#!/usr/bin/env python
"""Save all attachments for given gmail account."""
import os, sys
from libgmail import GmailAccount
ga = GmailAccount("your.account@gmail.com", "pA$$w0Rd_")
ga.login()
# folders: inbox, starred, all, drafts, sent, spam
for thread in ga.getMessagesByFolder('all', allPages=True):
for msg in thread:
sys.stdout.write('.')
if msg.attachments:
print "\n", msg.id, msg.number, msg.subject, msg.sender
for att in msg.attachments:
if att.filename and att.content:
attdir = os.path.join(thread.id, msg.id)
if not os.path.isdir(attdir):
os.makedirs(attdir)
with open(os.path.join(attdir, att.filename), 'wb') as f:
f.write(att.content)
import email, getpass, imaplib, os
detach_dir = '.' # directory where to save attachments (default: current)
user = raw_input("Enter your GMail username:")
pwd = getpass.getpass("Enter your password: ")
# connecting to the gmail imap server
m = imaplib.IMAP4_SSL("imap.gmail.com")
m.login(user,pwd)
m.select("[Gmail]/All Mail") # here you a can choose a mail box like INBOX instead
# use m.list() to get all the mailboxes
resp, items = m.search(None, "ALL") # you could filter using the IMAP rules here (check http://www.example-code.com/csharp/imap-search-critera.asp)
items = items[0].split() # getting the mails id
for emailid in items:
resp, data = m.fetch(emailid, "(RFC822)") # fetching the mail, "`(RFC822)`" means "get the whole stuff", but you can ask for headers only, etc
email_body = data[0][1] # getting the mail content
mail = email.message_from_string(email_body) # parsing the mail content to get a mail object
#Check if any attachments at all
if mail.get_content_maintype() != 'multipart':
continue
print "["+mail["From"]+"] :" + mail["Subject"]
# we use walk to create a generator so we can iterate on the parts and forget about the recursive headach
for part in mail.walk():
# multipart are just containers, so we skip them
if part.get_content_maintype() == 'multipart':
continue
# is this part an attachment ?
if part.get('Content-Disposition') is None:
continue
filename = part.get_filename()
counter = 1
# if there is no filename, we create one with a counter to avoid duplicates
if not filename:
filename = 'part-%03d%s' % (counter, 'bin')
counter += 1
att_path = os.path.join(detach_dir, filename)
#Check if its already there
if not os.path.isfile(att_path) :
# finally write the stuff
fp = open(att_path, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
import javax.mail.*
import java.util.Properties
String gmailServer
int gmailPort
def user, password, LIMIT
def inboxFolder, root, StartDate, EndDate
// Downloads all attachments from a gmail mail box as per some criteria
// to a specific folder
// Based on code from
// http://agileice.blogspot.com/2008/10/using-groovy-to-connect-to-gmail.html
// http://stackoverflow.com/questions/155504/download-mail-attachment-with-java
//
// Requires:
// java mail jars in the class path (mail.jar and activation.jar)
// openssl, with gmail certificate added to java keystore (see agileice blog)
//
// further improvement: maybe findAll could be used to filter messages
// subject could be added as another criteria
////////////////////// <CONFIGURATION> //////////////////////
// Maximm number of emails to access in case parameter range is too high
LIMIT = 10000
// gmail credentials
gmailServer = "imap.gmail.com"
gmailPort = 993
user = "gmailuser@gmail.com"
password = "gmailpassword"
// gmail label, or "INBOX" for inbox
inboxFolder = "finance"
// local file system where the attachment files need to be stored
root = "D:\\AttachmentStore"
// date range dd-mm-yyyy
StartDate= "31-12-2009"
EndDate = "1-6-2010"
////////////////////// </CONFIGURATION> //////////////////////
StartDate = Date.parse("dd-MM-yyyy", StartDate)
EndDate = Date.parse("dd-MM-yyyy", EndDate)
Properties props = new Properties();
props.setProperty("mail.store.protocol", "imaps");
props.setProperty("mail.imaps.host", gmailServer);
props.setProperty("mail.imaps.port", gmailPort.toString());
props.setProperty("mail.imaps.partialfetch", "false");
def session = javax.mail.Session.getDefaultInstance(props,null)
def store = session.getStore("imaps")
store.connect(gmailServer, user, password)
int i = 0;
def folder = store.getFolder(inboxFolder)
folder.open(Folder.READ_ONLY)
for(def msg : folder.messages) {
//if (msg.subject?.contains("bank Statement"))
println "[$i] From: ${msg.from} Subject: ${msg.subject} -- Received: ${msg.receivedDate}"
if (msg.receivedDate < StartDate || msg.receivedDate > EndDate) {
println "Ignoring due to date range"
continue
}
if (msg.content instanceof Multipart) {
Multipart mp = (Multipart)msg.content;
for (int j=0; j < mp.count; j++) {
Part part = mp.getBodyPart(j);
println " ---- ${part.fileName} ---- ${part.disposition}"
if (part.disposition?.equalsIgnoreCase(Part.ATTACHMENT)) {
if (part.content) {
def name = msg.receivedDate.format("yyyy_MM_dd") + " " + part.fileName
println "Saving file to $name"
def f = new File(root, name)
//f << part.content
try {
if (!f.exists())
f << part.content
}
catch (Exception e) {
println "*** Error *** $e"
}
}
else {
println "NO Content Found!!"
}
}
}
}
if (i++ > LIMIT)
break;
}
# Something in lines of http://stackoverflow.com/questions/348630/how-can-i-download-all-emails-with-attachments-from-gmail
# Make sure you have IMAP enabled in your gmail settings.
# Right now it won't download same file name twice even if their contents are different.
# Gmail as of now returns in bytes but just in case they go back to string this line is left here.
import email
import getpass, imaplib
import os
import sys
import time
detach_dir = '.'
if 'attachments' not in os.listdir(detach_dir):
os.mkdir('attachments')
userName = input('Enter your GMail username:\n')
passwd = getpass.getpass('Enter your password:\n')
try:
imapSession = imaplib.IMAP4_SSL('imap.gmail.com',993)
typ, accountDetails = imapSession.login(userName, passwd)
if typ != 'OK':
print ('Not able to sign in!')
raise
imapSession.select('Inbox')
typ, data = imapSession.search(None, 'ALL')
if typ != 'OK':
print ('Error searching Inbox.')
raise
# Iterating over all emails
for msgId in data[0].split():
typ, messageParts = imapSession.fetch(msgId, '(RFC822)')
if typ != 'OK':
print ('Error fetching mail.')
raise
#print(type(emailBody))
emailBody = messageParts[0][1]
#mail = email.message_from_string(emailBody)
mail = email.message_from_bytes(emailBody)
for part in mail.walk():
#print (part)
if part.get_content_maintype() == 'multipart':
# print part.as_string()
continue
if part.get('Content-Disposition') is None:
# print part.as_string()
continue
fileName = part.get_filename()
if bool(fileName):
filePath = os.path.join(detach_dir, 'attachments', fileName)
if not os.path.isfile(filePath) :
print (fileName)
fp = open(filePath, 'wb')
fp.write(part.get_payload(decode=True))
fp.close()
imapSession.close()
imapSession.logout()
except :
print ('Not able to download all attachments.')
time.sleep(3)