import re

pattern = re.compile("(http|ftp|https)://([\w_-]+(?:(?:\.[\w_-]+)+))([\w.,@?^=%&:/~+#-]*[\w@?^=%&/~+#-])?")

webList = []

##########################
## Change Input File Here
##

INPUT_PATH = "test.html"

##
## Change Output File Here
##

OUTPUT_PATH = "results.txt"

##
## Change Character Limit Here
##

CHAR_LIMIT = 37

##
##########################

# Append Input to Array
for i, line in enumerate(open(INPUT_PATH)):
    for match in re.finditer(pattern, line):
        webList.append(match.group()[0:CHAR_LIMIT])

with open(OUTPUT_PATH, "a") as myfile:
    for i in webList:
        myfile.write(i + '\n')
    myfile.close()