import sys
import re

def parse_vcf(vcf_file):
    ###Open your file
    with open(vcf_file, 'r') as vcf_f:
        for line in vcf_f:
            ###Skip metadata lines
            if line[0] != '#':
                ###Split the line by "tab" to keep info field (for me it's the 8th column, so choose the index = 7, I don't remember if it's always the 8th, change this if needed)
                info_field_line = line.split("\t")[7]
                ###Split the info line by ";"
                info_field_line_array = info_field_line.split(";")
                ###For each line of your VCF, create a dictionnary with this array key : info, value : value of this info
                dict_info={}
                for i in info_field_line_array:
                    ###Just looking for line with "=" character (as key = value)
                    if "=" in i:
                        ###Left from equal sign is key (Gene.refGene, ExonicFunc.refGene...)
                        key = i.split("=")[0]
                        ###Right from equal sign is value (RBL1,synonymous_SNV...)
                        value = i.split("=")[1]
                        ###Put them in a dictionnary
                        dict_info[key]=value
                ###After dictionnary creation, you can have an access to all your features (key), just by their name as follow
                my_GeneRefGene = dict_info['Gene.refGene']
                my_ExonicFuncRefGene = dict_info['ExonicFunc.refGene']
                my_AAChangeRefGene = dict_info['AAChange.refGene']

                print(my_GeneRefGene)
                print(my_ExonicFuncRefGene)
                print(my_AAChangeRefGene)
                ###This is the result for the first line, you can save the data in array to use it later or process line by line as you wish

if __name__ == '__main__':
    vcf=sys.argv[1]
    parse_vcf(vcf)

First:

but it is not working

isn't a good error description.

Second:

Some people, when confronted with a problem, think “I know, I'll use regular expressions.” Now they have two problems.

:)

I would do something like this:

1. split each vcf line by the column delimiter (tab)
2. take the column that contains the information you like to extract and split it by ";"
3. take the result of (2) and split it by "=". Store it in a dictionary. So you can just return result["Gene.refGene"] or any other value you like for the line.

fin swimmer