A python script to replace relative paths in src/href attributes of HTML with absolute paths. Created with help from http://stackoverflow.com/questions/3836644/c-sharp-convert-relative-to-absolute-links-in-html-string and http://docs.python.org/2/howto/regex.html

relative_to_absolute_path.py

#!/usr/bin/env python
import re
import os

def srcrepl(match):
   "Return the file contents with paths replaced"
   absolutePath = "http://www.example.com/" #update the URL to be prefixed here.
   print "<" + match.group(1) + match.group(2) + "=" + "\"" + absolutePath + match.group(3) + match.group(4) + "\"" + ">"
   return "<" + match.group(1) + match.group(2) + "=" + "\"" + absolutePath + match.group(3) + match.group(4) + "\"" + ">"
   # 
f = open("/path/to/data/file", "r+") #update the file name here.

fileContents = f.read()
p = re.compile(r"<(.*?)(src|href)=\"(?!http)(.*?)\"(.*?)>")
updatedFileContents = p.sub(srcrepl, fileContents)
f.write(updatedFileContents)