Created
February 6, 2010 05:32
-
-
Save timtrueman/296560 to your computer and use it in GitHub Desktop.
Takes a body of text and truncates full urls into domain + tld
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def truncate_urls_to_domain_plus_tld(text): | |
""" | |
Get all the urls | |
Find the domain + tld | |
Find and replace each url found with its domain + tld | |
""" | |
match_urls = re.compile(r'\b(([\w-]+://?|www[.])[^\s()<>]+(?:\([\w\d]+\)|([^%s\s]|/)))') | |
break_down_url = re.compile(r'^((?P<scheme>https?|ftp):\/)?\/?((?P<username>.*?)(:(?P<password>.*?)|)@)?(?P<hostname>[^:\/\s]+)(?P<port>:([^\/]*))?(?P<path>(\/\w+)*\/)(?P<filename>[-\w.]+[^#?\s]*)?(?P<query>\?([^#]*))?(?P<fragment>#(.*))?$') | |
urls = match_urls.findall(text) | |
for url in urls: | |
try: | |
if url[0][-1] == "/": | |
fixed_url = url[0] | |
else: | |
fixed_url = "%s/" % url[0] | |
result = break_down_url.search(fixed_url) | |
componentized_url = result.groupdict() | |
domain_and_tld = componentized_url['hostname'] | |
chunks = domain_and_tld.split(".") | |
if chunks[-2] in ['co', 'ac', 'gov', 'com', 'mil', 'org', 'net', 'edu',]: | |
domain_and_tld = ".".join([chunks[-3], chunks[-2], chunks[-1]]) | |
else: | |
domain_and_tld = ".".join([chunks[-2], chunks[-1]]) | |
print domain_and_tld | |
text = text.replace(url[0], " %s" % domain_and_tld.replace(".", "-----")) # hack to pass on dots in the domain | |
except Exception, e: | |
print "Failed to shorten URL to domain + TLD: %s (so it got removed)" % url[0] | |
text = text.replace(url[0], "") | |
return text |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment