I'm new to python and I've write a simple code that reading lines from serial port and than write those lines to a text file. No errores occured, but the serial masseges did not appear in the text.
the code:
import serial
ser = serial.Serial('COM32', baudrate=115200, parity=serial.PARITY_NONE, stopbits=serial.STOPBITS_ONE,
bytesize=serial.EIGHTBITS, xonxoff=1)
text = open("temptext1.txt", "a+")
while 1:
read_line = ser.readline()
print read_line
text.write(read_line)
Thnaks for the helpers, i siriously dont have a clue how to debug this.
Try below code.
import serial
import io
def getSerialLogs(comport, fileName='SerialLog.txt', baudrate=115200):
ser = serial.Serial(comport, baudrate, xonxoff =True, timeout=1)
sio = io.TextIOWrapper(io.BufferedRWPair(ser, ser, 1), encoding="utf-8")
with open(fileName, 'a') as f:
while ser.isOpen():
datastring = sio.readline()
f.write(datastring)
Related
I have a text file to ingest but, some of the text fields os this file are coming with CR char in it. The official line break is LF so I figured I could replace all CR and normalize to files.
But I'm triyng to do this for a week now with no good results.
What I tried so far is using replaceText processor with several configurations. Line by line, entire text, already tried "\r", "\\r", "[\r]" but nothing seemed to work.
Do you have any suggestions or experience to share?
You can achieve same with ExecuteScript processor, where you can implement your custom cleaning logic with less limitations. Refer below python snippet to start with,
from org.apache.commons.io import IOUtils
from java.nio.charset import StandardCharsets
from org.apache.nifi.processor.io import StreamCallback
from org.apache.nifi.processors.script import ExecuteScript
from org.python.core.util.FileUtil import wrap
from io import StringIO
import re
# Define a subclass of StreamCallback for use in session.write()
class PyStreamCallback(StreamCallback):
def __init__(self):
pass
def process(self, inputStream, outputStream):
with wrap(inputStream) as f:
lines = f.readlines()
outer_new_value_list = []
is_header_row = True
for row in lines:
if is_header_row:
is_header_row = False
outer_new_value_list.append(row)
continue
char_list = list(row.strip())
for position, char in enumerate(char_list):
// put your custom cleaning logic here
if char == '\\' or char == '^' or char == '"' or char == '~' :
replace_char = '\\' + char
char_list[position] = replace_char
new_data_line = ''.join([str(elem) for elem in char_list])
outer_new_value_list.append(new_data_line + '\r\n')
with wrap(outputStream, 'w') as filehandle:
filehandle.writelines("%s" % line for line in outer_new_value_list)
# end class
flowFile = session.get()
if (flowFile != None):
flowFile = session.write(flowFile, PyStreamCallback())
session.transfer(flowFile, ExecuteScript.REL_SUCCESS)
# implicit return at the end
After a week of attempts, i was able to replace the carriage return in my file with a simple replacetext processor. Here is the print for you to try if needed.
i have a written piece of code of around 100 lines which is printing some output of around 20 lines. How can I print this output in GUI ??
I just wrote this implementation for a project of mine, its in Python 2.7 but it should be easy to adapt it to Python 3.6
#!/usr/lib/python2.7/
# -*- coding: utf-8 -*-
from Tkinter import *
import ttk, collections
class GUI():
def __init__(self) :
self.window = Tk()
def draw(self) :
self.root = Frame(self.window,padx=15,pady=15,width=800,height=200)
self.root.grid(column=0,row=0)
self.drawConsole()
self.window.mainloop()
def drawConsole(self) :
self.consoleFrame = Frame(self.root, padx=15)
self.consoleFrame.grid(column=0,row=4,sticky="EW",pady=10)
self.logTest = Text(self.consoleFrame, height=15, state='disabled', wrap='word',background='black',foreground='yellow')
self.logTest.grid(column=0,row=0,sticky="EW")
self.scrollbar = Scrollbar(self.consoleFrame, orient=VERTICAL,command=self.logTest.yview)
self.scrollbar.grid(column=1,row=0,sticky=(N,S))
self.logTest['yscrollcommand'] = self.scrollbar.set
def writeToLog(self, msg):
numlines = self.logTest.index('end - 1 line').split('.')[0]
self.logTest['state'] = 'normal'
if numlines==24:
self.logTest.delete(1.0, 2.0)
if self.logTest.index('end-1c')!='1.0':
self.logTest.insert('end', '\n')
self.logTest.insert('end', msg)
self.logTest.see(END)
self.logTest['state'] = 'disabled'
if __name__ == "__main__":
gui = GUI()
gui.draw()
gui.writeToLog("Hello World")
I am a Python 3.x guy, but when it comes to tkinter, you can set labels with variables instead of using print(). So to get it on the GUI, you want to set labels with variables. This would look something like this:
from tkinter import *
window = Tk()
variable = StringVar()
variable.set(data_to_console) #You can use a variable with a string here or any string
label = Label(window, textvariable=variable)
label.grid(row=x, column=y)
So you take the strings that would be output into the console and use .set() to put it into a String Variable that tkinter can use. The Labels will allow for the data that would be printed to be in the GUI. Hope this helps!
I am using tesseract to perform OCR on screengrabs. I have an app using a tkinter window leveraging self.after in the initialization of my class to perform constant image scrapes and update label, etc values in the tkinter window. I have searched for multiple days and can't find any specific examples how to leverage CREATE_NO_WINDOW with Python3.6 on a Windows platform calling tesseract with pytesseract.
This is related to this question:
How can I hide the console window when I run tesseract with pytesser
I have only been programming Python for 2 weeks and don't understand what/how to perform the steps in the above question. I opened up the pytesseract.py file and reviewed and found the proc = subprocess.Popen(command, stderr=subproces.PIPE) line but when I tried editing it I got a bunch of errors that I couldn't figure out.
#!/usr/bin/env python
'''
Python-tesseract. For more information: https://github.com/madmaze/pytesseract
'''
try:
import Image
except ImportError:
from PIL import Image
import os
import sys
import subprocess
import tempfile
import shlex
# CHANGE THIS IF TESSERACT IS NOT IN YOUR PATH, OR IS NAMED DIFFERENTLY
tesseract_cmd = 'tesseract'
__all__ = ['image_to_string']
def run_tesseract(input_filename, output_filename_base, lang=None, boxes=False,
config=None):
'''
runs the command:
`tesseract_cmd` `input_filename` `output_filename_base`
returns the exit status of tesseract, as well as tesseract's stderr output
'''
command = [tesseract_cmd, input_filename, output_filename_base]
if lang is not None:
command += ['-l', lang]
if boxes:
command += ['batch.nochop', 'makebox']
if config:
command += shlex.split(config)
proc = subprocess.Popen(command, stderr=subprocess.PIPE)
status = proc.wait()
error_string = proc.stderr.read()
proc.stderr.close()
return status, error_string
def cleanup(filename):
''' tries to remove the given filename. Ignores non-existent files '''
try:
os.remove(filename)
except OSError:
pass
def get_errors(error_string):
'''
returns all lines in the error_string that start with the string "error"
'''
error_string = error_string.decode('utf-8')
lines = error_string.splitlines()
error_lines = tuple(line for line in lines if line.find(u'Error') >= 0)
if len(error_lines) > 0:
return u'\n'.join(error_lines)
else:
return error_string.strip()
def tempnam():
''' returns a temporary file-name '''
tmpfile = tempfile.NamedTemporaryFile(prefix="tess_")
return tmpfile.name
class TesseractError(Exception):
def __init__(self, status, message):
self.status = status
self.message = message
self.args = (status, message)
def image_to_string(image, lang=None, boxes=False, config=None):
'''
Runs tesseract on the specified image. First, the image is written to disk,
and then the tesseract command is run on the image. Tesseract's result is
read, and the temporary files are erased.
Also supports boxes and config:
if boxes=True
"batch.nochop makebox" gets added to the tesseract call
if config is set, the config gets appended to the command.
ex: config="-psm 6"
'''
if len(image.split()) == 4:
# In case we have 4 channels, lets discard the Alpha.
# Kind of a hack, should fix in the future some time.
r, g, b, a = image.split()
image = Image.merge("RGB", (r, g, b))
input_file_name = '%s.bmp' % tempnam()
output_file_name_base = tempnam()
if not boxes:
output_file_name = '%s.txt' % output_file_name_base
else:
output_file_name = '%s.box' % output_file_name_base
try:
image.save(input_file_name)
status, error_string = run_tesseract(input_file_name,
output_file_name_base,
lang=lang,
boxes=boxes,
config=config)
if status:
errors = get_errors(error_string)
raise TesseractError(status, errors)
f = open(output_file_name, 'rb')
try:
return f.read().decode('utf-8').strip()
finally:
f.close()
finally:
cleanup(input_file_name)
cleanup(output_file_name)
def main():
if len(sys.argv) == 2:
filename = sys.argv[1]
try:
image = Image.open(filename)
if len(image.split()) == 4:
# In case we have 4 channels, lets discard the Alpha.
# Kind of a hack, should fix in the future some time.
r, g, b, a = image.split()
image = Image.merge("RGB", (r, g, b))
except IOError:
sys.stderr.write('ERROR: Could not open file "%s"\n' % filename)
exit(1)
print(image_to_string(image))
elif len(sys.argv) == 4 and sys.argv[1] == '-l':
lang = sys.argv[2]
filename = sys.argv[3]
try:
image = Image.open(filename)
except IOError:
sys.stderr.write('ERROR: Could not open file "%s"\n' % filename)
exit(1)
print(image_to_string(image, lang=lang))
else:
sys.stderr.write('Usage: python pytesseract.py [-l lang] input_file\n')
exit(2)
if __name__ == '__main__':
main()
The code I am leveraging is similar to the example in the similar question:
def get_string(img_path):
# Read image with opencv
img = cv2.imread(img_path)
# Convert to gray
img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# Apply dilation and erosion to remove some noise
kernel = np.ones((1, 1), np.uint8)
img = cv2.dilate(img, kernel, iterations=1)
img = cv2.erode(img, kernel, iterations=1)
# Write image after removed noise
cv2.imwrite(src_path + "removed_noise.png", img)
# Apply threshold to get image with only black and white
# Write the image after apply opencv to do some ...
cv2.imwrite(src_path + "thres.png", img)
# Recognize text with tesseract for python
result = pytesseract.image_to_string(Image.open(src_path + "thres.png"))
return result
When it gets to the following line, there is a flash of a black console window for less than a second and then it closes when it runs the command.
result = pytesseract.image_to_string(Image.open(src_path + "thres.png"))
Here is the picture of the console window:
Program Files (x86)_Tesseract
Here is what is suggested from the other question:
You're currently working in IDLE, in which case I don't think it
really matters if a console window pops up. If you're planning to
develop a GUI app with this library, then you'll need to modify the
subprocess.Popen call in pytesser.py to hide the console. I'd first
try the CREATE_NO_WINDOW process creation flag. – eryksun
I would greatly appreciate any help for how to modify the subprocess.Popen call in the pytesseract.py library file using CREATE_NO_WINDOW. I am also not sure of the difference between pytesseract.py and pytesser.py library files. I would leave a comment on the other question to ask for clarification but I can't until I have more reputation on this site.
I did more research and decided to learn more about subprocess.Popen:
Documentation for subprocess
I also referenced the following articles:
using python subprocess.popen..can't prevent exe stopped working prompt
I changed the original line of code in pytesseract.py:
proc = subprocess.Popen(command, stderr=subprocess.PIPE)
to the following:
proc = subprocess.Popen(command, stderr=subprocess.PIPE, creationflags = CREATE_NO_WINDOW)
I ran the code and got the following error:
Exception in Tkinter callback Traceback (most recent call last):
File
"C:\Users\Steve\AppData\Local\Programs\Python\Python36-32\lib\tkinter__init__.py",
line 1699, in call
return self.func(*args) File "C:\Users\Steve\Documents\Stocks\QuickOrder\QuickOrderGUI.py", line
403, in gather_data
update_cash_button() File "C:\Users\Steve\Documents\Stocks\QuickOrder\QuickOrderGUI.py", line
208, in update_cash_button
currentCash = get_string(src_path + "cash.png") File "C:\Users\Steve\Documents\Stocks\QuickOrder\QuickOrderGUI.py", line
150, in get_string
result = pytesseract.image_to_string(Image.open(src_path + "thres.png")) File
"C:\Users\Steve\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pytesseract\pytesseract.py",
line 125, in image_to_string
config=config) File "C:\Users\Steve\AppData\Local\Programs\Python\Python36-32\lib\site-packages\pytesseract\pytesseract.py",
line 49, in run_tesseract
proc = subprocess.Popen(command, stderr=subprocess.PIPE, creationflags = CREATE_NO_WINDOW) NameError: name 'CREATE_NO_WINDOW'
is not defined
I then defined the CREATE_NO_WINDOW variable:
#Assignment of the value of CREATE_NO_WINDOW
CREATE_NO_WINDOW = 0x08000000
I got the value of 0x08000000 from the above linked article. After adding the definition I ran the application and I didn't get any more console window popups.
I worked today in a simple script to checksum files in all available hashlib algorithms (md5, sha1.....) I wrote it and debug it with Python2, but when I decided to port it to Python 3 it just won't work. The funny thing is that it works for small files, but not for big files. I thought there was a problem with the way I was buffering the file, but the error message is what makes me think it is something related to the way I am doing the hexdigest (I think) Here is a copy of my entire script, so feel free to copy it, use it and help me figure out what the problem is with it. The error I get when checksuming a 250 MB file is
"'utf-8' codec can't decode byte 0xf3 in position 10: invalid continuation byte"
I google it, but can't find anything that fixes it. Also if you see better ways to optimize it, please let me know. My main goal is to make work 100% in Python 3. Thanks
#!/usr/local/bin/python33
import hashlib
import argparse
def hashFile(algorithm = "md5", filepaths=[], blockSize=4096):
algorithmType = getattr(hashlib, algorithm.lower())() #Default: hashlib.md5()
#Open file and extract data in chunks
for path in filepaths:
try:
with open(path) as f:
while True:
dataChunk = f.read(blockSize)
if not dataChunk:
break
algorithmType.update(dataChunk.encode())
yield algorithmType.hexdigest()
except Exception as e:
print (e)
def main():
#DEFINE ARGUMENTS
parser = argparse.ArgumentParser()
parser.add_argument('filepaths', nargs="+", help='Specified the path of the file(s) to hash')
parser.add_argument('-a', '--algorithm', action='store', dest='algorithm', default="md5",
help='Specifies what algorithm to use ("md5", "sha1", "sha224", "sha384", "sha512")')
arguments = parser.parse_args()
algo = arguments.algorithm
if algo.lower() in ("md5", "sha1", "sha224", "sha384", "sha512"):
Here is the code that works in Python 2, I will just put it in case you want to use it without having to modigy the one above.
#!/usr/bin/python
import hashlib
import argparse
def hashFile(algorithm = "md5", filepaths=[], blockSize=4096):
'''
Hashes a file. In oder to reduce the amount of memory used by the script, it hashes the file in chunks instead of putting
the whole file in memory
'''
algorithmType = hashlib.new(algorithm) #getattr(hashlib, algorithm.lower())() #Default: hashlib.md5()
#Open file and extract data in chunks
for path in filepaths:
try:
with open(path, mode = 'rb') as f:
while True:
dataChunk = f.read(blockSize)
if not dataChunk:
break
algorithmType.update(dataChunk)
yield algorithmType.hexdigest()
except Exception as e:
print e
def main():
#DEFINE ARGUMENTS
parser = argparse.ArgumentParser()
parser.add_argument('filepaths', nargs="+", help='Specified the path of the file(s) to hash')
parser.add_argument('-a', '--algorithm', action='store', dest='algorithm', default="md5",
help='Specifies what algorithm to use ("md5", "sha1", "sha224", "sha384", "sha512")')
arguments = parser.parse_args()
#Call generator function to yield hash value
algo = arguments.algorithm
if algo.lower() in ("md5", "sha1", "sha224", "sha384", "sha512"):
for hashValue in hashFile(algo, arguments.filepaths):
print hashValue
else:
print "Algorithm {0} is not available in this script".format(algorithm)
if __name__ == "__main__":
main()
I haven't tried it in Python 3, but I get the same error in Python 2.7.5 for binary files (the only difference is that mine is with the ascii codec). Instead of encoding the data chunks, open the file directly in binary mode:
with open(path, 'rb') as f:
while True:
dataChunk = f.read(blockSize)
if not dataChunk:
break
algorithmType.update(dataChunk)
yield algorithmType.hexdigest()
Apart from that, I'd use the method hashlib.new instead of getattr, and hashlib.algorithms_available to check if the argument is valid.
Does AppHub let us see reviews of our apps from all marketplaces at once? As I didn't find any, o took some time writing some code to print them all in a file, so i won't waste my time looking for them in every single language.
I'd appreciate any better solution. In the worst case, I'm glad to share the code with anyone who finds it usefull.
It uses BeautifulSoup.
The only parametter is the id of the app, like this:
wp7reviews.py 62289160-6970-4674-85a0-aef3dbe3f93d
Here is the code
import sys
import getopt
from urllib2 import URLError
from urllib2 import HTTPError
import urllib2
from BeautifulSoup import BeautifulStoneSoup
opts, extraparams = getopt.getopt(sys.argv[1:], '')
# starts at the second element of argv since the first one is the script name
# extraparms are extra arguments passed after all option/keywords are assigned
# opts is a list containing the pair "option"/"value"
#print 'Opts:',opts
#print 'Extra parameters:',extraparams
try:
appid = extraparams[0]
except:
#Awsome Linkit appid as default appid
appid="62289160-6970-4674-85a0-aef3dbe3f93d"
allreviewsFILE = open("allreviews.txt", "w")
def output(text):
allreviewsFILE.write(text)
#print text,
def outputln(text):
allreviewsFILE.write(text+'\n')
#print text
def geturl(lang):
return "http://catalog.zune.net/v3.2/"+lang+"/apps/"+appid
try:
request = urllib2.Request(geturl("en-us"))
fd = urllib2.urlopen(request)
content = fd.read()
fd.close()
soup = BeautifulStoneSoup(content)
try:
outputln("App title: "+soup.findAll("a:title")[0].string)
outputln("");
except:
print "Failed to get App Title"
langs = ["en-us", "en-gb", "de-de",
"fr-fr", "es-es", "it-it",
"en-au", "de-at", "fr-be",
"fr-ca", "en-ca", "en-hk",
"en-in", "en-ie", "es-mx",
"en-nz", "en-sg", "de-ch",
"fr-ch", "zh-hk", "zh-cn",
"en-hk"]
outputln("Here we got reviews from each marketplace")
for lang in langs:
request = urllib2.Request(geturl(lang)+"/reviews")
fd = urllib2.urlopen(request)
print "Fetching "+lang+"...",
content = fd.read()
fd.close()
print "OK"
soup = BeautifulStoneSoup(content)
#print soup.prettify()
contents = soup.findAll("a:content")
ratings = soup.findAll("userrating")
l = len(contents)
if l > 0:
outputln("----------- "+lang+" ---------------------------------------------------")
outputln("")
for i in range(0, l):
output(ratings[i].string+"/10 - ")
if len(contents[i].contents) > 0:
try:
outputln(contents[i].contents[0])
except:
outputln("*** Unknown chars ***")
else:
outputln("Rating only")
outputln("")
except HTTPError, e:
print("Error during request!\n")
print("Cod.: ", e.code)
except URLError, e:
print("Invalid URL!\n")
print("Message: ", e.reason)
There already is a site that gives you this information. Take a look at http://wp7reviews.tomverhoeff.com/
There is also a free WP7 app called AppTracker which allows you to track reviews from different regions, as well as translate them into your native language