Develop Reference

How to fix aws lambda function logs error?

I'm trying to extract aws trust advisor data through lambda function(trigger by event scheduler) and upload to s3. However, some part of the function throws error. below is my code
##libraries
import boto3
import os
import csv
from csv import DictWriter
import time
import traceback
## bucket_name is set as env variable
bucket_name = "test-ta-reports"
fail_msg = 'Pulling Trusted Advisor data failed'
Filename = "/tmp/checks_list.csv"
obj_name = time.strftime("%Y-%m-%d-%H-%M-%S") + '/' + '.csv'
##upload to s3
def s3_upload(bucket_name, Filename, obj_name):
if obj_name is None:
obj_name = os.path.basename(Filename)
try:
s3 = boto3.client("s3", region_name="eu-west-1")
response = s3.upload_file(Filename, bucket_name, obj_name)
return True
except:
print('Data failed to upload to bucket')
traceback.print_exc()
return False
def lambda_handler(event, context):
try:
support_client = boto3.client('support', region_name='us-east-1')
ta_checks = support_client.describe_trusted_advisor_checks(language='en')
checks_list = {ctgs: [] for ctgs in list(set([checks['category'] for checks in ta_checks['checks']]))}
for checks in ta_checks['checks']:
print('Getting check:' + checks['name'] + checks['category'])
try:
check_summary = support_client.describe_trusted_advisor_check_summaries(
checkIds=[checks['id']])['summaries'][0]
if check_summary['status'] != 'not_available':
checks_list[checks['category']].append(
[checks['name'], check_summary['status'],
str(check_summary['resourcesSummary']['resourcesProcessed']),
str(check_summary['resourcesSummary']['resourcesFlagged']),
str(check_summary['resourcesSummary']['resourcesSuppressed']),
str(check_summary['resourcesSummary']['resourcesIgnored'])
])
else:
print("unable to append checks")
except:
print('Failed to get check: ' + checks['name'])
traceback.print_exc()
except:
print('Failed! Debug further.')
traceback.print_exc()
##rewrite dict to csv
with open('/tmp/checks_list.csv', 'w', newline='') as csvfile:
csv_writer = DictWriter(csvfile, fieldnames=['status','hasFlaggedResources','timestamp','resourcesSummary','categorySpecificSummary', 'checkId'])
csv_writer.writeheader()
csv_writer.writerow(check_summary)
return checks_list
if s3_upload(bucket_name, Filename, obj_name):
print("Successfully uploaded")
if __name__ == '__main__':
lambda_handler(event, context)
The error logs
unable to append checks
I'm new to Python. So, unsure of how to check for trackback stacks under else: statement. Is there any way to modify this code for getting traceback logs for the append block. Also, have i made any error in the above code. I'm unable to figure out any. PLz help

response = client.describe_trusted_advisor_check_summaries(
checkIds=[
'string',
]
)
describe_trusted_advisor_check_summaries() returns summarized results for one or more Trusted advisors. Here you are checking for the check_summary['status'] is not equal to not_avaialble i.e. alert status of the check is either "ok" (green), "warning" (yellow), "error" (red), and in that case, you are appending resourcesProcessed, resourcesFlagged, resourcesSuppressed, and resourcesIgnored to checks_list for further processing.
it's printing
unable to append checks
just because the status of the check is not_available. It is not an error log. Just deal with the case if the check status is not_available, what you should be doing?
See the documentation of describe_trusted_advisor_check_summaries. https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/support.html#Support.Client.describe_trusted_advisor_check_summaries

cookie_str = match.group(1).AttributeError: 'NoneType' object has no attribute 'group'

I am working on Stock predicting project.I want to download historical data from yahoo finance and save them in CSV format.
Since I am beginner in Python I am unable to correct the error.
My code is as follows:
import re
import urllib2
import calendar
import datetime
import getopt
import sys
import time
crumble_link = 'https://finance.yahoo.com/quote/{0}/history?p={0}'
crumble_regex = r'CrumbStore":{"crumb":"(.*?)"}'
cookie_regex = r'Set-Cookie: (.*?); '
quote_link = 'https://query1.finance.yahoo.com/v7/finance/download/{}?period1={}&period2={}&interval=1d&events=history&crumb={}'
def get_crumble_and_cookie(symbol):
link = crumble_link.format(symbol)
response = urllib2.urlopen(link)
match = re.search(cookie_regex, str(response.info()))
cookie_str = match.group(1)
text = response.read()
match = re.search(crumble_regex, text)
crumble_str = match.group(1)
return crumble_str, cookie_str
def download_quote(symbol, date_from, date_to):
time_stamp_from = calendar.timegm(datetime.datetime.strptime(date_from, "%Y-%m-%d").timetuple())
time_stamp_to = calendar.timegm(datetime.datetime.strptime(date_to, "%Y-%m-%d").timetuple())
attempts = 0
while attempts < 5:
crumble_str, cookie_str = get_crumble_and_cookie(symbol)
link = quote_link.format(symbol, time_stamp_from, time_stamp_to, crumble_str)
#print link
r = urllib2.Request(link, headers={'Cookie': cookie_str})
try:
response = urllib2.urlopen(r)
text = response.read()
print "{} downloaded".format(symbol)
return text
except urllib2.URLError:
print "{} failed at attempt # {}".format(symbol, attempts)
attempts += 1
time.sleep(2*attempts)
return ""
if __name__ == '__main__':
print get_crumble_and_cookie('KO')
from_arg = "from"
to_arg = "to"
symbol_arg = "symbol"
output_arg = "o"
opt_list = (from_arg+"=", to_arg+"=", symbol_arg+"=")
try:
options, args = getopt.getopt(sys.argv[1:],output_arg+":",opt_list)
except getopt.GetoptError as err:
print err
for opt, value in options:
if opt[2:] == from_arg:
from_val = value
elif opt[2:] == to_arg:
to_val = value
elif opt[2:] == symbol_arg:
symbol_val = value
elif opt[1:] == output_arg:
output_val = value
print "downloading {}".format(symbol_val)
text = download_quote(symbol_val, from_val, to_val)
with open(output_val, 'wb') as f:
f.write(text)
print "{} written to {}".format(symbol_val, output_val)
And the Error message that I am getting is :
File "C:/Users/Murali/PycharmProjects/generate/venv/tcl/generate2.py", line
49, in <module>
print get_crumble_and_cookie('KO')
File "C:/Users/Murali/PycharmProjects/generate/venv/tcl/generate2.py", line
19, in get_crumble_and_cookie
cookie_str = match.group(1)
AttributeError: 'NoneType' object has no attribute 'group'
So how can we resolve this problem that has popped up?

Look at these two commands:
match = re.search(cookie_regex, str(response.info()))
cookie_str = match.group(1)
The first one takes the string response.info() does a regular expression search to match cookie_regex. Then match.group(1) is supposed to take the match from it. The problem however is that if you do a print match in between these commands, you'll see that the re.search() returned nothing. This means match.group() has nothing to "group", which is why it errors out.
If you take a closer look at response.info() (you could just add a print response.info() command in your script to see it), you'll see that there's a line in response code that starts with "set-cookie:", the code after which you're trying to capture. However, you have your cookie_regex string set to look for a line with "Set-Cookie:". Note the capital letters. When I change that string to all lower-case, the error goes away:
cookie_regex = r'set-cookie: (.*?); '
I did run into another error after that, where print "downloading {}".format(symbol_val) stops because symbol_val hasn't been defined. It seems that this variable is only declared and assigned when opt[2:] == symbol_arg:. So you may want to rewrite that part to cover all cases.

Python Warning - Expected type 'Union[Integral, slice]', got 'str' instead

My code below in python is giving me a warning on the line:
some_new_object['someVar'] = cd['someVar']
The warning is
Expected type 'Union[Integral, slice]', got 'str' instead
Code:
def some_object():
return {
'someId': 0,
'someVar' : ''
}
def warn_test(in_list):
try:
new_list = []
some_new_object = some_object()
for cd in in_list:
if cd['someVar']:
new_list.append(cd)
for cd in new_list:
some_new_object['someVar'] = cd['someVar']
in_list.append(some_new_object.copy())
return in_list
except Exception:
print 'baaa'
#Main Program
new_obj = some_object()
new_obj['someId'] = 1
new_obj['someVar'] = 'Next'
new_obj2 = some_object()
new_obj2['someId'] = 1
new_obj2['someVar'] = None
new_list = []
new_list.append(new_obj)
new_list.append(new_obj2)
out_list = warn_test(new_list)
for obj in out_list:
print obj
If I change the function warn_test to this:
def warn_test(in_list):
try:
new_list = []
some_new_object = some_object()
for cd in in_list:
if cd['someVar']:
some_new_object['someVar'] = cd['someVar']
new_list.append(some_new_object.copy())
for cd in new_list:
in_list.append(cd)
return in_list
except Exception:
print 'baaa'
It gives me no warning.
Can someone help me to understand why I get the warning, and how I can access the cd['someVar'] in the second iteration without getting a warning?
I know this code is weird, I need this for a project I am working on, I made this test to share here, but it gives me the same Warning so a solution for this will fix it in my system. (No warnings is one of the Must Haves for this system)

Better late than never.
In general I have found that if variables/method returns are strongly typed these warnings go away.

Get Windows Process/File Description in Python

I have the following code so far that tells me every time a new process is created.
import wmi
c = wmi.WMI()
process_watcher = c.Win32_Process.watch_for("creation")
while True:
new_process = process_watcher()
print(new_process.Caption)
print(new_process.ExecutablePath)
This works fine, but what I'm really trying to do is get at the Processes Description because while the filename of what I'm looking for might change, the description does not. I can't find anything in Win32_Process or win32file that gets me the file description though. Does anybody know how to do this?
Thanks!

while True:
try:
new_process = process_watcher()
proc_owner = new_process.GetOwner()
proc_owner = "%s\\%s" % (proc_owner[0],proc_owner[2])
create_date = new_process.CreationDate
executable = new_process.ExecutablePath
cmdline = new_process.CommandLine
pid = new_process.ProcessId
parent_pid = new_process.parentProcessId
privileges = "N/A"
process_log_message = "%s,%s,%s,%s,%s,%s,%s,\r\n" % (create_date,proc_owner,executable,cmdline,pid,parent_pid,privileges)
print "1"
print process_log_message
log_to_file(process_log_message)
except:
print "2"
pass
Hope this helps :)

"Not implemented" Exception when using pywin32 to control Adobe Acrobat

I have written a script in python using pywin32 to save pdf files to text that up until recently was working fine. I use similar methods in Excel. The code is below:
def __pdf2Txt(self, pdf, fileformat="com.adobe.acrobat.accesstext"):
outputLoc = os.path.dirname(pdf)
outputLoc = os.path.join(outputLoc, os.path.splitext(os.path.basename(pdf))[0] + '.txt')
try:
win32com.client.gencache.EnsureModule('{E64169B3-3592-47d2-816E-602C5C13F328}', 0, 1, 1)
adobe = win32com.client.DispatchEx('AcroExch.App')
pdDoc = win32com.client.DispatchEx('AcroExch.PDDoc')
pdDoc.Open(pdf)
jObject = pdDoc.GetJSObject()
jObject.SaveAs(outputLoc, "com.adobe.acrobat.accesstext")
except:
traceback.print_exc()
return False
finally:
del jObject
pdDoc.Close()
del pdDoc
adobe.Exit()
del adobe
However this code has suddenly stopped working and I get the following output:
Traceback (most recent call last):
File "C:\Documents and Settings\ablishen\workspace\HooverKeyCreator\src\HooverKeyCreator.py", line 38, in __pdf2Txt
jObject.SaveAs(outputLoc, "com.adobe.acrobat.accesstext")
File "C:\Python27\lib\site-packages\win32com\client\dynamic.py", line 505, in __getattr__
ret = self._oleobj_.Invoke(retEntry.dispid,0,invoke_type,1)
com_error: (-2147467263, 'Not implemented', None, None)
False
I have similar code written in VB that works correctly so I'm guessing that it has something to do with the COM interfaces not binding to the appropriate functions correctly? (my COM knowledge is patchy).

Blish, this thread holds the key to the solution you are looking for: https://mail.python.org/pipermail/python-win32/2002-March/000260.html
I admit that the post above is not the easiest to find (probably because Google scores it low based on the age of the content?).
Specifically, applying this piece of advice will get things running for you: https://mail.python.org/pipermail/python-win32/2002-March/000265.html
For reference, the complete piece of code that does not require you to manually patch dynamic.py (snippet should run pretty much out of the box):
# gets all files under ROOT_INPUT_PATH with FILE_EXTENSION and tries to extract text from them into ROOT_OUTPUT_PATH with same filename as the input file but with INPUT_FILE_EXTENSION replaced by OUTPUT_FILE_EXTENSION
from win32com.client import Dispatch
from win32com.client.dynamic import ERRORS_BAD_CONTEXT
import winerror
# try importing scandir and if found, use it as it's a few magnitudes of an order faster than stock os.walk
try:
from scandir import walk
except ImportError:
from os import walk
import fnmatch
import sys
import os
ROOT_INPUT_PATH = None
ROOT_OUTPUT_PATH = None
INPUT_FILE_EXTENSION = "*.pdf"
OUTPUT_FILE_EXTENSION = ".txt"
def acrobat_extract_text(f_path, f_path_out, f_basename, f_ext):
avDoc = Dispatch("AcroExch.AVDoc") # Connect to Adobe Acrobat
# Open the input file (as a pdf)
ret = avDoc.Open(f_path, f_path)
assert(ret) # FIXME: Documentation says "-1 if the file was opened successfully, 0 otherwise", but this is a bool in practise?
pdDoc = avDoc.GetPDDoc()
dst = os.path.join(f_path_out, ''.join((f_basename, f_ext)))
# Adobe documentation says "For that reason, you must rely on the documentation to know what functionality is available through the JSObject interface. For details, see the JavaScript for Acrobat API Reference"
jsObject = pdDoc.GetJSObject()
# Here you can save as many other types by using, for instance: "com.adobe.acrobat.xml"
jsObject.SaveAs(dst, "com.adobe.acrobat.accesstext")
pdDoc.Close()
avDoc.Close(True) # We want this to close Acrobat, as otherwise Acrobat is going to refuse processing any further files after a certain threshold of open files are reached (for example 50 PDFs)
del pdDoc
if __name__ == "__main__":
assert(5 == len(sys.argv)), sys.argv # <script name>, <script_file_input_path>, <script_file_input_extension>, <script_file_output_path>, <script_file_output_extension>
#$ python get.txt.from.multiple.pdf.py 'C:\input' '*.pdf' 'C:\output' '.txt'
ROOT_INPUT_PATH = sys.argv[1]
INPUT_FILE_EXTENSION = sys.argv[2]
ROOT_OUTPUT_PATH = sys.argv[3]
OUTPUT_FILE_EXTENSION = sys.argv[4]
# tuples are of schema (path_to_file, filename)
matching_files = ((os.path.join(_root, filename), os.path.splitext(filename)[0]) for _root, _dirs, _files in walk(ROOT_INPUT_PATH) for filename in fnmatch.filter(_files, INPUT_FILE_EXTENSION))
# patch ERRORS_BAD_CONTEXT as per https://mail.python.org/pipermail/python-win32/2002-March/000265.html
global ERRORS_BAD_CONTEXT
ERRORS_BAD_CONTEXT.append(winerror.E_NOTIMPL)
for filename_with_path, filename_without_extension in matching_files:
print "Processing '{}'".format(filename_without_extension)
acrobat_extract_text(filename_with_path, ROOT_OUTPUT_PATH, filename_without_extension, OUTPUT_FILE_EXTENSION)
I have tested this on WinPython x64 2.7.6.3, Acrobat X Pro

makepy.py is a script that comes with the win32com python package.
Running it for your installation "wires" python into the COM/OLE object in Windows. The following is an excerpt of some code I used to talk to Excel and do some stuff in it. This example gets the name of sheet 1 in the current workbook. It automatically runs makepy if it has an exception:
import win32com;
import win32com.client;
from win32com.client import selecttlb;
def attachExcelCOM():
makepyExe = r'python C:\Python25\Lib\site-packages\win32com\client\makepy.py';
typeList = selecttlb.EnumTlbs();
for tl in typeList:
if (re.match('^Microsoft.*Excel.*', tl.desc, re.IGNORECASE)):
makepyCmd = "%s -d \"%s\"" % (makepyExe, tl.desc);
os.system(makepyCmd);
# end if
# end for
# end def
def getSheetName(sheetNum):
try:
xl = win32com.client.Dispatch("Excel.Application");
wb = xl.Workbooks.Item(sheetNum);
except Exception, detail:
print 'There was a problem attaching to Excel, refreshing connect config...';
print Exception, str(detail);
attachExcelCOM();
try:
xl = win32com.client.Dispatch("Excel.Application");
wb = xl.Workbooks.Item(sheetNum);
except:
print 'Could not attach to Excel...';
sys.exit(-1);
# end try/except
# end try/except
wsName = wb.Name;
if (wsName == 'PERSONAL.XLS'):
return( None );
# end if
print 'The target worksheet is:';
print ' ', wsName;
print 'Is this correct? [Y/N]',;
answer = string.strip( sys.stdin.readline() );
answer = answer.upper();
if (answer != 'Y'):
print 'Sheet not identified correctly.';
return(None);
# end if
return( (wb, wsName) );
# end def
# -- Main --
sheetInfo = getSheetName(sheetNum);
if (sheetInfo == None):
print 'Sheet not found';
sys.exit(-1);
else:
(wb, wsName) = sheetInfo;
# end if