Merge pull request mitmproxy#3443 from BoboTiG/fix-invalid-seq-warnings

Fix several DeprecationWarning: invalid escape sequence

examples/complex/sslstrip.py

@@ -38,7 +38,7 @@ def response(flow: http.HTTPFlow) -> None:
     flow.response.content = flow.response.content.replace(b'https://', b'http://')
 
     # strip meta tag upgrade-insecure-requests in response body
-    csp_meta_tag_pattern = b'<meta.*http-equiv=["\']Content-Security-Policy[\'"].*upgrade-insecure-requests.*?>'
+    csp_meta_tag_pattern = br'<meta.*http-equiv=["\']Content-Security-Policy[\'"].*upgrade-insecure-requests.*?>'
     flow.response.content = re.sub(csp_meta_tag_pattern, b'', flow.response.content, flags=re.IGNORECASE)
 
     # strip links in 'Location' header
@@ -52,7 +52,7 @@ def response(flow: http.HTTPFlow) -> None:
     # strip upgrade-insecure-requests in Content-Security-Policy header
     if re.search('upgrade-insecure-requests', flow.response.headers.get('Content-Security-Policy', ''), flags=re.IGNORECASE):
         csp = flow.response.headers['Content-Security-Policy']
-        flow.response.headers['Content-Security-Policy'] = re.sub('upgrade-insecure-requests[;\s]*', '', csp, flags=re.IGNORECASE)
+        flow.response.headers['Content-Security-Policy'] = re.sub(r'upgrade-insecure-requests[;\s]*', '', csp, flags=re.IGNORECASE)
 
     # strip secure flag from 'Set-Cookie' headers
     cookies = flow.response.headers.get_all('Set-Cookie')

examples/complex/xss_scanner.py

@@ -1,4 +1,4 @@
-"""
+r"""
 
  __   __ _____ _____     _____
  \ \ / // ____/ ____|   / ____|

mitmproxy/contentviews/css.py

@@ -16,7 +16,7 @@
 CSS_SPECIAL_AREAS = (
     "'" + strutils.SINGLELINE_CONTENT + strutils.NO_ESCAPE + "'",
     '"' + strutils.SINGLELINE_CONTENT + strutils.NO_ESCAPE + '"',
-    r"/\*" + strutils.MULTILINE_CONTENT + "\*/",
+    r"/\*" + strutils.MULTILINE_CONTENT + r"\*/",
     "//" + strutils.SINGLELINE_CONTENT + "$"
 )
 CSS_SPECIAL_CHARS = "{};:"

mitmproxy/contentviews/javascript.py

@@ -10,9 +10,9 @@
     r"'" + strutils.MULTILINE_CONTENT_LINE_CONTINUATION + strutils.NO_ESCAPE + "'",
     r'"' + strutils.MULTILINE_CONTENT_LINE_CONTINUATION + strutils.NO_ESCAPE + '"',
     r'`' + strutils.MULTILINE_CONTENT + strutils.NO_ESCAPE + '`',
-    r"/\*" + strutils.MULTILINE_CONTENT + "\*/",
+    r"/\*" + strutils.MULTILINE_CONTENT + r"\*/",
     r"//" + strutils.SINGLELINE_CONTENT + "$",
-    r"for\(" + strutils.SINGLELINE_CONTENT + "\)",
+    r"for\(" + strutils.SINGLELINE_CONTENT + r"\)",
 )
 
 

mitmproxy/contentviews/xml_html.py

@@ -18,7 +18,7 @@
 """
 
 # http://www.xml.com/pub/a/2001/07/25/namingparts.html - this is close enough for what we do.
-REGEX_TAG = re.compile("[a-zA-Z0-9._:\-]+(?!=)")
+REGEX_TAG = re.compile(r"[a-zA-Z0-9._:\-]+(?!=)")
 # https://www.w3.org/TR/html5/syntax.html#void-elements
 HTML_VOID_ELEMENTS = {
     "area", "base", "br", "col", "embed", "hr", "img", "input", "keygen", "link", "meta", "param",

mitmproxy/net/check.py

@@ -2,7 +2,7 @@
 import re
 
 # Allow underscore in host name
-_label_valid = re.compile(b"(?!-)[A-Z\d\-_]{1,63}(?<!-)$", re.IGNORECASE)
+_label_valid = re.compile(br"(?!-)[A-Z\d\-_]{1,63}(?<!-)$", re.IGNORECASE)
 
 
 def is_valid_host(host: bytes) -> bool:

mitmproxy/platform/pf.py

@@ -11,7 +11,7 @@ def lookup(address, port, s):
     """
     # We may get an ipv4-mapped ipv6 address here, e.g. ::ffff:127.0.0.1.
     # Those still appear as "127.0.0.1" in the table, so we need to strip the prefix.
-    address = re.sub("^::ffff:(?=\d+.\d+.\d+.\d+$)", "", address)
+    address = re.sub(r"^::ffff:(?=\d+.\d+.\d+.\d+$)", "", address)
     s = s.decode()
     spec = "%s:%s" % (address, port)
     for i in s.split("\n"):

mitmproxy/platform/windows.py

@@ -58,7 +58,7 @@ def _connect(self):
 
     def original_addr(self, csock: socket.socket):
         ip, port = csock.getpeername()[:2]
-        ip = re.sub("^::ffff:(?=\d+.\d+.\d+.\d+$)", "", ip)
+        ip = re.sub(r"^::ffff:(?=\d+.\d+.\d+.\d+$)", "", ip)
         ip = ip.split("%", 1)[0]
         with self.lock:
             try:

mitmproxy/tools/console/help.py

@@ -91,9 +91,9 @@ def filtexp(self):
             )
         )
         examples = [
-            ("google\.com", "Url containing \"google.com"),
-            ("~q ~b test", "Requests where body contains \"test\""),
-            ("!(~q & ~t \"text/html\")", "Anything but requests with a text/html content type."),
+            (r"google\.com", r"Url containing \"google.com"),
+            ("~q ~b test", r"Requests where body contains \"test\""),
+            (r"!(~q & ~t \"text/html\")", "Anything but requests with a text/html content type."),
         ]
         text.extend(
             common.format_keyvals(examples, indent=4)

mitmproxy/tools/web/app.py

@@ -370,7 +370,7 @@ def get(self, flow_id, message):
         original_cd = message.headers.get("Content-Disposition", None)
         filename = None
         if original_cd:
-            filename = re.search('filename=([-\w" .()]+)', original_cd)
+            filename = re.search(r'filename=([-\w" .()]+)', original_cd)
             if filename:
                 filename = filename.group(1)
         if not filename:

mitmproxy/utils/strutils.py

@@ -169,7 +169,7 @@ def split_special_areas(
 
     >>> split_special_areas(
     >>>     "test /* don't modify me */ foo",
-    >>>     [r"/\*[\s\S]*?\*/"])  # (regex matching comments)
+    >>>     [r"/\\*[\\s\\S]*?\\*/"])  # (regex matching comments)
     ["test ", "/* don't modify me */", " foo"]
 
     "".join(split_special_areas(x, ...)) == x always holds true.
@@ -201,7 +201,7 @@ def escape_special_areas(
     >>> x = escape_special_areas(x, "{", ["'" + SINGLELINE_CONTENT + "'"])
     >>> print(x)
     if (true) { console.log('�}'); }
-    >>> x = re.sub(r"\s*{\s*", " {\n    ", x)
+    >>> x = re.sub(r"\\s*{\\s*", " {\n    ", x)
     >>> x = unescape_special_areas(x)
     >>> print(x)
     if (true) {

test/mitmproxy/coretypes/test_basethread.py

@@ -4,4 +4,4 @@
 
 def test_basethread():
     t = basethread.BaseThread('foobar')
-    assert re.match('foobar - age: \d+s', t._threadinfo())
+    assert re.match(r'foobar - age: \d+s', t._threadinfo())

test/mitmproxy/net/http/test_cookies.py

@@ -27,7 +27,7 @@
         [["one", "uno"], ["two", "due"]]
     ],
     [
-        'one="uno"; two="\due"',
+        'one="uno"; two="\\due"',
         [["one", "uno"], ["two", "due"]]
     ],
     [
@@ -70,7 +70,7 @@ def test_read_key():
 def test_read_quoted_string():
     tokens = [
         [('"foo" x', 0), ("foo", 5)],
-        [('"f\oo" x', 0), ("foo", 6)],
+        [('"f\\oo" x', 0), ("foo", 6)],
         [(r'"f\\o" x', 0), (r"f\o", 6)],
         [(r'"f\\" x', 0), (r"f" + '\\', 5)],
         [('"fo\\\"" x', 0), ("fo\"", 6)],

test/mitmproxy/net/test_tcp.py

@@ -102,7 +102,7 @@ def handle(self):
             # We may get an ipv4-mapped ipv6 address here, e.g. ::ffff:127.0.0.1.
             # Those still appear as "127.0.0.1" in the table, so we need to strip the prefix.
             peername = self.connection.getpeername()
-            address = re.sub("^::ffff:(?=\d+.\d+.\d+.\d+$)", "", peername[0])
+            address = re.sub(r"^::ffff:(?=\d+.\d+.\d+.\d+$)", "", peername[0])
             port = peername[1]
 
             self.wfile.write(str((address, port)).encode())