def handle_feed(self, resource):
# TODO - model attribute for item count?
# TODO - model attributes for other hard-coded values?
types = ",".join([ "'%s'" % t for t in resource.resource_types ])
children = model.Resource.gql("WHERE class IN (" + types + ") ORDER BY publication_date DESC").fetch(10)
last_modified = resource.modification_date
for c in children:
if c.modification_date > last_modified:
last_modified = c.modification_date
feed = rss.RssFeed(
title = resource.title,
description = resource.body,
link = self.request.host_url + "/",
copyright = "Copyright 2009 Jason DeFontes",
email = "[email protected] (Jason DeFontes)",
pub_date = last_modified,
rss_link = self.request.host_url + resource.path
)
for c in children:
body = self.render_template(c.class_name().lower() + "_post.html", { "child": c })
# fix links to local URLs in body
soup = BeautifulSoup(body, fromEncoding='utf-8')
for link in soup.findAll('a', href=re.compile('^\/.*')):
link['href'] = self.request.host_url + link['href']
for img in soup.findAll('img', src=re.compile('^\/.*')):
img['src'] = self.request.host_url + img['src']
feed.add_item(
title = c.title,
description = unicode(soup),
link = self.request.host_url + c.path,
author = "[email protected] (Jason DeFontes)",
pub_date = c.publication_date,
guid = c.uuid
)
return Representation("application/rss+xml", feed.to_xml(), True)
def strip_tags(text, valid_tags={}):
"""strip tags, remove invalid tag attrs.
example::
>>> strip_tags('this <a href="">xxx</a>')
u'this xxx'
>>> strip_tags('this <a href="">xxx</a>',{'a':'href'})
u'this <a href="">xxx</a>'
"""
from app.BeautifulSoup import BeautifulSoup, Comment
soup = BeautifulSoup(text)
for comment in soup.findAll(text=lambda text: isinstance(text, Comment)):
comment.extract()
for tag in soup.findAll(True):
if tag.name in valid_tags:
valid_attrs = valid_tags[tag.name]
tag.attrs = [(attr, val.replace('javascript:', ''))
for attr, val in tag.attrs if attr in valid_attrs]
else:
tag.hidden = True
return soup.renderContents().decode('utf8')