Download, organize and search logs

mailfetch.py

import email
import imaplib
import os

class FetchEmail():
    connection = None
    error = None

    def __init__(self, mail_server, username, password):
        self.connection = imaplib.IMAP4_SSL(mail_server)
        self.connection.login(username, password)
        self.connection.select(readonly=False)   # so we can mark mails as read

    def close_connection(self):
        self.connection.close()

    def save_attachment(self, msg, download_folder='tmp'):
        try:
            data = self.connection.fetch(msg, '(RFC822)')

        except Exception:
            print "\033[1;36m[Error fetching]\033[1;m"
            self.close_connection()
            exit()
        att_path = None
        m = email.message_from_string(data[1][0][1])
        for part in m.walk():
            filename = part.get_filename()
            if (
                part.get_content_maintype() is 'multipart'
                or not part.get('Content-Disposition')
                or not filename
                or 'Keys' not in filename
                ):
                continue

            filename = '[{}]'.format(msg.zfill(6)) + filename
            att_path = os.path.join(download_folder, filename)

            if os.path.isfile(att_path):
                print att_path, '\033[1;32m[EXIST]#\033[1;m'
                continue
            open(att_path, 'wb').write(part.get_payload(decode=True))
            print att_path, '\033[1;32m[OK]#\033[1;m'

        if not att_path:
            print "\033[1;36m[No attachment found in: {}]\033[1;m".format(msg)

    def save_all_attachment(self, WEmails, download_folder='tmp'):
        if WEmails.startswith('a'):
            WEmails = 'ALL'
        elif WEmails.startswith('u'):
            WEmails = 'UnSeen'
        else:
            print 'Set ALL or UNSEEN to download'
            exit()
        items = self.connection.search(None, WEmails)
        mails = items[1][0]
        if not mails:
            print "\033[1;36m[No new mail]\033[1;m"
            exit()
        for emailid in mails.split(' '):
            print '\033[1;33m[Fetching...] => \033[1;m', emailid
            self.save_attachment(emailid, download_folder)

if __name__ == "__main__":
    datos = ['imap.gmail.com', '', '']
    FetchEmail(datos[0], datos[1], datos[2]).save_all_attachment('u')

organizelogs.py

import glob
import os
import json
from bs4 import BeautifulSoup

try:
    with open('database', 'r') as database:
        my_dict = json.load(database)
except IOError:
    my_dict = {}

for File in sorted(glob.glob('tmp/*')):
    filename = os.path.basename(File)
    if filename in my_dict:
        continue
    htmlfile = open(File).read()
    tmplist = []
    soup = BeautifulSoup(htmlfile, 'html.parser')
    c = soup.find('body').findAll(text=True, recursive=False)
    for i in c:
        tmplist.append(i)
    my_dict[filename] = tmplist
    print filename, '=> Done#'
with open('database', 'w') as outfile:
    print '[Writing...]'
    json.dump(my_dict, outfile)

searchlogs.py

import json
string = raw_input('String to search: ')
with open('database') as f:
    my_dict = json.load(f)
for i in sorted(my_dict):
    for ii in my_dict[i]:
        if string in ii:
            print '\033[1;31m[{}] => \033[1;m'.format(i) + \
                '\033[1;32m{}\033[1;m'.format(ii.encode('utf-8')), ' #'