def call_api(self):
outlook = Dispatch("Outlook.Application")
mapi = outlook.GetNamespace("MAPI")
Accounts = mapi.Folders
#解析邮件内容
if self.mail_title != "":
try:
for Account in Accounts:
if Account.Name == self.account_name:
Folders = Account.Folders #读取该账户下的文件夹列表
for Folder in Folders: #第一层目录
if len(self.folder_name[0]) == 0: #输入文件夹为空
if Folder.Name == "收件箱":
mail_info = self.save_attachments(
Folder) #调用邮件解析和附件下载函数
elif len(self.folder_name) == 1:
if Folder.Name == self.folder_name[0]:
mail_info = self.save_attachments(
Folder) #调用邮件解析和附件下载函数
else:
if Folder.Name == self.folder_name[0]:
for i in range(1, len(self.folder_name)):
for Folder2 in Folder.Folders:
if Folder2.Name == self.folder_name[
i]:
Folder = Folder2
mail_info = self.save_attachments(
Folder) #调用邮件解析和附件下载函数
return (mail_info)
except:
traceback.print_exc()
sys.exit()
else:
return ("邮件title不能为空！~")
def read_outlook_mailbox():
"""连接Outlook邮箱，读取收件箱内的邮件内容"""
# 使用MAPI协议连接Outlook
account = Dispatch('Outlook.Application').GetNamespace('MAPI')
# 获取收件箱所在位置
inbox = account.GetDefaultFolder(6) # 数字6代表收件箱
# 获取收件箱下的所有邮件
mails = inbox.Items
mails.Sort('[ReceivedTime]', True) # 邮件按时间排序
# 读取收件箱内前3封邮件的所有信息（下标从1开始）
for index in range(1, 4):
print('正在读取第[{}]封邮件...'.format(index))
mail = mails.Item(index)
print('接收时间：{}'.format(str(mail.ReceivedTime)[:-6]))
print('发件人：{}'.format(mail.SenderName))
print('收件人：{}'.format(mail.To))
print('抄送人：{}'.format(mail.CC))
print('主题：{}'.format(mail.Subject))
print('邮件正文内容：{}'.format(mail.Body))
print('邮件附件数量：{}'.format(mail.Attachments.Count))
print('邮件MessageID：{}'.format(mail.EntryID))
print('会话主题：{}'.format(mail.ConversationTopic))
print('会话ID：{}'.format(mail.ConversationID))
print('会话记录相对位置：{}'.format(mail.ConversationIndex))
# 保存邮件中的附件，如果没有附件不会执行也不会产生异常
attachment = mail.Attachments
for each in attachment:
save_attachment_path = os.getcwd() # 保存附件到当前路径
each.SaveAsFile(r'{}\{}'.format(save_attachment_path,
each.FileName))
print('附件（{}）保存完毕'.format(each.FileName))
def send_email(to, subject, body):
'''
docstring
'''
try:
outlook = Dispatch("Outlook.Application")
mailitem = outlook.CreateItem(0)
tostr = ''
if type(to) is list:
tostr = ';'.join(to).strip(';').strip().strip(';')
else:
tostr = to.strip()
mailitem.To = tostr
mailitem.Subject = subject
mailitem.Body = body
mailitem.Send()
except Exception as e:
print(e)
traceback.print_exc()
from win32com.client.gencache import EnsureDispatch as Dispatch
import os
import sys
outlook = Dispatch("Outlook.Application")
mapi = outlook.GetNamespace("MAPI")
class Oli():
def __init__(self, outlook_object):
self._obj = outlook_object
def items(self):
array_size = self._obj.Count
for item_index in range(1,array_size+1):
yield (item_index, self._obj[item_index])
def prop(self):
return sorted( self._obj._prop_map_get_.keys() )
# for inx, folder in Oli(mapi.Folders).items():
# # iterate all Outlook folders (top level)
# #print "-"*70
# print(folder.Name)
# for inx,subfolder in Oli(folder.Folders).items():
# print("({}) {} => {}".format(inx, subfolder.Name, subfolder))
def mkdir_p(path):
try:
os.makedirs(path)
except:
def scan_inbox():
'''
docstring
'''
global CONFIG
foldertree = CONFIG["foldertree"]
outlook = Dispatch("Outlook.Application")
mapi = outlook.GetNamespace("MAPI")
cwd = os.getcwd()
processed = []
matchfound = False
class Oli():
def __init__(self, outlook_object):
self._obj = outlook_object
def items(self):
array_size = self._obj.Count
for item_index in xrange(1, array_size + 1):
yield (item_index, self._obj[item_index])
def prop(self):
return sorted(self._obj._prop_map_get_.keys())
rules = None
def loadrules():
'''
docstring
'''
rules = load_yara("rules")
rulecount = 0
for r in rules:
rulecount += 1
print("Loaded " + str(rulecount) + " YARA rules.")
folderindex = 0
loadrules()
loadioc()
#this needs fixing :/
outlookfolder = mapi.Folders
for inx, folder in Oli(outlookfolder).items():
if folder.Name == foldertree[0]:
outlookfolder = folder
print(">" + folder.Name + ":")
break
for currentfolder in foldertree[1:]:
for inx, folder in Oli(outlookfolder.Folders).items():
if folder.Name == currentfolder:
print("\t>> " + folder.Name)
outlookfolder = folder
folderindex = inx
# break
try:
os.mkdir(cwd + "\\workdir")
except Exception:
pass
# https://docs.microsoft.com/en-us/dotnet/api/microsoft.office.interop.outlook._mailitem?view = outlook-pia
for msg in outlookfolder.Items:
try:
for attachment in msg.Attachments:
if attachment.FileName.startswith(
"Scan_results") and hashlib.sha256(
msg.Body).hexdigest() not in processed:
print("Removed Scan_results")
msg.Attachments.Remove(attachment.Index)
msg.Save()
except Exception as e:
print(e)
#raw_input("Press any key to start scanning, Outlook will ask you for grant permission to access the Inbox...")
while True:
print(
"[" + datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d %H:%M:%S') +
"] Inbox Scan started for " + "/".join(foldertree).strip("/"))
print("Scanning folder: /".join(foldertree).strip("/"))
for msg in outlookfolder.Items:
try:
msgsha256 = hashlib.sha256(msg.Body).hexdigest()
if msgsha256 in processed:
continue
else:
processed.append(msgsha256)
yarascan = ''
external_scan_result = ''
msgmeta = ''
yaramatches = None
senderdomain = sendertxt = senderspf = ''
try:
msgmeta += "SenderEmailAddress:\t" + \
unidecode.unidecode(msg.SenderEmailAddress)+"\n"
msgmeta += "To:\t" + unidecode.unidecode(msg.To) + "\n"
msgmeta += "Subject:\t" + \
unidecode.unidecode(msg.Subject)+"\n"
msgmeta += "CC:\t" + unidecode.unidecode(msg.CC) + "\n"
msgmeta += "Categories:\t" + \
unidecode.unidecode(msg.Categories)+"\n"
except AttributeError:
pass
print("-" * 80)
print(msgmeta)
if msg.Attachments.Count > 0:
#print "."
for attachment in msg.Attachments:
# print attachment
#print attachment.GetTemporaryFilePath()
#print attachment.FileName
if attachment.FileName:
attachment.SaveAsFile(cwd + "\\workdir\\" +
attachment.FileName)
try:
yaramatches = rules.match(cwd + "\\workdir\\" +
attachment.FileName)
except Exception as e:
pass
if yaramatches:
matchfound = True
yarascan += print_yara(
yaramatches,
context="Attachment match:" +
str(attachment.FileName)[:40],
msg=msgmeta)
with open(
cwd + "\\workdir\\" +
attachment.FileName, "rb") as f:
scan_result, matchfound = external_scans(
f.read(), binary=True)
external_scan_result += scan_result
if attachment.FileName.lower().endswith(".msg"):
msgdata = ExtractMsg.process_msg(
cwd + "\\workdir\\" + attachment.FileName)
m = "MSG found:"+cwd+"\\workdir\\"+attachment.FileName+"\n\tSubject:" + \
str(msgdata["subject"])+"\n\tTo:"+str(msgdata["to"])+"\n\tFrom:"+str(
msgdata["from"])+"\n\tDate:"+str(msgdata["date"])
msgmeta += m + "\n"
print("MSG attachment:")
print(m)
# print(msgdata["body"])
try:
yaramatches = rules.match(
data=msgdata["body"])
except Exception as e:
pass
# traceback.print_exc()
if yaramatches:
yarascan += print_yara(
yaramatches,
context="MSG attachment body match",
msg=msgmeta)
matchfound = True
scan_result, matchfound = external_scans(
msgdata["body"], vt=False)
external_scan_result += scan_result
if not None is msgdata:
for msgattachment in msgdata[
'attachments']:
# print("Attachment:"+msgattachment["filename"])
with open(
cwd + "\\workdir\\__" +
attachment.FileName + "__" +
msgattachment["filename"],
"wb+") as f:
f.write(
base64.b64decode(
msgattachment['data']))
try:
yaramatches = rules.match(
cwd + "\\workdir\\__" +
attachment.FileName + "__" +
msgattachment["filename"])
except Exception as e:
pass
if yaramatches:
matchfound = True
yarascan += print_yara(
yaramatches,
msg=msgmeta,
context=
"Attachment extracted from MSG attachment matched: "
+
str(attachment.FileName +
"__" +
msgattachment["filename"])
[:64])
with open(
cwd + "\\workdir\\__" +
attachment.FileName +
"__" +
msgattachment["filename"],
"rb") as f:
scan_result, matchfound = external_scans(
f.read(), binary=True)
external_scan_result += scan_result
else:
print("MSGdata is none")
hbody = unidecode.unidecode(msg.HTMLBody)
body = unidecode.unidecode(msg.Body)
for line in hbody.splitlines():
if "x-originating-ip" in line.lower():
print line
try:
yaramatches = rules.match(data=hbody)
yaramatches = rules.match(data=body)
except Exception as e:
pass
if yaramatches:
print '-' * 80
matchfound = True
yarascan += print_yara(yaramatches,
context="HTMLBody matched",
msg=msgmeta,
showstrings=True)
print '-' * 80
# if yaramatches:
# print '-'*80
#yarascan += print_yara(yaramatches,context = "Plain body matched",msg = msgmeta,showstrings = True)
# print '-'*80
scan_result, matchfound = external_scans(hbody, vt=False)
external_scan_result += scan_result
#print (external_scan_result)
header = '''
<html>
<body>
'''
footer = '''
</body>
</html>
'''
if senderspf:
header += "<h1>SPF records</h1></b>"
header += "<h3>Domain</h3>:" + senderdomain
header += "</br>SPF records:" + senderspf
if yarascan.strip():
yarascan = "<h1>Yara matches</h1></br><pre>" + yarascan + "</pre><hr>"
scanres = header + yarascan + "</br>\n" + external_scan_result
resfile = ''
if matchfound:
resfile = "Scan_results_matchfound.htm"
else:
resfile = "Scan_results_nomatches.htm"
if scanres:
with open(cwd + "\\" + resfile, "w+") as f:
f.write(scanres)
msg.Attachments.Add(cwd + "\\" + resfile, 1, 1, resfile)
msg.Save()
except Exception as e:
print e
traceback.print_exc()
print(
"[" + datetime.datetime.fromtimestamp(
time.time()).strftime('%Y-%m-%d %H:%M:%S') +
"] Done scanning,sleeping for " + str(CONFIG["scan_interval"]) +
" seconds...")
time.sleep(int(CONFIG["scan_interval"]))
loadconfig()
loadioc()
"""Open the grid combination csv file, skip the header with the .next method, and split out each column by the comma delimiter"""
combofileloc = "c:/temp/dog.csv"
combofile = open(combofileloc, 'r')
combofile.next()
print 'connecting to db'
DATABASE_FILEPATH = r"c:\temp\test.accdb"
CONNECTION_STRING = "Provider=Microsoft.Jet.OLEDB.4.0; data Source=%s" % \
DATABASE_FILEPATH
if os.path.exists (DATABASE_FILEPATH):
os.remove (DATABASE_FILEPATH)
adox = Dispatch ("ADOX.Catalog")
adox.Create (CONNECTION_STRING)
adox = None
db = Dispatch ('ADODB.Connection')
db.Open (CONNECTION_STRING)
print 'made it to here'
try:
## db.Execute ('CREATE TABLE dtest (id INT, data INT)')
## db.Execute ('INSERT INTO dtest (id, data) VALUES (1, 2)')
db.Execute ('CREATE TABLE combo(rowid INT, value2 INT, count2 INT, evt INT, evc INT, evh INT)')
## db.Execute ('INSERT INTO combo(rowid, value2, count2, evt, evc, evh) VALUES (1, 2, 3, 4, 5, 6)')
## print' it worked'
for line in combofile:
print 'iterating'
items = line.split(',')
from win32com.client import constants
from win32com.client.gencache import EnsureDispatch as Dispatch
def list_folders(mapi_object, indent=''):
for _, folder in enumerate(mapi_object.Folders, 1): # 1-index
if folder.DefaultItemType == constants.olMailItem:
print('{}{}'.format(indent, folder.Name))
list_folders(folder, indent=indent + ' ')
#def to_folder(mapi, folder):
mapi = Dispatch("Outlook.Application").GetNamespace("MAPI")
#list_folders( mapi )
#mapi.Logon("Outlook")
#inbox = mapi.GetDefaultFolder()
inbox = mapi.Folders.Item("production")
print(inbox)
'''
messages = inbox.Items
message = messages.GetLast()
body = message.Body
print(body)
'''
def read_email(date, my_account, sent_account):
# 读取邮箱
outlook = Dispatch("Outlook.Application")
mapi = outlook.GetNamespace("MAPI")
Accounts = mapi.Folders
# 读取的员工账号
names = []
# 短信内容
contents = []
# 读取邮件存入pandas
c = ['Root_Directory_Name_1', 'Level_1_FolderName_1', 'Level_2_FolderName_1', 'ReceivedTime_1', 'SenderName_1',
'to_to_1', 'cc_cc_1', 'Subject_1', 'MessageID_1', 'ConversationTopic_1', 'ConversationID_1',
'ConversationIndex_1', 'EmailBody_1']
df = pd.DataFrame(columns=c)
for Account_Name in Accounts:
# 只查找需要的邮箱账号信息
if Account_Name.Name == my_account:
print(' >> 正在查询的帐户名称：', Account_Name.Name, '\n')
Level_1_Names = Account_Name.Folders
for Level_1_Name in Level_1_Names:
# 只需要收件箱的邮件
if Level_1_Name.Name == '收件箱':
print(' - 正在查询一级目录：', Level_1_Name.Name)
Mail_1_Messages = Level_1_Name.Items
# 将邮件按日期排序，可减少遍历内容
Mail_1_Messages.Sort("[ReceivedTime]", True)
for xx in Mail_1_Messages: # xx = 'mail' # 开始查看单个邮件的信息
print(xx.Subject)
Root_Directory_Name_1 = Account_Name.Name
Level_1_FolderName_1 = Level_1_Name.Name
Level_2_FolderName_1 = ''
ReceivedTime_1 = str(xx.ReceivedTime)[:10] # 接收日期
if ReceivedTime_1 != date: # 只要特定日期的邮件
continue
SenderName_1 = xx.SenderName # 发件人
if SenderName_1 != sent_account: # 只要特定发件人的邮件
continue
Subject_1 = xx.Subject # 主题
EmailBody_1 = xx.Body # 邮件内容
to_to_1 = xx.To # 收件人
cc_cc_1 = xx.CC # 抄送人
MessageID_1 = xx.EntryID # 邮件MessageID
ConversationTopic_1 = xx.ConversationTopic # 会话主题
ConversationID_1 = xx.ConversationID # 会话ID
ConversationIndex_1 = xx.ConversationIndex # 会话记录相对位置
data = [Root_Directory_Name_1, Level_1_FolderName_1, Level_2_FolderName_1, ReceivedTime_1,
SenderName_1, to_to_1, cc_cc_1, Subject_1, MessageID_1, ConversationTopic_1,
ConversationID_1, ConversationIndex_1, EmailBody_1]
dataf = dict(zip(c, data))
df = df.append(dataf, ignore_index=True)
return df
for i in range(result.Size):
document = result.GetDocument(i)
try:
sep = document.rindex(':')
line = int(document[sep + 1:])
document = document[:sep]
print document.decode('iso-8859-1'), line, result.GetScore(
i), linecache.getline(document, line + 1).decode('iso-8859-1'),
except ValueError:
print document.encode('iso-8859-1', 'ignore'), result.GetScore(i)
try:
try:
ti = Dispatch('tstlib.TextIndex')
print "Version :", ti.Version
# ---------------- petit test sans conséquence
ti.AddText('bonjour, je suis nicolas', '1')
ti.AddText('bonjour, je suis alfred', '2')
ti.AddText('alfred hitchcock', '3')
ti.AddText('bonjour comment allez-vous ?', '3')
dump(ti, 'bonjour')
dump(ti, 'bonjour comment alfred', 0)
dump(ti, 'bonjour comment alfred', 1)
print "Saved %s !" % ti.Save(r'c:\temp\test.ti')
import requests, os, sys
from bs4 import BeautifulSoup
from win32com.client.gencache import EnsureDispatch as Dispatch
URL = "https://community.articulate.com/series/storyline-3"
HOME_URL = "https://community.articulate.com"
with requests.Session() as s:
r = s.get(URL)
html = BeautifulSoup(r.text, "html.parser")
sections = html.find("div", {
"class": "post__body series__body"
}).find_all("section", {"class": "series__section"})
message = Dispatch("CDO.Message")
message.CreateMHTMLBody(URL)
stream = Dispatch(message.GetStream())
stream.SaveToFile("main page.mht", 2)
stream.Close()
for sec in sections:
ftag = sec.find("h2")
links = sec.find("nav").find("ol").find_all("li")
fpath = ""
if ftag is not None:
fpath = ftag.string
else:
fpath = "Getting Started"
os.mkdir(fpath)
for link in links:
u = link.find("a")["href"]
fname = u.split("/")[len(u.split("/")) - 1]
message = Dispatch("CDO.Message")