Use python's email parser instead of bad self-parsing.

1 files changed, 31 insertions, 31 deletions

diff --git a/src/emailinfo.py b/src/emailinfo.py
index 95fc1fc3..deaa285f 100644
--- a/src/emailinfo.py
+++ b/src/emailinfo.py
@@ -6,12 +6,14 @@ import ipaddr
 import email.utils
 import datetime
 from weblookuptools import *
+from email.parser import Parser
 
 class EmailInfo:
 	__location = None
 	ipRegex = re.compile(r"(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)\.){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)")
 	ipInHostRegex = re.compile(r"(?:(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)-){3}(?:25[0-5]|2[0-4][0-9]|[01]?[0-9][0-9]?)")
 	hostRegex = re.compile(generateHostRegex())
+	parser = Parser()
 	def __init__(self, ip = "", date = 0, debug = "", path = ""):
 		self.ip = ip
 		self.date = date
@@ -31,39 +33,37 @@ class EmailInfo:
 	@classmethod
 	def parseFile(cls, fileName):
 		file = open(fileName)
+		msg = EmailInfo.parser.parse(file, True)
 		receiveHosts = []
 		date = False
-		for line in file:
-			line = line.strip()
-			if line.startswith("Received:"): #Only look at Received lines
-				filteredIps = []
-				#After the "by" or "for" there is no useful information
-				byIndex = line.find("by")
-				forIndex = line.find("for")
-				if forIndex != -1 and forIndex < byIndex:
-					byIndex = forIndex
-				if byIndex != -1:
-					line = line[:byIndex]
-				ips = EmailInfo.ipRegex.findall(line)
-				hosts = EmailInfo.hostRegex.findall(line)
-				#Some host names have IPs embedded in them, like dyn-23.54.128.44.columbia.edu
-				for host in hosts:
-					ipInHosts = EmailInfo.ipInHostRegex.findall(host)
-					if len(ipInHosts) > 0:
-						ips.insert(0, ipInHosts[0].replace("-", "."))
-						hosts.remove(host)
-				#Filter out non-internet IPs using Google's library
-				for ip in ips:
-					if EmailInfo.isInternetIP(ip):
-						filteredIps.append(ip)
-				#We seperate the hosts from the ips because we give more importance to IPs, since host resolution may have changed over the years.
-				if len(hosts) > 0 or len(filteredIps) > 0:
-					receiveHosts.append([hosts, filteredIps])
-			elif line.startswith("Date:") and not date:
-				try:
-					date = datetime.datetime.utcfromtimestamp(email.utils.mktime_tz(email.utils.parsedate_tz(line[6:])))
-				except:
-					date = False
+		for line in msg.get_all("Received"):
+			filteredIps = []
+			#After the "by" or "for" there is no useful information
+			byIndex = line.find("by")
+			forIndex = line.find("for")
+			if forIndex != -1 and forIndex < byIndex:
+				byIndex = forIndex
+			if byIndex != -1:
+				line = line[:byIndex]
+			ips = EmailInfo.ipRegex.findall(line)
+			hosts = EmailInfo.hostRegex.findall(line)
+			#Some host names have IPs embedded in them, like dyn-23.54.128.44.columbia.edu
+			for host in hosts:
+				ipInHosts = EmailInfo.ipInHostRegex.findall(host)
+				if len(ipInHosts) > 0:
+					ips.insert(0, ipInHosts[0].replace("-", "."))
+					hosts.remove(host)
+			#Filter out non-internet IPs using Google's library
+			for ip in ips:
+				if EmailInfo.isInternetIP(ip):
+					filteredIps.append(ip)
+			#We seperate the hosts from the ips because we give more importance to IPs, since host resolution may have changed over the years.
+			if len(hosts) > 0 or len(filteredIps) > 0:
+				receiveHosts.append([hosts, filteredIps])
+		try:
+			date = datetime.datetime.utcfromtimestamp(email.utils.mktime_tz(email.utils.parsedate_tz(msg.get("Date"))))
+		except:
+			date = False
 		file.close()
 		#Earlier lines come later in the file, so we look at the file reversed
 		receiveHosts.reverse()