Python PDF Parser example code.

moneydj_pdf_parser_example.py

import os, csv
from urllib2 import Request, urlopen
from StringIO import StringIO
from PyPDF2 import PdfFileReader

# Get the moneydj urls into a list.
with open('/money_url_list.csv', 'rb') as money_url_list:
    reader = csv.reader(money_url_list, delimiter = ',')
    moneydj_list = list(reader)
    
# Open PDF Reader.
pdfFile = PdfFileReader(StringIO(urlopen(Request(moneydj_list[1][2])).read()))

# Print content extracted.
page = pdfFile.getPage(pageNumber = 1)
print page.extractText().encode("ascii", "ignore")