Python script to Grep strings from input file and output in csv format

Here we go! So as the comment above said you can just use "startswith" rather then regex to match the lines.

I have used python3 rather then python2 here.

If you run this in a directory using "python3 main.py" it will search the "inputs" subdirectory for all files to parse.

We then build a dictionary for each file with the relevant fields and load their values. We add these dictionaries to a list. At the end we just write the headers to the csv then loop through the rows and write values. You could probably write the rows while reading the files but I find separating parsing and output cleaner mentally.

I changed the ordering of your "for lines in line" to "for line in lines" as you want to loop through each line in the lines.

import os
import csv

def parseFile(fileName):

    # We are using a dictionary to store info for each file
    data = dict()

    # Set all Yes/Nos to NO by default
    data["lpts punt excessive-flow-trap"] = "NO"
    data["dampening"] = "NO"
    data["non-subscriber-interfaces"] = "NO"

    fh = open(fileName, "r")
    lines = fh.readlines()
    for line in lines:

        # We need this so we don't end up with newline characters in our CSV
        line = line.rstrip("\n")

        # We dont need regular expressions here as matching whole line
        # Do YES/NO first
        if line == "lpts punt excessive-flow-trap":
            data["lpts punt excessive-flow-trap"] = "YES"
            continue;

        if line == "dampening":
            data["dampening."] = "YES"
            continue;

        if line == "non-subscriber-interfaces":
            data["non-subscriber-interfaces"] = "YES"
            continue;

        # Now do the rest
        if line.startswith("Hostname"):
            splitted = line.split(' ')
            data["Hostname"] = splitted[1]
            continue;

        if line.startswith("loopback"):
            splitted = line.split(' ')
            data["loopback"] = splitted[1]
            continue;

        if line.startswith("penalty-rate arp"):
            print("ARP")
            splitted = line.split(' ')
            data["penalty-rate arp"] = splitted[2]
            continue;

        if line.startswith("penalty-rate icmp"):
            splitted = line.split(' ')
            data["penalty-rate icmp"] = splitted[2]
            continue;

        if line.startswith("penalty-rate igmp"):
            splitted = line.split(' ')
            data["penalty-rate igmp"] = splitted[2]
            continue;

        if line.startswith("penalty-rate ip"):
            splitted = line.split(' ')
            data["penalty-rate ip"] = splitted[2]
            continue;

        if line.startswith("report-threshold"):
            splitted = line.split(' ')
            data["report-threshold"] = splitted[1]
            continue;

    return data


if __name__ == "__main__":
    inputsDirectory = "inputs"
    path = os.path.abspath(inputsDirectory)
    fileList = ["{}/{}".format(path,x) for x in os.listdir(inputsDirectory)]
    print(fileList)

    # Load Each File and Build Dictionary
    csvRows = []
    for file in fileList:
        newRow = parseFile(file)
        csvRows.append(newRow)

    print(csvRows)

    # Output CSV using dictionaries for each file
    outputFile = "output.csv"
    with open(outputFile, 'w') as csvfile:
        fieldnames = ["Hostname",
                      "loopback",
                      "lpts punt excessive-flow-trap",
                      "penalty-rate arp",
                      "penalty-rate icmp",
                      "penalty-rate igmp",
                      "penalty-rate ip",
                      "dampening",
                      "non-subscriber-interfaces",
                      "report-threshold"]
        writer = csv.DictWriter(csvfile, fieldnames=fieldnames)

        writer.writeheader()
        for row in csvRows:
            writer.writerow(row)