convert.py

# Usage:
# 	Make sure all files are in current folder
#	Run `python convert.py`
#
# Output:
#	Output file in `out.csv`
#	Ignored rows in `ignored.csv`

cols = ['Voter`s Slip', 'AC Number', 'Part Number', 'Section Number', 'SerialNo. in Part ',
	'Name in English', ' Name in Hindi', 'Relation FirstName in English', 'Relation FirstName in Hindi',
	'Gender', 'ID Card No.']

import re, os, csv

out, ignored = [cols], []

for source in os.listdir("."):
	if "." in source and source.rsplit(".", 1)[1] in ("html", "xml"):
		with open(source, "r") as f:
			print "Converting " + source
			html = f.read()

			for row in html.split('<tr bgcolor="#D0E0FB">'):
				data = re.findall('\>([^<]+)\<', row)
				if data[0] == "Click to view":
					out.append(data[:len(cols)])
				else:
					ignored.append(data)


# spit out files
with open("out.csv", "w") as f:
	csv.writer(f).writerows(out)

with open("ignored.csv", "w") as f:
	csv.writer(f).writerows(ignored)