Locating and extracting a string from multiple text files in Python

Question

I am just picking up and learning Python, For work i go through a lot of pdfs and so I found a PDFMINER tool that converts a directory to a text file. I then made the below code to tell me whether the pdf file is an approved claim or a denied claim. I dont understand how I can say find me the string that starts with "Tracking Identification Number..." AND is the 18 characters after that and stuff it into an array?

import os
import glob
import csv
def check(filename):
    if 'DELIVERY NOTIFICATION' in open(filename).read():
        isDenied = True
        print ("This claim was Denied")
        print (isDenied)
    elif 'Dear Customer:' in open(filename).read():
        isDenied = False
        print("This claim was Approved")
        print (isDenied)
    else:
        print("I don't know if this is approved or denied")

def iterate():

    path = 'text/'
    for infile in glob.glob(os.path.join(path, '*.txt')):
        print ('current file is:' + infile)
        filename = infile
        check(filename)


iterate()

Any help would be appreciated. this is what the text file looks like

Shipper Number............................577140Pickup Date....................................06/27/17
Number of Parcels........................1Weight.............................................1 LBS
Shipper Invoice Number..............30057010Tracking Identification Number...1Z000000YW00000000
Merchandise..................................1 S NIKE EQUALS EVERYWHERE T BK B
WE HAVE BEEN UNABLE TO PROVIDE SATISFACTORY PROOF OF DELIVERY FOR THE ABOVE
SHIPMENT.  WE APOLOGIZE FOR THE INCONVENIENCE THIS CAUSES.
NPT8AEQ:000A0000LDI 07
----------------Page (1) Break----------------

update: Many helpful answers, here is the route I took, and is working quite nicely if I do say so myself. this is gonna save tons of time!! Here is my the entire code for any future viewers.

import os
import glob

arrayDenied = []

def iterate():
    path = 'text/'
    for infile in glob.glob(os.path.join(path, '*.txt')):
        print ('current file is:' + infile)
        check(infile)

def check(filename):
    with open(filename, 'rt') as file_contents:
        myText = file_contents.read()
        if 'DELIVERY NOTIFICATION' in myText:
            start = myText.index("Tracking Identification Number...") + len("Tracking Identification Number...")
            myNumber = myText[start : start+18]
            print("Denied: " + myNumber)
            arrayDenied.append(myNumber)
        elif 'Dear Customer:' in open(filename).read():
print("This claim was Approved")

startTrackingNum = myText.index("Tracking Identification Number...") + len("Tracking Identification Number...")
myNumber = myText[startTrackingNum : startTrackingNum+18]

startClaimNumberIndex = myText.index("Claim Number ") + len("Claim Number ")
myClaimNumber = myText[startClaimNumberIndex : startClaimNumberIndex+11]

arrayApproved.append(myNumber + " - " + myClaimNumber)
        else:
            print("I don't know if this is approved or denied")   
iterate()
with open('Approved.csv', "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    for val in arrayApproved:
        writer.writerow([val])
with open('Denied.csv', "w") as output:
    writer = csv.writer(output, lineterminator='\n')
    for val in arrayDenied:
        writer.writerow([val])
print(arrayDenied) 
print(arrayApproved)

Update: Added the rest of my finished code, Writes the lists to a CSV file where i go execute some =left()'s and such and boom I have 1000 tracking numbers in a matter of minutes. This is why programming is great.

Answer 1

If your goal is just to find the "Tracking Identification Number..." string and the subsequent 18 characters; you can just find the index of that string, then reach where it ends, and slice from that point until the end of the subsequent 18 characters.

# Read the text file into memory:
with open(filename, 'rt') as txt_file:
    myText = txt_file.read()
    if 'DELIVERY NOTIFICATION' in myText:
        # Find the desired string and get the subsequent 18 characters:
        start = myText.index("Tracking Identification Number...") + len("Tracking Identification Number...")
        myNumber = myText[start : start+18]
        arrayDenied.append(myNumber)

You can also modify the append line into arrayDenied.append(myText + ' ' + myNumber) or things like that.

Answer 2

Regular expressions are the way to go for your task. Here is a way to modify your code to search for the pattern.

import re
pattern = r"(?<=Tracking Identification Number)(?:(\.+))[A-Z-a-z0-9]{18}"

def check(filename):
    file_contents = open(filename, 'r').read()
    if 'DELIVERY NOTIFICATION' in file_contents:
        isDenied = True
        print ("This claim was Denied")
        print (isDenied)
        matches = re.finditer(pattern, test_str)
        for match in matches:
            print("Tracking Number = %s" % match.group().strip("."))
    elif 'Dear Customer:' in file_contents:
        isDenied = False
        print("This claim was Approved")
        print (isDenied)
    else:
        print("I don't know if this is approved or denied")

Explanation:

r"(?<=Tracking Identification Number)(?:(\.+))[A-Z-a-z0-9]{18}"

• (?<=Tracking Identification Number) Looks behind the capturing group to find the string "Tracking Identification Number"
• (?:(\.+)) matches one or more dots (.) (we strip these out after)
• [A-Z-a-z0-9]{18} matches 18 instances of (capital or lowercase) letters or numbers

More on Regex.

Answer 3

I think this solves your issue, just turn it into a function.

import re

string = 'Tracking Identification Number...1Z000000YW00000000'

no_dots = re.sub('\.', '', string) #Removes all dots from the string

matchObj = re.search('^Tracking Identification Number(.*)', no_dots) #Matches anything after the "Tracking Identification Number"

try:
   print (matchObj.group(1))
except:
    print("No match!")

If you want to read the documentation it is here: https://docs.python.org/3/library/re.html#re.search