use raw strings for regex (fix SyntaxWarning: invalid escape sequence…

… '\d')

convey/config.py

@@ -176,7 +176,7 @@ def integrity_check():
             section_lines = {}  # [section name] = section start line number
             for i, line in enumerate(config_lines):
                 try:
-                    section = re.match("\[([^]]*)\]", line).group(1)
+                    section = re.match(r"\[([^]]*)\]", line).group(1)
                 except AttributeError:
                     pass
                 else:

convey/contacts.py

@@ -28,7 +28,7 @@ def get_domains(mail: str):
         """ mail = [email protected];[email protected] -> [example.com, example2.com] """
         try:
             # return set(re.findall("@([\w.]+)", mail))
-            return set([x[0] for x in re.findall("@(([A-Za-z0-9-]{1,63}\.)+[A-Za-z]{2,6})", mail)])
+            return set([x[0] for x in re.findall(r"@(([A-Za-z0-9-]{1,63}\.)+[A-Za-z]{2,6})", mail)])
         except AttributeError:
             return []
 

convey/convert.py

@@ -8,11 +8,11 @@
 
 logger = logging.getLogger(__name__)
 
-reIpWithPort = re.compile("((\d{1,3}\.){4})(\d+)")
-reAnyIp = re.compile("\"?((\d{1,3}\.){3}(\d{1,3}))")
+reIpWithPort = re.compile(r"((\d{1,3}\.){4})(\d+)")
+reAnyIp = re.compile(r"\"?((\d{1,3}\.){3}(\d{1,3}))")
 reFqdn = re.compile(
-    "(?=^.{4,253}$)(^((?!-)[a-zA-Z0-9-_]{1,63}(?<!-)\.)+[a-zA-Z]{2,63}$)")  # Xtoo long, infinite loop: ^(((([A-Za-z0-9]+){1,63}\.)|(([A-Za-z0-9]+(\-)+[A-Za-z0-9]+){1,63}\.))+){1,255}$
-reUrl = re.compile('[htps]*://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
+    r"(?=^.{4,253}$)(^((?!-)[a-zA-Z0-9-_]{1,63}(?<!-)\.)+[a-zA-Z]{2,63}$)")  # Xtoo long, infinite loop: ^(((([A-Za-z0-9]+){1,63}\.)|(([A-Za-z0-9]+(\-)+[A-Za-z0-9]+){1,63}\.))+){1,255}$
+reUrl = re.compile(r'[htps]*://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+')
 # reBase64 = re.compile('^([A-Za-z0-9+/]{4})*([A-Za-z0-9+/]{4}|[A-Za-z0-9+/]{3}=|[A-Za-z0-9+/]{2}==)$')
 
 
@@ -43,7 +43,7 @@ def port_ip_port(s):
 
 def url_port(s):
     s = s.split(":")[1]
-    return re.match("^(\d*)", s).group(1)
+    return re.match(r"^(\d*)", s).group(1)
 
 
 def url_hostname(url):
@@ -103,7 +103,7 @@ def nmap(val, port=""):
     if Config.get("multiple_nmap_ports", "FIELDS"):
         l = []
         for row in text.split("\n"):
-            l.append(int(re.match("(\d+)", row).group(1)))
+            l.append(int(re.match(r"(\d+)", row).group(1)))
         return l
 
     return text

convey/identifier.py

@@ -83,7 +83,7 @@ def reg_s_method(s):
                     return search.sub("", s)
                 try:
                     # we convert "str{0}" → "\g<0>" (works better than conversion to a mere "\0" that may result to ambiguity
-                    return search.sub(re.sub("{(\d+)}", r"\\g<\1>", replace), s)
+                    return search.sub(re.sub(r"{(\d+)}", r"\\g<\1>", replace), s)
                 except re.error:
                     logger.error(f"RegExp failed: `{replace}` cannot be used to substitute `{s}` with `{search}`")
                     if not Config.error_caught():

convey/infodicts.py

@@ -3,7 +3,7 @@
 
 idds = ('00', '+')
 phone_reg = re.compile(r"(\+|00)?\d[\d\-()]{7,12}\d$")
-phone_dial = re.compile("[+(]?(\d{0,6})")  # any prefix like `+420` or `(089)`, then up to 6 digits (there is no longer prefix)
+phone_dial = re.compile(r"[+(]?(\d{0,6})")  # any prefix like `+420` or `(089)`, then up to 6 digits (there is no longer prefix)
 
 
 def phone_regex_match(val):

convey/types.py

@@ -349,7 +349,7 @@ def get_method(start: Type, target: Type):
                      ["sourceipaddress", "source", "src"], Checker.is_ip, usual_must_match=True)
     destination_ip = Type("destination_ip", TypeGroup.general, "valid destination IP address",
                           ["destinationipaddress", "destination", "dest", "dst"], Checker.is_ip, usual_must_match=True)
-    port = Type("port", TypeGroup.general, "port", ["port", "prt"], lambda x: re.match("\d{1,5}", x),
+    port = Type("port", TypeGroup.general, "port", ["port", "prt"], lambda x: re.match(r"\d{1,5}", x),
                 usual_must_match=True)
     cidr = Type("cidr", TypeGroup.general, "CIDR 127.0.0.1/32", ["cidr"], Checker.check_cidr)
     port_ip = Type("port_ip", TypeGroup.general, "IP in the form 1.2.3.4.port", [], reIpWithPort.match)
@@ -362,7 +362,7 @@ def get_method(start: Type, target: Type):
     url = Type("url", TypeGroup.general, "URL starting with http/https", ["url", "uri", "location"],
                lambda s: reUrl.match(s) and "[.]" not in s)  # input "example[.]com" would be admitted as a valid URL)
     asn = Type("asn", TypeGroup.whois, "Autonomous system number", ["as", "asn", "asnumber"],
-               lambda x: re.search('AS\d+', x) is not None)
+               lambda x: re.search(r'AS\d+', x) is not None)
     base64 = Type("base64", TypeGroup.general, "Text encoded with Base64", ["base64"], Checker.is_base64)
     quoted_printable = Type("quoted_printable", TypeGroup.general, "Text encoded as quotedprintable", [],
                             Checker.is_quopri)

convey/whois.py

@@ -373,7 +373,7 @@ def _load_country_from_addresses(self):
                 return c
         return ""
 
-    reAbuse = re.compile('[a-z0-9._%+-]{1,64}@(?:[a-z0-9-]{1,63}\.){1,125}[a-z]{2,63}')
+    reAbuse = re.compile(r'[a-z0-9._%+-]{1,64}@(?:[a-z0-9-]{1,63}\.){1,125}[a-z]{2,63}')
 
     def get_abusemail(self):
         """ Loads abusemail from last whois response OR from whois json api. """

convey/wrapper.py

@@ -307,7 +307,7 @@ def check_log(self):
         """ Check if the contents is a CSV and not just a log
          ex: "06:25:13.378767 IP 142.234.39.36.51354 > 195.250.148.86.80: Flags [S], seq 1852455482, win 29200, length 0"
          """
-        re_ip_with_port = re.compile("((\d{1,3}\.){4})(\d+)")
+        re_ip_with_port = re.compile(r"((\d{1,3}\.){4})(\d+)")
         re_log_line = re.compile(r"([^\s]*)\sIP\s([^\s]*)\s>\s([^\s:]*)")
         _, sample, _ = Identifier(None).get_sample(self.file)
         if sample and re_log_line.match(sample[0]):