convert plain text to html

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
import re
import cgi

re_string = re.compile(r'(?P<htmlchars>[<&>])|(?P<space>^[ \t]+)|(?P<lineend>\r\n|\r|\n)|(?P<protocal>(^|\s)((http|ftp)://.*?))(\s|$)', re.S|re.M|re.I)
def plaintext2html(text, tabstop=4):
    def do_sub(m):
        c = m.groupdict()
        if c['htmlchars']:
            return cgi.escape(c['htmlchars'])
        if c['lineend']:
            return '<br>'
        elif c['space']:
            t = m.group().replace('\t', '&nbsp;'*tabstop)
            t = t.replace(' ', '&nbsp;')
            return t
        elif c['space'] == '\t':
            return ' '*tabstop;
        else:
            url = m.group('protocal')
            if url.startswith(' '):
                prefix = ' '
                url = url[1:]
            else:
                prefix = ''
            last = m.groups()[-1]
            if last in ['\n', '\r', '\r\n']:
                last = '<br>'
            return '%s<a href="%s">%s</a>%s' % (prefix, url, url, last)
    return re.sub(re_string, do_sub, text)

More like this

  1. Another pygments for ReST by limodou 6 years, 2 months ago
  2. Git Revision Template Tag by sbaechler 6 months, 1 week ago
  3. HTML to text filter by MasonM 4 years, 9 months ago
  4. Format transition middleware by limodou 6 years, 2 months ago
  5. CallTag - Just like include, but can pass parameters to it by limodou 6 years, 2 months ago

Comments

alexdong (on March 2, 2007):

how about adding a re expression to support auto convert http://djangobook.com to [HTML_REMOVED]http://djangobook.com[HTML_REMOVED]

With this, your script could be a minimal textarea filter that's quite handy to lots of websites.

#

alexdong (on March 2, 2007):

sorry that the tags were stripped off from <a href="http://djangobook.com">http://djangobook.com</a>

#

Hugotox (on July 20, 2012):

you have a semicolon at the end of line 17. Seems like a syntax error

#

(Forgotten your password?)