A simple (and probably naive) script to extract attachments from .eml files for those of us who don't use software email clients.

extract_attachments.py

#!/usr/bin/env python
"""
Extract all attachments from MS Outlook '.eml' file EML_FILE into
directory OUTPUT_DIR. If OUTPUT_DIR does not exist, it will be
created.

Usage: extract_attachments.py EML_FILE OUTPUT_DIR
"""
from __future__ import print_function
import sys
import os
import os.path
from collections import defaultdict
from email.parser import Parser

def parse_message(filename):
    with open(filename) as f:
        return Parser().parse(f)

def find_attachments(message):
    """
    Return a tuple of parsed content-disposition dict, message object
    for each attachment found.
    """
    found = []
    for part in message.walk():
        if 'content-disposition' not in part:
            continue
        cdisp = part['content-disposition'].split(';')
        cdisp = [x.strip() for x in cdisp]
        if cdisp[0].lower() != 'attachment':
            continue
        parsed = {}
        for kv in cdisp[1:]:
            key, _, val = kv.partition('=')
            if val.startswith('"'):
                val = val.strip('"')
            elif val.startswith("'"):
                val = val.strip("'")
            parsed[key] = val
        found.append((parsed, part))
    return found

def run(eml_filename, output_dir):
    msg = parse_message(eml_filename)
    attachments = find_attachments(msg)
    print("Found {0} attachments...".format(len(attachments)))
    if not os.path.isdir(output_dir):
        os.mkdir(output_dir)
    for cdisp, part in attachments:
        cdisp_filename = os.path.normpath(cdisp['filename'])
        # prevent malicious crap
        if os.path.isabs(cdisp_filename):
            cdisp_filename = os.path.basename(cdisp_filename)
        towrite = os.path.join(output_dir, cdisp_filename)
        print("Writing", towrite)
        with open(towrite, 'wb') as fp:
            data = part.get_payload(decode=True)
            fp.write(data)


def main():
    args = sys.argv[1:]
    if len(args) != 2:
        print('Usage: extract_attachments.py EML_FILE OUTPUT_DIR')
        sys.exit(1)
    filename, outdir = args
    run(filename, outdir)


if __name__ == '__main__':
    main()

Thanks, works great. Quick diff for Python3:

diff extracter.py extracter-orig.py
45c45
<     print(  "Found {0} attachments...".format(len(attachments)) )
---
>     print "Found {0} attachments...".format(len(attachments))
54c54
<         print(  "Writing " + towrite )
---
>         print "Writing " + towrite
63c63
<         print(  'Usage: extract_attachments.py EML_FILE OUTPUT_DIR' )
---
>         print 'Usage: extract_attachments.py EML_FILE OUTPUT_DIR'

Great stuff

Thanks!

ValueError: too many values to unpack
Any idea how to fix it?

Traceback (most recent call last):
File "extract_attachments.py", line 71, in
main()
File "extract_attachments.py", line 67, in main
run(filename, outdir)
File "extract_attachments.py", line 45, in run
attachments = find_attachments(msg)
File "extract_attachments.py", line 34, in find_attachments
key, val = kv.split('=')
ValueError: too many values to unpack

Probably an embedded equals sign in the value. `str`’s `partition` is a better choice.

…

On 4. Apr 2020, at 05:38, zarza ***@***.***> wrote: @zarza commented on this gist. Traceback (most recent call last): File "extract_attachments.py", line 71, in main() File "extract_attachments.py", line 67, in main run(filename, outdir) File "extract_attachments.py", line 45, in run attachments = find_attachments(msg) File "extract_attachments.py", line 34, in find_attachments key, val = kv.split('=') ValueError: too many values to unpack — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe.

File "D:\Users\prashant.kochar\PycharmProjects\TABLE_COPY_AND_OTHER_STUFF\try_1.py", line 70, in
main()
main()
File "D:\Users\prashant.kochar\PycharmProjects\TABLE_COPY_AND_OTHER_STUFF\try_1.py", line 66, in main
run(filename, outdir)
File "D:\Users\prashant.kochar\PycharmProjects\TABLE_COPY_AND_OTHER_STUFF\try_1.py", line 49, in run
cdisp_filename = os.path.normpath(cdisp['filename'])
KeyError: 'filename'

@pkochar263 Did you have a question?

Really nice, thanks! It is also great to feed with find -exec to get all attachments from all .eml files in a directory (or directory tree).

excellent!!! thanks!!!