Develop Reference

syntax error for writing a variable in a script

dump.pbd='pdb' + pdbFile + '_' + 'res' + residMin + '_' residMax + '.pdb'
the program keep giving me syntax error when I run it.
import re
import sys
import os
import time
from sys import argv
import xmltodict
if len(sys.argv) < 3:
message = '\n Get protein file in the form of pdf file from pdb website. \n\n Usage: '+sys.argv[0] + ' [4-letter PDBid] [resid range] \n' + ' Example: ' + sys.argv[0] + ' 2rh1 53-71\n' + ' Output File: pdb2rh1_res53-71.pdb'
print (message)
exit()
pdbID=sys.argv[1]
residRange=sys.argv[2]
residData=residRange.split('-')
residMin=int(residData[0])
residMax=int(residData[1])
twoletter=pdbID[1:3]
xmlfile=pdbID + '.xml'
pdbgzfile=pdbID + '.pdb.gz'
pdbFile=pdbID+'.pdb'
dump.pbd='pdb' + pdbFile + '_' + 'res' + residMin + '_' residMax + '.pdb'
wgetcom='wget https://files.rcsb.org/view/'+pdbFile+' -O '+pdbFile
print(wgetcom)
os.system(wgetcom)
f = open (pdbFile,'r')
k = 0
rc = 0
data = f.readlines()
g = open (dump.pdb, 'w')
for linedata in data:
line=linedata.strip()
words = line.split()
if(words[0] == 'ATOM'):
k=k+1
words[5]=int(line[22:26].strip())
if(words[5] in range(residMin,residMax+1)):
g.write(linedata)
for i in words:
if(i=='CA'):
rc = rc+1
print(rc)
the code is not working because it is giving me a syntax error for line number 22 that states dump.pbd='pdb' + pdbFile + '' + 'res' + residMin + '' residMax + '.pdb'. so can you please help me with that?
Thanks so much on advance!

You've forgotten to add a + sign.
This line should work: dump.pbd='pdb' + pdbFile + '' + 'res' + residMin + '' + residMax + '.pdb'
There must be a + sign between '_' and residMax as this is the Python concatenating strings syntax.

I have a Pandas code error, but the solution is uncleared

I am a newbie to Python, and I have been dooing this Pandas code for reading malware IP addresses, this is the code and below is the error.
import os
from datetime import datetime, date, timedelta
import subprocess
import pyjq
import pandas as pd
# Initializes the variables for the directories
HomeDir = "Users/kiya/Downloads/"
ScriptDir = HomeDir + "pan-python-0.12.0 2"
ResultDir = HomeDir + "techscroll/"
# Create the dates
ToDay = datetime.now().strftime('%Y%m%d')
# checkDATE = (date.today() - timedelta(1)).strfttime('%Y%m%d')
ResultFile = "Test"
CheckDATE = "Test"
NOWDATE = "TEST"
# Run the panafpi
subprocess.check_output('python ' + ScriptDir + '/bin/panafapi.py -K secretkey --samples -j -r "{\"query\":{\"operator\":\"all\",\"children\":[{\"field\":\"alias.ip_address\",\"operator\":\"contains\",\"value\":\"' + ResultFile + '\"},{\"operator\":\"any\",\"children\":[{\"field\":\"sample.update_date\",\"operator\":\"is in the range\",\"value\":[\"' + CheckDATE + 'T00:00:00\",\"$' + NOWDATE + 'T23:59:59\"]},{\"field\":\"sample.create_date\",\"operator\":\"is in the range\",\"value\":[\"' + CheckDATE + 'T00:00:00\",\"' + NOWDATE + 'T23:59:59\"]},{\"operator\":\"any\",\"children\":[{\"field\":\"sample.malware\",\"operator\":\"is\",\"value\":1},{\"field\":\"sample.malware\",\"operator\":\"is\",\"value\":4}]}]}]},\"scope\":\"global\",\"size\":1,\"from\":0,\"sort\":{\"create_date\":{\"order\":\"desc\"}}}" > ' + ResultDir + 'srciplist-' + ToDay + '.json', shell=True)
# Using pyjq to filter
filteredResultData = pyjq.all('.hits[]._source | .create_date + "," + .sha256')
# Save the JSON file to comma-separated file
pd.to_csv(ResultDir + "/srciplist-" + ToDay + ".csv", sep=",")
error:
/bin/sh: Users/kiya/Downloads/techscroll/srciplist-20180125.json: No such file or directory
Traceback (most recent call last):
File "/Users/mani/Downloads/tester (1).py", line 22, in <module>
subprocess.check_output('python ' + ScriptDir + '/bin/panafapi.py -K secretkey --samples -j -r "{\"query\":{\"operator\":\"all\",\"children\":[{\"field\":\"alias.ip_address\",\"operator\":\"contains\",\"value\":\"' + ResultFile + '\"},{\"operator\":\"any\",\"children\":[{\"field\":\"sample.update_date\",\"operator\":\"is in the range\",\"value\":[\"' + CheckDATE + 'T00:00:00\",\"$' + NOWDATE + 'T23:59:59\"]},{\"field\":\"sample.create_date\",\"operator\":\"is in the range\",\"value\":[\"' + CheckDATE + 'T00:00:00\",\"' + NOWDATE + 'T23:59:59\"]},{\"operator\":\"any\",\"children\":[{\"field\":\"sample.malware\",\"operator\":\"is\",\"value\":1},{\"field\":\"sample.malware\",\"operator\":\"is\",\"value\":4}]}]}]},\"scope\":\"global\",\"size\":1,\"from\":0,\"sort\":{\"create_date\":{\"order\":\"desc\"}}}" > ' + ResultDir + 'srciplist-' + ToDay + '.json', shell=True)
File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/subprocess.py", line 336, in check_output
**kwargs).stdout
File "/usr/local/Cellar/python3/3.6.2/Frameworks/Python.framework/Versions/3.6/lib/python3.6/subprocess.py", line 418, in run
output=stdout, stderr=stderr)
subprocess.CalledProcessError: Command 'python Users/kiya/Downloads/pan-python-0.12.0 2/bin/panafapi.py -K secret key --samples -j -r "{"query":{"operator":"all","children":[{"field":"alias.ip_address","operator":"contains","value":"Test"},{"operator":"any","children":[{"field":"sample.update_date","operator":"is in the range","value":["TestT00:00:00","$TESTT23:59:59"]},{"field":"sample.create_date","operator":"is in the range","value":["TestT00:00:00","TESTT23:59:59"]},{"operator":"any","children":[{"field":"sample.malware","operator":"is","value":1},{"field":"sample.malware","operator":"is","value":4}]}]}]},"scope":"global","size":1,"from":0,"sort":{"create_date":{"order":"desc"}}}" > Users/kiya/Downloads/techscroll/srciplist-20180125.json' returned non-zero exit status 1.

os.rename returning winerror 2

I'm trying to a script to rename to the date that it was sent as an email(which is the first part of the script but doesn't matter for this part) then to rename, and sort it into a 'Complete' folder. This is what my code looks like
Edit - I have all the imported stuff way up at the top and i didnt show it, but i assume i have the right stuff imported if you would like to see just ask
dir5 = "C:\\Users\\Michael D\\Documents\\Test\\AmLit"
dir6 = "C:\\Users\\Michael D\\Documents\\Test\\History"
dir7 = "C:\\Users\\Michael D\\Documents\\Test\\MultiLit"
dir8 = "C:\\Users\\Michael D\\Documents\\Test\\Physics"
dir5_final = "C:\\Users\\Michael D\\Documents\\TestMove\\AmLit"
dir6_final = "C:\\Users\\Michael D\\Documents\\TestMove\\History"
dir7_final = "C:\\Users\\Michael D\\Documents\\TestMove\\MultiLit"
dir8_final = "C:\\Users\\Michael D\\Documents\\TestMove\\Physics"
now = datetime.datetime.now()
now1 = (str(now.day) + '/' + str(now.month) + '/' + str(now.year))
dir5_files = os.listdir(dir5)
dir6_files = os.listdir(dir6)
dir7_files = os.listdir(dir7)
dir8_files = os.listdir(dir8)
for f in dir5_files:
if (f.startswith("A") or f.startswith("a")):
os.rename(f, now1 + " " + f)
but i keep getting this error
RESTART: C:/Users/Michael D/Documents/Coding/Schoolwork Email/Email Sender Beta 1.7.21.9.16.py
Traceback (most recent call last):
File "C:/Users/Michael D/Documents/Coding/Schoolwork Email/Email Sender Beta 1.7.21.9.16.py", line 148, in <module>
os.rename(f, now1 + " " + f)
FileNotFoundError: [WinError 2] The system cannot find the file specified: 'A Test.txt' -> '21/9/2016 A Test.txt'
any thoughts as to what I'm doing wrong?

2 errors:
You are not in the current directory
You just cannot have slashes in the names. The filesystem won't allow it as it is (alternately) used to separate path parts.
First, generate the date directly with underscores:
now1 = (str(now.day) + '_' + str(now.month) + '_' + str(now.year))
Then replace
os.rename(f, now1 + " " + f)
by
os.rename(os.path.join(dir5,f), os.path.join(dir5,now1.replace("/","_") + " " + f))
and A Test.txt would be renamed to 21_9_2016 A Test.txt in the directory you specified.

Script Loop through files in directory

I have the following code which creates the txt file I require from a shp.file with the data I need. I have a folder called profiles containing a few number of shape files named (profil1.shp, profil2.shp, profil3.shp etc.). I was wondering how to create a loop so that the script creates for each file a txt file with the same name (eg. for profil1.shp create profil1.txt, profil2.shp create profil2.txt and so on).
import ogr, os, sys, osr
os.chdir('..\profiles')
file = open('profil1.txt', 'w')
driver = ogr.GetDriverByName('ESRI Shapefile')
datasource = driver.Open('profil1.shp', 0)
if datasource is None:
print 'Could not open file'
sys.exit(1)
layer = datasource.GetLayer()
feature = layer.GetNextFeature()
while feature:
id = feature.GetFieldAsString('ID')
Distanta = feature.GetFieldAsString('DIST')
Z = feature.GetFieldAsString('Z')
geom = feature.GetGeometryRef()
x = str(geom.GetX())
y = str(geom.GetY())
file.write(id + " " + Distanta + " " + "[X]:" + " " + x + ' ' + '[Y]:' + " " + y + " " + " " + "[Z]" + Z + " " + "\n")
feature.Destroy()
feature = layer.GetNextFeature()
datasource.Destroy()
file.close()
edit: the code is returning a Could not open file.Photo of the folder containing the files and their respective names. Safe to assume I am doing something wrong.
import ogr, os, sys, osr,os.path
os.chdir = ('C:\Users\Andrei\Desktop\profil3')
l = os.listdir('C:\Users\Andrei\Desktop\profil3')
for i in l:
if i.endswith('.shp'):
s1 = s.split('.')[0] + '.txt'
file = open(s1, 'w')
driver = ogr.GetDriverByName('ESRI Shapefile')
datasource = driver.Open(i, 0)
if datasource is None:
print 'Could not open file'
sys.exit(1)
layer = datasource.GetLayer()
feature = layer.GetNextFeature()
while feature:
id = feature.GetFieldAsString('ID')
Distanta = feature.GetFieldAsString('DIST')
Z = feature.GetFieldAsString('Z')
geom = feature.GetGeometryRef()
x = str(geom.GetX())
y = str(geom.GetY())
file.write(id + " " + Distanta + " " + "[X]:" + " " + x + ' ' + '[Y]:' + " " + y + " " + " " + "[Z]" + Z + " " + "\n")
feature.Destroy()
feature = layer.GetNextFeature()
datasource.Destroy()
file.close()

You can use os.listdir() to list the files and folders in the current directory.
This returns a list of all files in the current directory (or the directory given to it as parameter , if no parameter is specified it checks the current directory) .
Then you can check for files with the name ending with .shp using string.endswith() function and then use that to create your new files.
Example of a small portion -
import os , os.path
l = os.listdir()
for i in l:
if i.endswith('.shp'):
s1 = s.split('.')[0] + '.txt'
At the end s1 would contain the file with extension as .txt .
Then you can do your logic on this file, and keep on doing like this.
Full code would look something like -
import ogr, os, sys, osr,os.path
os.chdir('..\profiles')
l = os.listdir()
for i in l:
if i.endswith('.shp'):
s1 = s.split('.')[0] + '.txt'
file = open(s1, 'w')
driver = ogr.GetDriverByName('ESRI Shapefile')
datasource = driver.Open(i, 0)
if datasource is None:
print 'Could not open file'
sys.exit(1)
layer = datasource.GetLayer()
feature = layer.GetNextFeature()
while feature:
id = feature.GetFieldAsString('ID')
Distanta = feature.GetFieldAsString('DIST')
Z = feature.GetFieldAsString('Z')
geom = feature.GetGeometryRef()
x = str(geom.GetX())
y = str(geom.GetY())
file.write(id + " " + Distanta + " " + "[X]:" + " " + x + ' ' + '[Y]:' + " " + y + " " + " " + "[Z]" + Z + " " + "\n")
feature.Destroy()
feature = layer.GetNextFeature()
datasource.Destroy()
file.close()
A better way of openning files, etc is using with statement. Look up its tutorial here.

Scripting Python for Linux commands

I have a question. I have been really trying to learn Python. For a project, I want to make an ncurses GUI for my backup server. My backup server runs rdiff-backup, and I want to have the ncurses take in variable names and plug them into my script. I have been trying to do a lot of reading so I don't ask dumb questions.
Here is my function for running the script:
def runScript():
# Cannot concatenate 'str' and 'list' objects
#script = rdiff + rdiffArgs
script = rdiff + ' ' + rdiffVerbosity + ' ' + rdiffStatistics \
+ ' ' + clientName + '#' + clientHost + '::' + clientDir \
+ ' ' + serverDir
os.system(script)
What I originally thought would be neat was to add all the variables into a list, so I could just run say
script = rdiff + rdiffArgs
Is there a better way to do this without all the space concatenation?
Thanks for your assistance
EDIT: Let me post the whole script so far. I wasn't very clear and I really appreciate your help and patience
#!/usr/bin/env python
import os
import smtplib
# Global variables
rdiff = '/usr/bin/rdiff-backup'
rdiffVerbosity = '-v5'
rdiffStatistics = '--print-statistics'
emailSmtp = 'smtp.gmail.com'
smtpPort = '465'
emailUsername = 'reports'
emailPassword = '3kc9dl'
emailTo = 'user#domain.com'
emailFrom = 'internal#domain.com'
serverName = 'root'
serverHost = 'SV-Datasafe'
serverDir = '/srv/backup/SV-Samba01'
clientName = 'root'
clientHost = 'SV-Samba01'
clientDir = '/srv'
rdiffArgs = rdiffArgs = [rdiffVerbosity, rdiffStatistics, \
clientName + '#' + clientHost + '::' \
+clientDir + ' ' + serverDir]
time = ''
dateStamp = datetime.now()
def sendEmail():
subject = dateStamp + clientName
body = clientDir + ' on ' + clientHost + ' backed up to ' + serverName + \
' in the directory ' + serverDir + ' on ' + dateStamp
message = """\
From: %s
To: %s
Subject: %s
%s
""" % (emailFrom, emailTo, subject, body)
deliverEmail = smtplib.SMTP(emailSmtp, port=smtpPort)
deliverEmail.login(emailUsername, emailPassword)
def runScript():
# Cannot concatenate 'str' and 'list' objects
#script = rdiff + rdiffArgs
script = rdiff + ' ' + rdiffVerbosity + ' ' + rdiffStatistics \
+ ' ' + clientName + '#' + clientHost + '::' + clientDir \
+ ' ' + serverDir
os.system(script)
# TODO:: Logging

you can use format specifiers
def runScript():
script = "%s %s %s#%s %s::%s %s" %(rdiff,rdiffVerbosity,rdiffStatistics,clientName,clientHost,clientDir,serverDir)
os.system(script)
or say your rdiffArgs is already in a list
rdiffArgs = [rdiffVerbosity,rdiffStatistics,clientName,clientHost,clientDir,serverDir]
you can join them with a space
rdiffArgs = ' '.join(rdiffArgs)
lastly, just so you might want to know, you can import rdiff in your script , since rdiff-backup is written in Python
from rdiff_backup.Main import Main as backup
task=['/etc', '/tmp/backup']
backup(task)
the above backs up /etc/ to /tmp/backup. That way, you don't have to make system call to rdiff-backup. Of course, this is up to you. making system call is sometimes easier

try to use subprocess module and pass arguments as list e.g.
client = clientName + '#' + clientHost + '::' + clientDir
cmd = [rdiff, rdiffVerbosity, rdiffStatistics, client , serverDir]
p = Popen(cmd ", shell=True)
print os.waitpid(p.pid, 0)[1]
or if have args already as list use something like this
cmd = [rdiff] + args

You join paths using os.path.join
You concatenate strings like so: "".join(['a', 'b']) or ", ".join(['c', 'd'])
Which part is difficult? I am not sure I understand the question 100%
Is this it?
script = rdiff + " ".join(rdiffArgs)