adding new pdf extract capability

scripts/pyaccuwage-pdfparse

@@ -0,0 +1,47 @@
+#!/usr/bin/python
+from pyaccuwage.parser import RecordBuilder
+from pyaccuwage.pdfexport import PDFRecordFinder
+import argparse
+import sys
+
+parser = argparse.ArgumentParser(description="Parse and convert contents of IRS files into pyaccuwage e-file classes.")
+parser.add_argument("-f", "--full", help="Generate full python file, including related imports.", action="store_true")
+parser.add_argument("-i", "--input", metavar="file", type=argparse.FileType('r'), help="Source PDF file, ie: p1220.pdf")
+
+
+args = parser.parse_args()
+
+"""
+lines = []
+for x in sys.stdin.readlines():
+    lines.append(x)
+
+pdp = PastedDefParser()
+tokens = pdp.load("".join(lines))
+"""
+def generate_imports():
+    return "\n".join([
+        "from pyaccuwage import model",
+        "from pyaccuwage.fields import *",
+        "",
+        "",
+        ])
+
+def generate_class_begin(name):
+    return "class %s(mode.Model):\n" % name
+
+if args.full:
+    sys.stdout.write(generate_imports())
+
+if args.classname:
+    classname = args.classname
+else:
+    classname = "GeneratedRecord"
+
+sys.stdout.write(generate_class_begin(classname))
+
+
+for x in tokens:
+    sys.stdout.write('\t' + x + '\n')
+
+