Initial commit.HEADmaster

1 files changed, 106 insertions, 0 deletions

diff --git a/uniqueemails.py b/uniqueemails.py
new file mode 100755
index 0000000..f94992f
--- /dev/null
+++ b/uniqueemails.py
@@ -0,0 +1,106 @@
+#!/usr/bin/env python
+# -*- coding: iso-8859-1 -*-
+from imaplib import IMAP4_SSL
+from optparse import OptionParser
+from email.parser import HeaderParser
+from email.message import Message
+from email.utils import getaddresses
+import sys
+import os.path
+import os
+
+def main():
+	parser = OptionParser(usage="%prog --username/-u USERNAME --password/-p PASSWORD --mode/-m MODE [--domain/-d DOMAIN] [--cachedir/-c CACHEDIR]", description="Downloads gmail message headers and determines the set of all e-mail addresses on DOMAIN at which people have emailed you.")
+	parser.add_option("-u", "--username", action="store", type="string", metavar="USERNAME", help="Gmail username")
+	parser.add_option("-p", "--password", action="store", type="string", metavar="PASSWORD", help="Gmail password")
+	parser.add_option("-d", "--domain", action="store", type="string", metavar="DOMAIN", help="Domain name")
+	parser.add_option("-c", "--cachedir", action="store", type="string", metavar="CACHEDIR", help="The directory to cache fetched headers for subsequent runs")
+	parser.add_option("-m", "--mode", action="store", type="string", metavar="SENDERSFILE", help="If the mode is \"to\", this prints a list of all the emails you've received email on. If the mode is \"from\" this prints a list of everyone who has sent you email. If the mode is \"frombyto\" this prints a list of all the addresses that have emailed you sorted by the address at which you received email. If the mode is \"tobyfrom\" this prints a of all the addresses you have received e-mail from sorted and duplicated by who sent the e-mail.")
+	(options, args) = parser.parse_args()
+	if options.username == None or options.password == None:
+		parser.error("Username and password are all required.")
+	if options.mode != "from" and options.mode != "to" and options.mode != "frombyto" and options.mode != "tobyfrom":
+		parser.error("You must specify a mode.")
+	if not options.username.lower().endswith("@gmail.com") and not options.username.lower().endswith("@googlemail.com"):
+		options.username += "@gmail.com"
+	if options.cachedir != None and not os.path.exists(options.cachedir):
+		try:
+			os.makedirs(options.cachedir)
+		except:
+			sys.stderr.write("Could not make cache dir. Skipping cache.\n")
+			options.cachedir = None
+
+	imap = IMAP4_SSL("imap.gmail.com")
+	imap.login(options.username, options.password)
+	imap.select("[Gmail]/All Mail", True)
+	typ, data = imap.search(None, 'ALL')
+	if typ != "OK":
+		sys.exit(("Could not search properly: %s" % typ))
+	emailAddresses = {}
+	data = data[0].split()
+	length = len(data)
+	counter = 0
+	parser = HeaderParser()
+	for num in data:
+		counter += 1
+		if options.cachedir != None:
+			cachePath = os.path.join(options.cachedir, num)
+		else:
+			cachePath = None
+		if cachePath != None and os.path.exists(cachePath):
+			message = parser.parse(open(cachePath, "r"))
+		else:
+			try:
+				typ, data = imap.fetch(num, '(RFC822.HEADER)')
+			except:
+				sys.stderr.write("Failed to fetch ID %s\n" % num)
+				continue
+			if typ != "OK":
+				sys.stderr.write("Failed to fetch ID %s: %s\n" % (num, typ))
+				continue
+			if cachePath != None:
+				try:
+					f = open(cachePath, "w")
+					f.write(data[0][1])
+					f.close()
+				except:
+					sys.stderr.write("Could not write cache for %s" % num)
+			message = parser.parsestr(data[0][1], True)
+		tos = message.get_all('to', [])
+		ccs = message.get_all('cc', [])
+		resent_tos = message.get_all('resent-to', [])
+		resent_ccs = message.get_all('resent-cc', [])
+		all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
+		for address in all_recipients:
+			if len(address) == 2 and (options.domain == None or address[1].endswith(options.domain)):
+				to = address[1].lower()
+				fros = getaddresses(message.get_all('from', []))
+				fro_addresses = set()
+				for addr in fros:
+					if len(addr) == 2:
+						fro_addresses.add(addr[1].lower())
+				if options.mode == "to" or options.mode == "tobyfrom":
+					if to not in emailAddresses:
+						emailAddresses[to] = set()
+					emailAddresses[to] = emailAddresses[to].union(fro_addresses)
+				elif options.mode == "from" or options.mode == "frombyto":
+					for fro in fro_addresses:
+						if fro not in emailAddresses:
+							emailAddresses[fro] = set()
+						emailAddresses[fro].add(to)
+				sys.stderr.write("[%s of %s]: Message to %s from %s.\n" % (counter, length, address[1], fro_addresses))
+		if len(all_recipients) == 0:
+			sys.stderr.write("[%s of %s]: Message has empty To header.\n" % (counter, length))
+	imap.close()
+	imap.logout()
+	if options.mode == "to" or options.mode == "from":
+		for addr in emailAddresses.keys():
+			print addr
+	elif options.mode == "tobyfrom" or options.mode == "frombyto":
+		for to, fro in emailAddresses.items():
+			print to
+			for f in fro:
+				print "\t%s" % f
+
+if __name__ == '__main__':
+	main()
\ No newline at end of file