP ; charset=utf-8"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) + r2 = Response("http://www.example.com", body=gunzip(r1.body)) + assert r2.body.endswith(b'') + self.assertFalse(gzip_magic_number(r2)) def test_is_gzipped_empty(self): r1 = Response("http://www.example.com") - self.assertFalse(is_gzipped(r1)) - - def test_is_gzipped_wrong(self): - hdrs = Headers({"Content-Type": "application/javascript"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertFalse(is_gzipped(r1)) - - def test_is_gzipped_with_charset(self): - hdrs = Headers({"Content-Type": "application/x-gzip;charset=utf-8"}) - r1 = Response("http://www.example.com", headers=hdrs) - self.assertTrue(is_gzipped(r1)) + self.assertFalse(gzip_magic_number(r1)) def test_gunzip_illegal_eof(self): with open(join(SAMPLEDIR, 'unexpected-eof.gz'), 'rb') as f: From 462014bc5738a5ed18ec4c15a91384eb17e57096 Mon Sep 17 00:00:00 2001 From: Eugenio Lacuesta Date: Mon, 23 Nov 2020 15:51:59 -0300 Subject: [PATCH 3/4] Scheduler: remove support for deprecated queuelib.PriorityQueue --- scrapy/core/scheduler.py | 12 ------------ 1 file changed, 12 deletions(-) diff --git a/scrapy/core/scheduler.py b/scrapy/core/scheduler.py index a18c26b17..9ce823dbc 100644 --- a/scrapy/core/scheduler.py +++ b/scrapy/core/scheduler.py @@ -1,14 +1,10 @@ import os import json import logging -import warnings from os.path import join, exists -from queuelib import PriorityQueue - from scrapy.utils.misc import load_object, create_instance from scrapy.utils.job import job_dir -from scrapy.utils.deprecate import ScrapyDeprecationWarning logger = logging.getLogger(__name__) @@ -56,14 +52,6 @@ class Scheduler: dupefilter_cls = load_object(settings['DUPEFILTER_CLASS']) dupefilter = create_instance(dupefilter_cls, settings, crawler) pqclass = load_object(settings['SCHEDULER_PRIORITY_QUEUE']) - if pqclass is PriorityQueue: - warnings.warn("SCHEDULER_PRIORITY_QUEUE='queuelib.PriorityQueue'" - " is no longer supported because of API changes; " - "please use 'scrapy.pqueues.ScrapyPriorityQueue'", - ScrapyDeprecationWarning) - from scrapy.pqueues import ScrapyPriorityQueue - pqclass = ScrapyPriorityQueue - dqclass = load_object(settings['SCHEDULER_DISK_QUEUE']) mqclass = load_object(settings['SCHEDULER_MEMORY_QUEUE']) logunser = settings.getbool('SCHEDULER_DEBUG') From 18b05af87783d71f9c8f9f1ebe027083037e6f86 Mon Sep 17 00:00:00 2001 From: Eugenio Lacuesta Date: Mon, 23 Nov 2020 16:18:58 -0300 Subject: [PATCH 4/4] Remove tests/test_utils_http.py --- tests/test_utils_http.py | 19 ------------------- 1 file changed, 19 deletions(-) delete mode 100644 tests/test_utils_http.py diff --git a/tests/test_utils_http.py b/tests/test_utils_http.py deleted file mode 100644 index 363b015a8..000000000 --- a/tests/test_utils_http.py +++ /dev/null @@ -1,19 +0,0 @@ -import unittest - -from scrapy.utils.http import decode_chunked_transfer - - -class ChunkedTest(unittest.TestCase): - - def test_decode_chunked_transfer(self): - """Example taken from: http://en.wikipedia.org/wiki/Chunked_transfer_encoding""" - chunked_body = "25\r\n" + "This is the data in the first chunk\r\n\r\n" - chunked_body += "1C\r\n" + "and this is the second one\r\n\r\n" - chunked_body += "3\r\n" + "con\r\n" - 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\nand this is the second one\r\nconsequence" - )