clean blogger(blogspot) posts.

blogger_post_tagcleaner.py

#!/usr/bin/env python

import sys, logging
sys.path.insert(0,"./gdata-2.0.11.final.zip/src")

from gdata import service
import gdata
import atom

import simplejson

accountinfo = simplejson.loads( open("auth.json").read() )

blogger_service = service.GDataService(*accountinfo)
blogger_service.source = 'exampleCo-exampleApp-1.0'
blogger_service.service = 'blogger'
blogger_service.account_type = 'GOOGLE'
blogger_service.server = 'www.blogger.com'
blogger_service.ProgrammaticLogin()

def get_blogs(blogger_service):
  query = service.Query()
  query.feed = '/feeds/default/blogs'
  feed = blogger_service.Get(query.ToUri())

  blogs = []
  print feed.title.text
  for entry in feed.entry:
    blog_id = entry.GetSelfLink().href.split("/")[-1]
#    print "\t" + entry.title.text + " " + blog_id
    blogs.append( ( blog_id, entry.title.text ) )
  return blogs

###PrintUserBlogTitles(blogger_service)
blogs = get_blogs(blogger_service)

def get_posts(blogger_service, blog_id):
  feed = blogger_service.GetFeed('/feeds/' + blog_id + '/posts/default')

  ret = []
#  print feed.title.text
  for entry in feed.entry:
   ### logging.warn( (entry.__dict__, dir(entry),  ) )
   #### break
    ret.append( ( entry.title.text, entry.content.text, entry.GetEditLink(), entry ) )
  return ret

def UpdatePostTitle(blogger_service, entry_to_update, new_title='The REAL answer'):
  entry_to_update.title = atom.Title('xhtml', new_title)
  return blogger_service.Put(entry_to_update, entry_to_update.GetEditLink().href)

for blog_id,title in blogs:
    posts = get_posts(blogger_service,blog_id)
 ###   logging.warn( posts[0] )
#    PrintAllPosts(blogger_service,blog_id)
    for art in posts:
        ot = unicode(art[1],"utf-8")
        import re
        nt = ot
        nt = re.sub( r'</?(span|div)[^>]*>', "", nt )
        nt = re.sub( r'</blockquote>((<br />)?)<blockquote>', r'<br/>', nt )
    ##    nt = re.sub( r'\n{2,}',r"\n", nt )
        nt = re.sub( r'(<br />){3,}',r"<br /><br />", nt )
        nt = re.sub( r'\s+<br />',r"<br />", nt )
        nt = re.sub( r'<br />\s+<br />',r"<br /><br />", nt )
        if nt != ot:
       ###     logging.warn( (ot,nt) )
            ob = art[-1]
            logging.warn( str(ob.title)+":updated..")
            ob.content = atom.Content(content_type='html', text=nt)
            blogger_service.Put(ob, ob.GetEditLink().href)
         ###   logging.warn( art[0] )
         ###   break

gdata.sh

wget https://github.com/kamawanu/gdata-python-client/archive/v2.zip