mailmanToMBox.py

#!/usr/bin/env python3
"""
mailmanToMBox.py:  Inserts line feeds to create mbox format from Mailman Gzip'd
Text archives decompressed
Usage:   ./to-mbox.py  dir
Where dir is a directory containing .txt files pulled from mailman Gzip'd Text and decompressed

Adapted from https://gist.github.com/corydolphin/1728592#gistcomment-2583599
"""
import sys
import os
import tokenize

def main():
    if len(sys.argv) !=2:
        print(__doc__)
        sys.exit()

    rootDir = sys.argv[1]
    numConv = 0
    for root, dirs, files in os.walk(rootDir):
        for fil in files:
            if(fil.find('.txt') > -1):
                inFile = os.path.join(rootDir,fil)
                outFile = inFile.replace('.txt','.mbox')
                print('Converting ',fil,' to mbox format')
                if not makeMBox(inFile,outFile):
                    print((outFile,' already exists, did not overwrite'))
                else:
                    numConv +=1
    print('Converted ' ,str(numConv),'archives to mbox format')
    

def makeMBox(fIn,fOut):
    '''
    from http://lists2.ssc.com/pipermail/linux-list/2006-February/026220.html
    '''
    if not os.path.exists(fIn):
        return False
    if os.path.exists(fOut):
        return False

    out = open(fOut,"w")

    lineNum = 0

    # detect encoding
    readsource =  open(fIn,'rb').__next__
    fInCodec = tokenize.detect_encoding(readsource)[0]

    for line in open(fIn,'rt', encoding=fInCodec, errors="replace"):
        if line.find("From ") == 0:
            if lineNum != 0:
                out.write("\n")
            lineNum +=1
            line = line.replace(" at ", "@")
        out.write(line)
        
            
    out.close()
    return True

# INIT
if __name__ == '__main__':
    main()