stripxml.py

#!/usr/bin/env python3
# stripxml.py
#
# Usage: stripxml.py
#   or
#   python stripxml.py
# Prints the text from the specified XML file (all tags are filtered out). The input file is unaltered.
#
import sys
from enum import Enum

class State(Enum):
    """
    Define some parser states.
    We're either procesing a TAG or processing raw TEXT.
    """
    TAG = 0
    TEXT = 1
    UNKNOWN = 100

def handleTAG(character, acc):
    """
    Handle the TAG state. 
    If we have a '>' character, then transition to the TEXT state. 
    Otherwise, remain in the TAG state.
    The accumulator is never changed in this state.
    """
    if character == '>':
        return State.TEXT, acc
    else:
        return State.TAG, acc

def handleTEXT(character, acc):
    """
    Handle the TEXT state. 
    If we have a '<' character, then transition to the TAG state. 
    Otherwise, accumulate the current character and remain in the TEXT state.
    """
    if character == '<':
        return State.TAG, acc + "\n"
    else:
        return State.TEXT, acc + c

def handleUnknown(character, acc):
    """
    Handle the UNKNOWN state.
    We should never get here, but accumulate characters just in case.
    """
    return State.UNKNOWN, acc + character

def proc(state, c, acc):
    handler = {State.TAG:handleTAG, State.TEXT:handleTEXT}.get(state, handleUnknown)
    return handler(c, acc)

currentState = State.TAG
acc = ""

file = open(sys.argv[1], 'r', encoding='utf-8')
xml = file.read()
file.close()
for c in xml:
    currentState, acc = proc(currentState, c, acc)

lines = [str.strip(s) for s in acc.splitlines() ]
output = [l for l in lines if len(l) > 0]
for s in output:
    print(s)