Created
January 30, 2020 04:08
-
-
Save dodger487/3e5843918f318770e39b570840595ce3 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"""Print out text of emails from MBox file.""" | |
from collections import Counter | |
import mailbox | |
import sys | |
import re | |
mbox = mailbox.mbox("friends-001.mbox") | |
c = Counter(m["from"] for m in mbox) | |
print(c.most_common(10)) | |
def remove_r(text): | |
return text.replace("\r", "") | |
def strip_replies(text): | |
lines = text.split("\n") | |
lines = [l for l in lines if len(l) > 0] | |
lines = [line for line in lines if line[0] != ">"] | |
return "\n".join(lines) | |
def strip_footer(text): | |
text, _ = re.subn("On (Sun|Mon|Tue|Wed|Thu|Fri|Sat),.*, 20.. at.*@gmail.com.*wrote.*", | |
"", | |
text, | |
flags=re.DOTALL) | |
text, _ = re.subn("You received this message because you are subscribed to the Google Groups.*", | |
"", | |
text, | |
flags=re.DOTALL) | |
return text | |
def get_core_text(msg): | |
msg = get_text(msg) | |
msg = remove_r(msg) | |
msg = strip_replies(msg) | |
msg = strip_footer(msg) | |
return msg | |
def get_member_emails(mbox, sender_list, limit=100): | |
msgs = [] | |
for msg in mbox: | |
if (msg["from"] in sender_list | |
and msg["to"] is not None | |
and "dunghole" in msg["to"]): | |
msgs.append(msg) | |
if limit is not None and len(msgs) > limit: | |
break | |
return msgs | |
def get_text(msg): | |
while msg.is_multipart(): | |
msg = msg.get_payload()[0] | |
return msg.get_payload() | |
def print_msgs(msg_list, f=sys.stdout): | |
for msg in msg_list: | |
print("-------------------------------------------------------------------", file=f) | |
print("Subject:", msg["subject"], file=f) | |
print("", file=f) | |
print(get_core_text(msg), file=f) | |
print("", file=f) | |
george_email_addr = [ | |
"George <george@example.com>", | |
"George <georgeS@college.edu>", | |
] | |
george_emails = get_member_emails(mbox, george_email_addr, limit=None) | |
with open("george_emails.txt", 'w') as f: | |
print_msgs(george_emails, f) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment