A better blip.append_content() for python wave robots.

append_content.py

from BeautifulSoup import BeautifulSoup, NavigableString
from waveapi import element
import re
import htmlentitydefs

IMAGE_PLACEHOLDER = '***{{((IMAGE_ELEMENT))}}***'

def append_content_to_blip(blip, content, type=None):
  if type == 'text/plain':
    # Replace characters that Wave breaks on
    text = content.replace('\t', ' ').replace('\r', '\n')
    blip.append(text)
    return
  
  imgs = []
  
  # originally by Pamela Fox (Google)
  # http://google-wave-resources.googlecode.com/svn/trunk/samples/extensions/robots/python/maildigester/handler.py
  def cleanup(soup):
    for tag in soup:
      if not isinstance(tag, NavigableString):
        if tag.name == 'img':
          imgs.append({'url': tag.get('src'),
                       'width': tag.get('width'),
                       'height': tag.get('height')})
          # replace it with an image element later
          tag.replaceWith(IMAGE_PLACEHOLDER)
        if tag.name == 'a':
          tag['href'] = tag['href'].replace('&', '&')
        cleanup(tag)
  
  html = unescape(content)
  soup = BeautifulSoup(html.strip())
  cleanup(soup)
  html = unicode(soup)
  html = html.replace('\t', ' ')
  # Since its HTML, it should use <br>s instead of line breaks.
  html = html.replace('\r', '').replace('\n', '')
  
  blip.append_markup(html)
  
  # Because append_markup doesn't accept images, we replace img tags in the
  # html with placeholders and then replace them with image elements.
  for img in imgs:
    image = element.Image(url=img['url'],
                        width=img['width'],
                        height=img['height'])
    placeholder = blip.first(IMAGE_PLACEHOLDER)
    # Image elements don't allow links on them.
    # So insert an extra space after images so that a link can still
    # be clicked if it would normally be on the image.
    placeholder.insert_after(' ')
    placeholder.replace(image)


def unescape(text):
  '''
  Replaces HTML entities with unicode characters
  
  by Fredrik Lundh
  http://effbot.org/zone/re-sub.htm#unescape-html
  '''
  def fixup(m):
    text = m.group(0)
    if text[:2] == "&#":
      # character reference
      try:
        if text[:3] == "&#x":
          return unichr(int(text[3:-1], 16))
        else:
          return unichr(int(text[2:-1]))
      except ValueError:
        pass
    else:
      # named entity
      try:
        text = unichr(htmlentitydefs.name2codepoint[text[1:-1]])
      except KeyError:
        pass
    return text # leave as is
  return re.sub("&#?\w+;", fixup, text)