wordpressExportPingbackGraph.py

import string
from xml.dom import minidom
#based on http://code.activestate.com/recipes/551792-convert-wordpress-export-file-to-multiple-html-fil/

infile='wpexport.xml'
# NB the WP export file seemed incomplete - I had to add the atom namespace
# xmlns:atom="http://www.w3.org/2005/Atom/"

dotfile='internalstructure.dot'
csvfile='internalstructure.csv'

dom = minidom.parse(infile)

f = open(dotfile, 'w')
f2 = open(csvfile,'w')

blog=[]

f.write('digraph blogstruct{')

for node in dom.getElementsByTagName('item'):
	post = dict()
	post["title"] = node.getElementsByTagName('title')[0].firstChild.data
	post["date"] = node.getElementsByTagName('pubDate')[0].firstChild.data
	post["link"] = node.getElementsByTagName('link')[0].firstChild.data
	post['comments'] =[]
	
	for comment in node.getElementsByTagName('wp:comment'):
		commentInfo = dict()
		if comment.getElementsByTagName('wp:comment_type')[0]:
			c= comment.getElementsByTagName('wp:comment_type')[0]
			if c.firstChild:
				commentInfo['type']= comment.getElementsByTagName('wp:comment_type')[0].firstChild.data
				commentInfo['url']= comment.getElementsByTagName('wp:comment_author_url')[0].firstChild.data
				commentInfo['date']= comment.getElementsByTagName('wp:comment_date')[0].firstChild.data
				if commentInfo['type']=='pingback' and commentInfo['url'].find('http://blog.ouseful.info')!=-1:
					cID=commentInfo['url'].strip('/')
					cID=cID.rpartition('/')
					rID=post["link"].strip('/')
					rID=rID.rpartition('/')
					f.write('"'+cID[2]+'"->"'+rID[2]+'"\n')
					f2.write('"'+cID[2]+'","'+rID[2]+'"\n')
					#post['comments'].append(comments)
	#blog.append(post)

f.write('}')
f.close()
f2.close()