rivermont · May 3, 2018 17:09
diff --git a/url_regex.py b/url_regex.py
 import re

 # Matches almost all URLs
 # Does not match for foreign characters; beyond the English alphabet and punctuation
 expression = '''((https?|ftp):\/\/)?(www\.)?((-|[0-9]|[A-Z]|[a-z])+\.)+(com|org|edu|gov|uk|net|ca|de|jp|fr|au|us|ru|ch|it|nl|se|no|es|mil|fi|cn|br|be|at|info|pl|dk|cz|cl|hu|nz|il|ie|za|tw|kr|mx|gr|ar|co|ly|gl)(([\/]|[\-\?\+\(\)\=\_\&\%\#\.]|[0-9]|[A-Z]|[a-z])+)*'''

 # Finds all the URLs as the original but also IP addresses.
 # Generates a lot of false positives though, such as '2.0'
 expression1 = '''((https?|ftp):\/\/)?(www\.)?((-|[0-9]|[A-Z]|[a-z])+\.)+((?:[0-9]|[1-9][0-9]|1[0-9][0-9]|2[0-4][0-9]|25[0-5])|com|org|edu|gov|uk|net|ca|de|jp|fr|au|us|ru|ch|it|nl|se|no|es|mil|fi|cn|br|be|at|info|pl|dk|cz|cl|hu|nz|il|ie|za|tw|kr|mx|gr|ar|co|ly|gl)(([\/]|[\-\?\+\(\)\=\_\&\%\#\.]|[0-9]|[A-Z]|[a-z])+)*'''
	import re

	# Matches almost all URLs
	# Does not match for foreign characters; beyond the English alphabet and punctuation
	expression = '''((https?\|ftp):\/\/)?(www\.)?((-\|[0-9]\|[A-Z]\|[a-z])+\.)+(com\|org\|edu\|gov\|uk\|net\|ca\|de\|jp\|fr\|au\|us\|ru\|ch\|it\|nl\|se\|no\|es\|mil\|fi\|cn\|br\|be\|at\|info\|pl\|dk\|cz\|cl\|hu\|nz\|il\|ie\|za\|tw\|kr\|mx\|gr\|ar\|co\|ly\|gl)(([\/]\|[\-\?\+\(\)\=\_\&\%\#\.]\|[0-9]\|[A-Z]\|[a-z])+)*'''

	# Finds all the URLs as the original but also IP addresses.
	# Generates a lot of false positives though, such as '2.0'
	expression1 = '''((https?\|ftp):\/\/)?(www\.)?((-\|[0-9]\|[A-Z]\|[a-z])+\.)+((?:[0-9]\|[1-9][0-9]\|1[0-9][0-9]\|2[0-4][0-9]\|25[0-5])\|com\|org\|edu\|gov\|uk\|net\|ca\|de\|jp\|fr\|au\|us\|ru\|ch\|it\|nl\|se\|no\|es\|mil\|fi\|cn\|br\|be\|at\|info\|pl\|dk\|cz\|cl\|hu\|nz\|il\|ie\|za\|tw\|kr\|mx\|gr\|ar\|co\|ly\|gl)(([\/]\|[\-\?\+\(\)\=\_\&\%\#\.]\|[0-9]\|[A-Z]\|[a-z])+)*'''