def clean_comment(self):
self.cleaned_data['comment'] = clean_html(self.cleaned_data['comment'])
self.cleaned_data['comment'] = autolink_html(
self.cleaned_data['comment'])
self.cleaned_data['comment'] = autolink_email(
self.cleaned_data['comment'])
return self.cleaned_data['comment']
def html_clean(body):
# validate HTML content
# Additional options at http://codespeak.net/lxml/lxmlhtml.html#cleaning-up-html
body = clean_html(body)
body = autolink_html(body)
# emails too
body = autolink_email(body)
return body
def html_clean(body):
# validate HTML content
# Additional options at http://codespeak.net/lxml/lxmlhtml.html#cleaning-up-html
body = clean_html(body)
body = autolink_html(body)
# emails too
body = autolink_email(body)
return body
def clean_body(self):
body = self.cleaned_data.get('body', '')
# validate HTML content
# Additional options at http://codespeak.net/lxml/lxmlhtml.html#cleaning-up-html
body = clean_html(body)
body = autolink_html(body)
# emails too
body = autolink_email(body)
return body
def clean_body(self):
body = self.cleaned_data.get('body', '')
# validate HTML content
# Additional options at http://codespeak.net/lxml/lxmlhtml.html#cleaning-up-html
body = clean_html(body)
body = autolink_html(body)
# emails too
body = autolink_email(body)
return body
def clean_description(self):
body = self.cleaned_data.get('description', '')
if body:
# validate HTML content
# Additional options at http://codespeak.net/lxml/lxmlhtml.html#cleaning-up-html
body = clean_html(body)
body = autolink_html(body)
# emails too
body = autolink_email(body)
self.cleaned_data['description'] = body
return body
def clean_comment(self):
self.cleaned_data['comment'] = clean_html(self.cleaned_data['comment'])
self.cleaned_data['comment'] = autolink_html(self.cleaned_data['comment'])
self.cleaned_data['comment'] = autolink_email(self.cleaned_data['comment'])
return self.cleaned_data['comment']
def parse_body(msg):
body = None
if msg.is_multipart():
html = None
txt = None
for part in msg.get_payload():
if part.is_multipart():
for part2 in part.get_payload():
if part2.get_content_type() == 'text/html':
html = part2.get_payload(decode=True)
elif part2.get_content_type() == 'text/plain':
txt = part2.get_payload(decode=True)
if part.get_content_type() == 'text/html':
html = part.get_payload(decode=True)
elif part.get_content_type() == 'text/plain':
txt = part.get_payload(decode=True)
if html:
body = html
elif txt:
body = txt.replace("\n", "<br/>\n")
else:
body = msg.get_payload(decode=True)
body = body.replace("\n", "<br/>\n")
try:
decoder = codecs.getdecoder(msg.get_content_charset())
body = decoder(body)[0]
except:
pass
# strip out reply text
# http://stackoverflow.com/questions/278788/parse-email-content-from-quoted-reply may be a better way
quoting_gmail = r'<div(?:.*)gmail_quote(?:.*)>' # gmail puts their quotes in <div class="gmail_quote">
body = re.split(quoting_gmail, body)[0]
quoting_thunderbird = r'<blockquote(?:.*)cite(?:.*)>' # thunderbird uses <blockquote type="cite">
body = re.split(quoting_thunderbird, body)[0]
quoting_outlook = r'<(?:.*)style(?:.*)border-top: #B5C4DF(?:.*)>' # outlook is just a pain
body = re.split(quoting_outlook, body)[0]
quoting_text = r'<br/>\n*(.*)<br/>\n*(>(.*)<br/>\n*)+[(?:<br/>)\n]*$' # takes any block of end-of-message >-prefix lines, plus the one line preceeding it
body = re.sub(quoting_text, '', body)
if not body:
raise BounceError("I wasn't able to understand the email you sent; it was in a format that is not supported.")
# validate HTML content
# Additional options at http://codespeak.net/lxml/lxmlhtml.html#cleaning-up-html
body = clean_html(body)
body = autolink_html(body)
body = autolink_email(body)
# TODO: strip out in-reference-to text in replies?
return body