RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Improve open_in_browser base tag injection (#5319)

This commit is contained in:
Samuel Marchal 2021-11-15 11:14:54 +01:00
parent 28eba610e2
commit f2c800c5c9
1 changed files with 5 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
scrapy/utils/response.py
View File

@ -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'<base' not in body:
repl = f'<head><base href="{response.url}">'
body = body.replace(b'<head>', to_bytes(repl))
repl = fr'\1<base href="{response.url}">'
body = re.sub(b"<!--.*?-->", b"", body, flags=re.DOTALL)
body = re.sub(rb"(<head(?:>|\s.*?>))", to_bytes(repl), body)
ext = '.html'
elif isinstance(response, TextResponse):
ext = '.txt'