ググソリューション:
#---------- find_urls.py----------#
# Functions to identify and extract URLs and email addresses
import re
def fix_urls(text):
pat_url = re.compile( r'''
(?x)(# verbose identify URLs within text
(http|ftp|gopher) # make sure we find a resource type
:// # ...needs to be followed by colon-slash-slash
(\w+[:.]?){2,} # at least two domain groups, e.g. (gnosis.)(cx)
(/?| # could be just the domain name (maybe w/ slash)
[^ \n\r"]+ # or stuff then space, newline, tab, quote
[\w/]) # resource name ends in alphanumeric or slash
(?=[\s\.,>)'"\]]) # assert: followed by white or clause ending
) # end of match group
''')
pat_email = re.compile(r'''
(?xm) # verbose identify URLs in text (and multiline)
(?=^.{11} # Mail header matcher
(?<!Message-ID:| # rule out Message-ID's as best possible
In-Reply-To)) # ...and also In-Reply-To
(.*?)(# must grab to email to allow prior lookbehind
([A-Za-z0-9-]+\.)? # maybe an initial part: [email protected]
[A-Za-z0-9-]+ # definitely some local user: [email protected]
@ # ...needs an at sign in the middle
(\w+\.?){2,} # at least two domain groups, e.g. (gnosis.)(cx)
(?=[\s\.,>)'"\]]) # assert: followed by white or clause ending
) # end of match group
''')
for url in re.findall(pat_url, text):
text = text.replace(url[0], '<a href="%(url)s">%(url)s</a>' % {"url" : url[0]})
for email in re.findall(pat_email, text):
text = text.replace(email[1], '<a href="mailto:%(email)s">%(email)s</a>' % {"email" : email[1]})
return text
if __name__ == '__main__':
print fix_urls("test http://google.com asdasdasd some more text")
EDIT:ニーズ
本当に "http"で始まるURLに頼ることはできますか?しばしば、私は "example.com/foo"と書かれたURLを参照しています。あなたもそれにマッチする必要がありますか? –
これは本当に良い点です。私は確かにgoogle.comとhttp://google.comを検出したいと思っています。私は提出された巨大なgoogleの回答をもう一度見ていきます。 。 –