Fast500Parser.py

import re
from glob import glob

nCo = re.compile("(\d+)\s+(.*)")
attributes = ['position', 'name', 'url', 'country', 'rate', 'field']
#all_fields = ['Software', 'Telecommunications/Networking', 'Media/Entertainment', 'Internet', 'Biotech/Pharmaceutical/ Medical Equipment', 'Other', 'Greentech', 'internet', 'Semiconductor, Components and Electronics', 'Computers/Peripherals']
#all_countries = ['Turkey', 'United Kingdom', 'Belgium', 'Germany', 'Netherlands', 'Republic of Ireland', 'Poland', 'France', 'Norway', 'Israel', 'Northern Ireland', 'Sweden', 'Russia', 'Romania', 'Finland', 'Bulgaria', 'Hungary', 'Greece', 'Serbia', 'Slovakia', 'Denmark', 'Austria', 'Czech Republic', 'Portugal', 'Croatia', 'Estonia']

my_fields = dict.fromkeys(['Software', 'Internet'])
my_countries = dict.fromkeys(['United Kingdom'])
my_out_html = open("AAA_Fast500_UK_SW2.html", 'w')

all_companies = []
for file in glob("Fast500_*.txt"):
	f = iter(open(file))
	line = ""
	companies = []
	for line in f:
		m = nCo.match(line.strip())
		if m:
			company = {attributes[0]: m.group(1), attributes[1]: m.group(2)}
			companies.append(company)
		else:
			break

	for attr in iter(attributes[2:]):
		for company in companies:
			company[attr] = line.strip()
			try:
				line = f.next()
			except StopIteration:
				break
	all_companies.extend(companies)

my_companies = [c for c in all_companies if c['field'] in my_fields and c['country'] in my_countries]

def format_str(att):
	default = "%({0})s"
	url = '"%({0})s":http://%({0})s'
	if att == 'url':
		return url.format(att)
	return default.format(att)

txtmpl = []
for company in my_companies:
	txt_row =  "| %s |\n" % " | ".join(map(format_str, attributes)) % company
	txtmpl.append(txt_row)

txt_header = "|_. %s |" % " |_. ".join([a.capitalize() for a in attributes])

import textile
my_out_html.write(textile.textile("%s\n%s" % (txt_header, "".join(txtmpl))))
my_out_html.close()