From f2c800c5c9f88b4b583181e9cf49eb3cd8d538f0 Mon Sep 17 00:00:00 2001 From: Samuel Marchal Date: Mon, 15 Nov 2021 11:14:54 +0100 Subject: [PATCH] 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'