Super Hacky Job Wage Parser

# encoding: utf-8
import re
import csv
import sys

out_file = csv.writer(sys.stdout)
c = csv.reader(sys.stdin, delimiter=',')

def per_hour_to_annum(value):
    value = value*40*52
    return value


for r in c:
    if len(r) > 5:
        # initial cleaning
        orig_col = r[5]
        col = r[5].lower()
        col = re.sub(r'([\d])k', r'\1,000', col)
        if re.search('£', col):
            col = re.search('(£.*$)', col).group(0)
            # print col
            # pass
        col = re.sub('£', '', col)
        # Massive if statement trying to clean everything
        if re.search('per hour', col):
            # col = re.sub(r' ', '', col)

            col = re.sub(r'([a-zA-Z]+)', '', col)
            col = re.sub(r'^-', '', col)
            col = re.sub(r'%', '', col)
            x_col = col
            col = re.split('-', col)[0]
            col = col.strip()
            col = re.sub('\+', '', col)
            if re.match('[0-9]', col):
                col = re.split(' ', col)[0]
                col = re.split('/', col)[0]
                # print col
            
            
            try:
                col = per_hour_to_annum(float(col))
            except Exception, e:
                pass
        elif re.search('per annum|pa |p\/a', col):
            if re.match('^[0-9]', col):
                col = re.split(' ', col)[0]
                col = re.split('Â|-', col)[0]
                col = re.sub(r'[^0-9\.]', '', col)
                
                # If there is still anything with 2 chars, assume it should have more!
                if len(col) <= 2:
                    col = "%s000" % col
                
                # sometimes people use dots in the wrong way:
                if re.search(r'^([0-9]{0,2})\.', col):
                    col = re.sub(r'^([0-9]{0,2}).', r'\1', col)
                
                col = re.sub('[a-z-A-Z]', '', col)
        else:
            col = re.split(' ', col)[0]
            col = re.sub('[a-zA-Z]', '', col)
            col = re.sub(',', '', col)
            col = re.sub('[^0-9\.]', '', col)

        if len(str(col)) > 0:
            try:
                col = float(col)
                if col:
                    r[5] = col
                r.insert(6, orig_col)
                out_file.writerow(r)
                
            except:
                print repr(col)