Related
Folks,
I am trying to parse log file into json format.
I have a lot of logs, there is one of them
How can I parse this?
03:02:03.113 [info] ext_ref = BANK24AOS_cl_reqmarketcreditorderstate_6M8I1NT8JKYD_1591844522410384_4SGA08M8KIXQ reqid = 1253166 type = INREQ channel = BANK24AOS sid = msid_1591844511335516_KRRNBSLH2FS duration = 703.991 req_uri = marketcredit/order/state login = 77012221122 req_type = cl_req req_headers = {"accept-encoding":"gzip","connection":"close","host":"test-mobileapp-api.bank.kz","user-agent":"okhttp/4.4.1","x-forwarded-for":"212.154.169.134","x-real-ip":"212.154.169.134"} req_body = {"$sid":"msid_1591844511335516_KRRNBSLH2FS","$sid":"msid_1591844511335516_KRRNBSLH2FS","app":"bank","app_version":"2.3.2","channel":"aos","colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv","colvir_commercial_id":"-1","colvir_id":"000120.335980","openway_commercial_id":"6247520","openway_id":"6196360","$lang":"ru","ekb_id":"923243","inn":"990830221722","login":"77012221122","bank24_id":"262"} resp_body = {"task_id":"","status":"success","data":{"state":"init","applications":[{"status":"init","id":"123db561-34a3-4a8d-9fa7-03ed6377b44f","name":"Sulpak","amount":101000,"items":[{"name":"Switch CISCO x24","price":100000,"count":1,"amount":100000}]}],"segment":{"range":{"min":6,"max":36,"step":1},"payment_day":{"max":28,"min":1}}}}
Into this type of json, or any other format (but I guess json is best one)
{
"time":"03:02:03.113",
"class_req":"info",
"ext_ref":"BANK24AOS_cl_reqmarketcreditorderstate_6M8I1NT8JKYD_1591844522410384_4SGA08M8KIXQ",
"reqid":"1253166",
"type":"INREQ",
"channel":"BANK24AOS",
"sid":"msid_1591844511335516_KRRNBSLH2FS",
"duration":"703.991",
"req_uri":"marketcredit/order/state",
"login":"77012221122",
"req_type":"cl_req",
"req_headers":{
"accept-encoding":"gzip",
"connection":"close",
"host":"test-mobileapp-api.bank.kz",
"user-agent":"okhttp/4.4.1",
"x-forwarded-for":"212.154.169.134",
"x-real-ip":"212.154.169.134"
},
"req_body":{
"$sid":"msid_1591844511335516_KRRNBSLH2FS",
"$sid":"msid_1591844511335516_KRRNBSLH2FS",
"app":"bank",
"app_version":"2.3.2",
"channel":"aos",
"colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv",
"colvir_commercial_id":"-1",
"colvir_id":"000120.335980",
"openway_commercial_id":"6247520",
"openway_id":"6196360",
"$lang":"ru",
"ekb_id":"923243",
"inn":"990830221722",
"login":"77012221122",
"bank24_id":"262"
},
"resp_body":{
"task_id":"",
"status":"success",
"data":{
"state":"init",
"applications":[
{
"status":"init",
"id":"123db561-34a3-4a8d-9fa7-03ed6377b44f",
"name":"Sulpak",
"amount":101000,
"items":[
{
"name":"Switch CISCO x24",
"price":100000,
"count":1,
"amount":100000
}
]
}
],
"segment":{
"range":{
"min":6,
"max":36,
"step":1
},
"payment_day":{
"max":28,
"min":1
}
}
}
}
}
I am trying to split first whole text, but there I met another problem is to match keys to values depending on '=' sign. Also there might be some keys with empty values. For ex.:
type = INREQ channel = sid = duration = 1.333 (to get to know that there is an empty value, you need to pay attention on number of spaces. Usually there is 1 space between prev.value and next key). So this example should look like this:
{
"type":"INREQ",
"channel":"",
"sid":"",
"duration":"1.333"
}
Thanks ahead!
Here, one thing pass for duplicate key about "$sid":"msid_1591844511335516_KRRNBSLH2FS"
import re
text = """03:02:03.113 [info] ext_ref = reqid = 1253166 type = INREQ channel = BANK24AOS sid = msid_1591844511335516_KRRNBSLH2FS duration = 703.991 req_uri = marketcredit/order/state login = 77012221122 req_type = cl_req req_headers = {"accept-encoding":"gzip","connection":"close","host":"test-mobileapp-api.bank.kz","user-agent":"okhttp/4.4.1","x-forwarded-for":"212.154.169.134","x-real-ip":"212.154.169.134"} req_body = {"$sid":"msid_1591844511335516_KRRNBSLH2FS","$sid":"msid_1591844511335516_KRRNBSLH2FS","app":"bank","app_version":"2.3.2","channel":"aos","colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv","colvir_commercial_id":"-1","colvir_id":"000120.335980","openway_commercial_id":"6247520","openway_id":"6196360","$lang":"ru","ekb_id":"923243","inn":"990830221722","login":"77012221122","bank24_id":"262"} resp_body = {"task_id":"","status":"success","data":{"state":"init","applications":[{"status":"init","id":"123db561-34a3-4a8d-9fa7-03ed6377b44f","name":"Sulpak","amount":101000,"items":[{"name":"Switch CISCO x24","price":100000,"count":1,"amount":100000}]}],"segment":{"range":{"min":6,"max":36,"step":1},"payment_day":{"max":28,"min":1}}}}"""
index1 = text.index('[')
index2 = text.index(']')
new_text = 'time = '+ text[:index1-1] + ' class_req = ' + text[index1+1:index2] + text[index2+2:]
lst = re.findall(r'\S+? = |\S+? = \{.*?\} |\S+? = \{.*?\}$|\S+? = \S+? ', new_text)
res = {}
for item in lst:
key, equal, value = item.partition('=')
key, value = key.strip(), value.strip()
if value.startswith('{'):
try:
value = json.loads(value)
except:
print(value)
res[key] = value
you can try regulation in python.
here is what i write, it works for your problem.
for convenience i deleted string before "ext_ref...",you can directly truncate the raw string.
import re
import json
string = 'ext_ref = BANK24AOS_cl_reqmarketcreditorderstate_6M8I1NT8JKYD_1591844522410384_4SGA08M8KIXQ reqid = 1253166 type = INREQ channel = BANK24AOS sid = msid_1591844511335516_KRRNBSLH2FS duration = 703.991 req_uri = marketcredit/order/state login = 77012221122 req_type = cl_req req_headers = {"accept-encoding":"gzip","connection":"close","host":"test-mobileapp-api.bank.kz","user-agent":"okhttp/4.4.1","x-forwarded-for":"212.154.169.134","x-real-ip":"212.154.169.134"} req_body = {"$sid":"msid_1591844511335516_KRRNBSLH2FS","$sid":"msid_1591844511335516_KRRNBSLH2FS","app":"bank","app_version":"2.3.2","channel":"aos","colvir_token":"GExPR0lOX1BBU1NXT1JEX0NMRUFSVEVYVFNzrzh4Thk1+MjDKWl/dDu1fQPsJ6gGLSanBp41yLRv","colvir_commercial_id":"-1","colvir_id":"000120.335980","openway_commercial_id":"6247520","openway_id":"6196360","$lang":"ru","ekb_id":"923243","inn":"990830221722","login":"77012221122","bank24_id":"262"} resp_body = {"task_id":"","status":"success","data":{"state":"init","applications":[{"status":"init","id":"123db561-34a3-4a8d-9fa7-03ed6377b44f","name":"Sulpak","amount":101000,"items":[{"name":"Switch CISCO x24","price":100000,"count":1,"amount":100000}]}],"segment":{"range":{"min":6,"max":36,"step":1},"payment_day":{"max":28,"min":1}}}}'
position = re.search("req_headers",string) # position of req_headers
resp_body_pos = re.search("resp_body",string)
resp_body = string[resp_body_pos.span()[0]:]
res1 = {}
res1.setdefault(resp_body.split("=")[0],resp_body.split("=")[1])
print(res1)
before = string[:position.span()[0]]
after = string[position.span()[0]:resp_body_pos.span()[0]] # handle req_body seperately
res2 = re.findall("(\S+) = (\S+)",before)
print(res2)
res3 = re.findall("(\S+) = ({.*?})",after)
print(res3)
#res1 type: dict{'resp_body':'...'} content in resp_body
#res2 type: list[(),()..] content before req_head
#res3 type: list[(),()..] the rest content
and now you can do what you want to do with the data(.e.g. transform it into json respectively)
Hope this is helpful
I have developed a code in Python in which -in order to run the program- I need to take some arguments from the command line. But I am getting continuously the same error:
Traceback (most recent call last):
File "<string>", line 1, in <fragment>
invalid syntax: <string>, line 1, pos 16
I have the faintest idea what is wrong with my code. So, I present my code below in case someone could help me:
import QSTK.qstkutil.qsdateutil as du
import QSTK.qstkutil.tsutil as tsu
import QSTK.qstkutil.DataAccess as da
import datetime as dt
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import time
import math
import copy
import QSTK.qstkstudy.EventProfiler as ep
import csv
import sys
import argparse
def readData(li_startDate, li_endDate, ls_symbols):
#Create datetime objects for Start and End dates (STL)
dt_start = dt.datetime(li_startDate[0], li_startDate[1], li_startDate[2])
dt_end = dt.datetime(li_endDate[0], li_endDate[1], li_endDate[2])
#Initialize daily timestamp: closing prices, so timestamp should be hours=16 (STL)
dt_timeofday = dt.timedelta(hours=16)
#Get a list of trading days between the start and end dates (QSTK)
ldt_timestamps = du.getNYSEdays(dt_start, dt_end, dt_timeofday)
#Create an object of the QSTK-dataaccess class with Yahoo as the source (QSTK)
c_dataobj = da.DataAccess('Yahoo', cachestalltime=0)
#Keys to be read from the data
ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']
#Read the data and map it to ls_keys via dict() (i.e. Hash Table structure)
ldf_data = c_dataobj.get_data(ldt_timestamps, ls_symbols, ls_keys)
d_data = dict(zip(ls_keys, ldf_data))
return [d_data, dt_start, dt_end, dt_timeofday, ldt_timestamps]
def marketsim(cash,orders_file,values_file):
orders = pd.read_csv(orders_file,index_col='Date',parse_dates=True,header=None)
ls_symbols = list(set(orders['X.4'].values))
df_lastrow = len(orders) - 1
dt_start = dt.datetime(orders.get_value(0, 'X.1'),orders.get_value(0, 'X.2'),orders.get_value(0, 'X.3'))
dt_end = dt.datetime(orders.get_value(df_lastrow, 'X.1'),orders.get_value(df_lastrow, 'X.2'),orders.get_value(df_lastrow, 'X.3') + 1 )
#d_data = readData(dt_start,dt_end,ls_symbols)
#Initialize daily timestamp: closing prices, so timestamp should be hours=16 (STL)
dt_timeofday = dt.timedelta(hours=16)
#Get a list of trading days between the start and end dates (QSTK)
ldt_timestamps = du.getNYSEdays(dt_start, dt_end, dt_timeofday)
#Create an object of the QSTK-dataaccess class with Yahoo as the source (QSTK)
c_dataobj = da.DataAccess('Yahoo', cachestalltime=0)
#Keys to be read from the data
ls_keys = ['open', 'high', 'low', 'close', 'volume', 'actual_close']
#Read the data and map it to ls_keys via dict() (i.e. Hash Table structure)
df_data = c_dataobj.get_data(ldt_timestamps, ls_symbols, ls_keys)
d_data = dict(zip(ls_keys, ldf_data))
ls_symbols.append("_CASH")
trades = pd.Dataframe(index=list(ldt_timestamps[0]),columns=list(ls_symbols))
current_cash = cash
trades["_CASH"][ldt_timestamps[0]] = current_cash
current_stocks = dict()
for symb in ls_symbols:
current_stocks[symb] = 0
trades[symb][ldt_timestamps[0]] = 0
for row in orders.iterrows():
row_data = row[1]
current_date = dt.datetime(row_data['X.1'],row_data['X.2'],row_data['X.3'],16)
symb = row_data['X.4']
stock_value = d_data['close'][symb][current_date]
stock_amount = row_data['X.6']
if row_data['X.5'] == "Buy":
current_cash = current_cash - (stock_value*stock_amount)
trades["_CASH"][current_date] = current_cash
current_stocks[symb] = current_stocks[symb] + stock_amount
trades[symb][current_date] = current_stocks[symb]
else:
current_cash = current_cash + (stock_value*stock_amount)
trades["_CASH"][current_date] = current_cash
current_stocks[symb] = current_stocks[symb] - stock_amount
trades[symb][current_date] = current_stocks[symb]
#trades.fillna(method='ffill',inplace=True)
#trades.fillna(method='bfill',inplace=False)
trades.fillna(0)
#alt_cash = current_cash
#alt_cash = trades.cumsum()
value_data = pd.Dataframe(index=list(ldt_timestamps),columns=list("V"))
value_data = value_data.fillna(0)
value_data = value_data.cumsum(axis=0)
for day in ldt_timestamps:
value = 0
for sym in ls_symbols:
if sym == "_CASH":
value = value + trades[sym][day]
else:
value = calue + trades[sym][day]*d_data['close'][sym][day]
value_data["V"][day] = value
fileout = open(values_file,"w")
for row in value_data.iterrows():
file_out.writelines(str(row[0].strftime('%Y,%m,%d')) + ", " + str(row[1]["V"].round()) + "\n" )
fileout.close()
def main(argv):
if len(sys.argv) != 3:
print "Invalid arguments for marketsim.py. It should be of the following syntax: marketsim.py orders_file.csv values_file.csv"
sys.exit(0)
#initial_cash = int (sys.argv[1])
initial_cash = 1000000
ordersFile = str(sys.argv[1])
valuesFile = str(sys.argv[2])
marketsim(initial_cash,ordersFile,valuesFile)
if __name__ == "__main__":
main(sys.argv[1:])
The input I gave to the command line was:
python marketsim.py orders.csv values.csv
I guess that the problem lies either into the imports or probably into the main function(incl. the if below the def main(argv)
I have to point out that the files orders.csv and values.csv exist and are located into the same folder.
I hope have made everything clear.
So, I am looking forward to reading your answers community-mates! :D
Thank you!
I got a CSV file with numbers and I want to insert these numbers into a specific location in an url : jus after " "value": "
Here is my code :
with open('update_cases_id.csv') as p:
for lines in p:
uuid = lines.rstrip()
url_POST = "www.example.com/"
values = {}
values['return_type'] = 'retrieval'
values['format'] = 'TSV'
values['size'] = '70'
values['filters'] = '{"op":"and","content":[{"op":"in","content":{"field":"cases.case_id","value": .format(uuid)}}]}'
data = urllib.urlencode(values)
url_final = url_POST + '?' + data
req2 = urllib2.Request(url_final)
req2.add_header('cookie', cookie)
handle = urllib2.urlopen(req2)
( edited :
example input : 123456-123456-987654
example output : it s data text )
You can do this with string formatting, this should work for you:
# ...snip
values['filters'] = '{"op":"and","content":[{"op":"in","content":{"field":"cases.case_id","value":%s}]}' % uuid
# snip...
The %s will be replaced by the uuid by the % replacement operator:
>>> values = {}
>>> uuid = 1234
>>> values['filters'] = '{"op":"and","content":[{"op":"in","content":{"field":"cases.case_id","value":%s}]}' % uuid
>>> values
{'filters': '{"op":"and","content":[{"op":"in","content":{"field":"cases.case_id","value":1234}]}'}
Try to use Template.
from string import Template
params = Template('{"op":"and","content":[{"op":"in","content":{"field":"cases.case_id","value": ${your_value}}}]}')
params = params.safe_substitute(your_value=123)
# params is '{"op":"and","content":[{"op":"in","content":{"field":"cases.case_id","value":123}]}'
I have a JSON array shown below.
[
"3D3iAR9M4HDETajfD79gs9BM8qhMSq5izX",
"35xfg4UnpEJeHDo55HNwJbr1V3G1ddCuVA"
]
I would like to add a value in the form of the string (self.tx_amount_5) so I get a JSON OBJECT something like this:
{
"3D3iAR9M4HDETajfD79gs9BM8qhMSq5izX" : 100000
"35xfg4UnpEJeHDo55HNwJbr1V3G1ddCuVA" : 100000
}
The part of code that has generated the first JSON array is:
r = requests.get('http://api.blockcypher.com/v1/btc/main/addrs/A/balance')
balance = r.json()['balance']
with open("Entries#x1.csv") as f,open("winningnumbers.csv") as nums:
nums = set(imap(str.rstrip, nums))
r = csv.reader(f)
results = defaultdict(list)
for row in r:
results[sum(n in nums for n in islice(row, 1, None))].append(row[0])
self.number_matched_0 = results[0]
self.number_matched_1 = results[1]
self.number_matched_2 = results[2]
self.number_matched_3 = results[3]
self.number_matched_4 = results[4]
self.number_matched_5 = results[5]
self.number_matched_5_json = json.dumps(self.number_matched_5, sort_keys = True, indent = 4)
print(self.number_matched_5_json)
if len(self.number_matched_3) == 0:
print('Nobody matched 3 numbers')
else:
self.tx_amount_3 = int((balance*0.001)/ len(self.number_matched_3))
if len(self.number_matched_4) == 0:
print('Nobody matched 4 numbers')
else:
self.tx_amount_4 = int((balance*0.1)/ len(self.number_matched_4))
if len(self.number_matched_5) == 0:
print('Nobody matched 3 numbers')
else:
self.tx_amount_5 = int((balance*0.4)/ len(self.number_matched_5))
If I understand correctly, you can create the dictionary like this:
import json
s="""[
"3D3iAR9M4HDETajfD79gs9BM8qhMSq5izX",
"35xfg4UnpEJeHDo55HNwJbr1V3G1ddCuVA"
]"""
d = {el: self.tx_amount_5 for el in json.loads(s)}
print(d)
which produces
{'3D3iAR9M4HDETajfD79gs9BM8qhMSq5izX': 100000,
'35xfg4UnpEJeHDo55HNwJbr1V3G1ddCuVA': 100000}
How to parse string composed of n parameter and randomly sorted such as:
{ UserID : 36875; tabName : QuickAndEasy}
{ RecipeID : 1150; UserID : 36716}
{ isFromLabel : 0; UserID : 36716; type : recipe; searchWord : soup}
{ UserID : 36716; tabName : QuickAndEasy}
Ultimately I'm looking to ouput parameters in separate columns for a table.
The regex ([^{}\s:]+)\s*:\s*([^{}\s;]+) works on your examples. You need to be aware, though, that all the matches will be strings, so if you want to store 36875 as a number, you'll need to do some additional processing.
import re
regex = re.compile(
r"""( # Match and capture in group 1:
[^{}\s:]+ # One or more characters except braces, whitespace or :
) # End of group 1
\s*:\s* # Match a colon, optionally surrounded by whitespace
( # Match and capture in group 2:
[^{}\s;]+ # One or more characters except braces, whitespace or ;
) # End of group 2""",
re.VERBOSE)
You can then do
>>> dict(regex.findall("{ isFromLabel : 0; UserID : 36716; type : recipe; searchWord : soup}"))
{'UserID': '36716', 'isFromLabel': '0', 'searchWord': 'soup', 'type': 'recipe'}
Test it live on regex101.com.
lines = "{ UserID : 36875; tabName : QuickAndEasy } ", \
"{ RecipeID : 1150; UserID : 36716}", \
"{ isFromLabel : 0; UserID : 36716; type : recipe; searchWord : soup}" , \
"{ UserID : 36716; tabName : QuickAndEasy}"
counter = 0
mappedLines = {}
for line in lines:
counter = counter + 1
lineDict = {}
line = line.replace("{","")
line = line.replace("}","")
line = line.strip()
fieldPairs = line.split(";")
for pair in fieldPairs:
fields = pair.split(":")
key = fields[0].strip()
value = fields[1].strip()
lineDict[key] = value
mappedLines[counter] = lineDict
def printField(key, lineSets, comma_desired = True):
if key in lineSets:
print(lineSets[key],end="")
if comma_desired:
print(",",end="")
else:
print()
for key in range(1,len(mappedLines) + 1):
lineSets = mappedLines[key]
printField("UserID",lineSets)
printField("tabName",lineSets)
printField("RecipeID",lineSets)
printField("type",lineSets)
printField("searchWord",lineSets)
printField("isFromLabel",lineSets,False)
CSV output:
36875,QuickAndEasy,,,,
36716,,1150,,,
36716,,,recipe,soup,0
36716,QuickAndEasy,,,,
The code above was Python 3.4. You can get similar output with 2.7 by replacing the function and the last for loop with this:
def printFields(keys, lineSets):
output_line = ""
for key in keys:
if key in lineSets:
output_line = output_line + lineSets[key] + ","
else:
output_line += ","
print output_line[0:len(output_line) - 1]
fields = ["UserID", "tabName", "RecipeID", "type", "searchWord", "isFromLabel"]
for key in range(1,len(mappedLines) + 1):
lineSets = mappedLines[key]
printFields(fields,lineSets)