Read a FASTA format and remove all except the ID and the sequence and write a new FASTA file

clean-blast.py

## Tested with python Python 2.7.12

# Instructions
# 
# 1. Put the fasta file in the same directory of this file with the name
# blast.fasta.
# 2. Run the script with the origin file name and the destination file name
# 
# Example: python clean_blast.py file1.fasta my_file.fasta

# Used to read arguments of the command line.
import sys

# Variables definitions. The id and buffer are reserved key words. You cannot used valid variable names
# thus it is necessary added a prefix, in this case an underscore.
_id = ""
_buffer = ""
sequence = ""

# Validation of the command line arguments
if len(sys.argv) < 2 or sys.argv[1] == '':
    print("You need to specific the fasta file to read.")
    print("")
    print("Example: python script_name.py file1.fasta my_file.fasta")
    exit()

if len(sys.argv) < 3 or sys.argv[2] == '':
    print("You need to specific the destination file name.")
    print("")
    print("Example: python script_name.py file1.fasta my_file.fasta")
    exit()
    
print("Start program");

sourcePathName = sys.argv[1]
destinationPathName = sys.argv[2]

print("Reading file")

with open(sourcePathName, "r") as lines:
    for line in lines:
        if line[:1] == ">": # First letter of the line
            if _id != "" and sequence != "": # Save in the buffer when the we have id and sequence with any value
                _buffer = _buffer + _id + sequence

            _id = line.split(" ")[0] + "\n" # Get only the first number of the id
            sequence = ""
        else:
            sequence = sequence + line

print("Writing file")

f = open(destinationPathName, 'w')
f.write(_buffer)
f.close()

print("File wrote in " + destinationPathName)