Add url expression to pyparsing_common (#249)

1 files changed, 48 insertions, 0 deletions

diff --git a/pyparsing/common.py b/pyparsing/common.py
index c6d91f6..0eb286e 100644
--- a/pyparsing/common.py
+++ b/pyparsing/common.py
@@ -358,6 +358,54 @@ class pyparsing_common:
     downcase_tokens = staticmethod(token_map(lambda t: t.lower()))
     """Parse action to convert tokens to lower case."""
 
+    url = Regex(
+        # https://mathiasbynens.be/demo/url-regex
+        # https://gist.github.com/dperini/729294
+        r"^" +
+        # protocol identifier (optional)
+        # short syntax // still required
+        r"(?:(?:(?P<scheme>https?|ftp):)?\/\/)" +
+        # user:pass BasicAuth (optional)
+        r"(?:(?P<auth>\S+(?::\S*)?)@)?" +
+        r"(?P<host>" +
+        # IP address exclusion
+        # private & local networks
+        r"(?!(?:10|127)(?:\.\d{1,3}){3})" +
+        r"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})" +
+        r"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})" +
+        # IP address dotted notation octets
+        # excludes loopback network 0.0.0.0
+        # excludes reserved space >= 224.0.0.0
+        # excludes network & broadcast addresses
+        # (first & last IP address of each class)
+        r"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])" +
+        r"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}" +
+        r"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))" +
+        r"|" +
+        # host & domain names, may end with dot
+        # can be replaced by a shortest alternative
+        # (?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+
+        r"(?:" +
+        r"(?:" +
+        r"[a-z0-9\u00a1-\uffff]" +
+        r"[a-z0-9\u00a1-\uffff_-]{0,62}" +
+        r")?" +
+        r"[a-z0-9\u00a1-\uffff]\." +
+        r")+" +
+        # TLD identifier name, may end with dot
+        r"(?:[a-z\u00a1-\uffff]{2,}\.?)" +
+        r")" +
+        # port number (optional)
+        r"(?P<port>:\d{2,5})?" +
+        # resource path (optional)
+        r"(?P<path>\/[^?# ]*)?" +
+        # query string (optional)
+        r"(?P<query>\?[^#]*)?" +
+        # fragment (optional)
+        r"(?P<fragment>#\S*)?" +
+        r"$"
+    ).set_name("url")
+
     # pre-PEP8 compatibility names
     convertToInteger = convert_to_integer
     convertToFloat = convert_to_float