From f2c800c5c9f88b4b583181e9cf49eb3cd8d538f0 Mon Sep 17 00:00:00 2001 From: Samuel Marchal Date: Mon, 15 Nov 2021 11:14:54 +0100 Subject: [PATCH 1/2] Improve open_in_browser base tag injection (#5319) --- scrapy/utils/response.py | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/scrapy/utils/response.py b/scrapy/utils/response.py index b3ef7b463..8b109dced 100644 --- a/scrapy/utils/response.py +++ b/scrapy/utils/response.py @@ -3,8 +3,9 @@ This module provides some useful functions for working with scrapy.http.Response objects """ import os -import webbrowser +import re import tempfile +import webbrowser from typing import Any, Callable, Iterable, Optional, Tuple, Union from weakref import WeakKeyDictionary @@ -80,8 +81,9 @@ def open_in_browser( body = response.body if isinstance(response, HtmlResponse): if b'' - body = body.replace(b'', to_bytes(repl)) + repl = fr'\1' + body = re.sub(b"", b"", body, flags=re.DOTALL) + body = re.sub(rb"(|\s.*?>))", to_bytes(repl), body) ext = '.html' elif isinstance(response, TextResponse): ext = '.txt' From 75ed765476a2ac66ea8f52e7b29186864f65535c Mon Sep 17 00:00:00 2001 From: Samuel Marchal Date: Mon, 15 Nov 2021 14:31:24 +0100 Subject: [PATCH 2/2] Test coverage for open_in_browser base tag injection (#5319) --- tests/test_utils_response.py | 53 ++++++++++++++++++++++++++++++++++++ 1 file changed, 53 insertions(+) diff --git a/tests/test_utils_response.py b/tests/test_utils_response.py index d6f4c0bb5..0a09f6109 100644 --- a/tests/test_utils_response.py +++ b/tests/test_utils_response.py @@ -83,3 +83,56 @@ class ResponseUtilsTest(unittest.TestCase): self.assertEqual(response_status_message(200), '200 OK') self.assertEqual(response_status_message(404), '404 Not Found') self.assertEqual(response_status_message(573), "573 Unknown Status") + + def test_inject_base_url(self): + url = "http://www.example.com" + + def check_base_url(burl): + path = urlparse(burl).path + if not os.path.exists(path): + path = burl.replace('file://', '') + with open(path, "rb") as f: + bbody = f.read() + self.assertEqual(bbody.count(b''), 1) + return True + + r1 = HtmlResponse(url, body=b""" + + Dummy +

Hello world.

+ """) + r2 = HtmlResponse(url, body=b""" + + Dummy + Hello world. + """) + r3 = HtmlResponse(url, body=b""" + + Dummy + +
Hello header
+

Hello world.

+ + """) + r4 = HtmlResponse(url, body=b""" + + + Dummy +

Hello world.

+ """) + r5 = HtmlResponse(url, body=b""" + + + + Standard head + +

Hello world.

+ """) + + assert open_in_browser(r1, _openfunc=check_base_url), "Inject base url" + assert open_in_browser(r2, _openfunc=check_base_url), "Inject base url with argumented head" + assert open_in_browser(r3, _openfunc=check_base_url), "Inject unique base url with misleading tag" + assert open_in_browser(r4, _openfunc=check_base_url), "Inject unique base url with misleading comment" + assert open_in_browser(r5, _openfunc=check_base_url), "Inject unique base url with conditional comment"