How to extract PDF fields from a filled out form in Python?

Question

I\'m trying to use Python to processes some PDF forms that were filled out and signed using Adobe Acrobat Reader.

I\'ve tried:

• The pdfminer demo: it di

Answer 1

Quick and dirty 2-minute job; just use PDFminer to convert PDF to xml and then grab all of the fields.

from xml.etree import ElementTree
from pprint import pprint
import os

def main():
    print "Calling PDFDUMP.py"
    os.system("dumppdf.py -a FILE.pdf > out.xml")

    # Preprocess the file to eliminate bad XML.
    print "Screening the file"
    o = open("output.xml","w") #open for append
    for line in open("out.xml"):
       line = line.replace("&#", "Invalid_XML") #some bad data in xml for formatting info.
       o.write(line) 
    o.close()

    print "Opening XML output"
    tree = ElementTree.parse('output.xml')
    lastnode = ""
    lastnode2 = ""
    list = {}
    entry = {}

    for node in tree.iter(): # Run through the tree..        
        # Check if New node
        if node.tag == "key" and node.text == "T":
            lastnode = node.tag + node.text
        elif lastnode == "keyT":
            for child in node.iter():
                entry["ID"] = child.text
            lastnode = ""

        if node.tag == "key" and node.text == "V":
            lastnode2 = node.tag + node.text
        elif lastnode2 == "keyV":
            for child in node.iter():
                if child.tag == "string":
                    if entry.has_key("ID"):
                        entry["Value"] = child.text
                        list[entry["ID"]] = entry["Value"]
                        entry = {}
            lastnode2 = ""

    pprint(list)

if __name__ == '__main__':
  main()

It isn't pretty, just a simple proof of concept. I need to implement it for a system I'm working on so I will be cleaning it up, but I thought I would post it in case anyone finds it useful.