I am trying to run a code to load dataframe into a sql server using PyQT5 and also at the same time showing a "Please wait" pop up while data is being loaded in DB. I am utilizing QThread for the same. If there is some error then QMessageBox shows the error to the user. But my program is crashing with Message Box appearing blank. I am attaching both code and error snippet.Error Snippet
from functools import partial
from PyQt5 import QtCore, QtGui, QtWidgets
import configparser
import pyodbc
def ConfigSection(section,Config):
dict1 = {}
options = Config.options(section)
for option in options:
try:
dict1[option] = Config.get(section,option)
except:
dict1[option] = None
return dict1
class DatabaseWorker(QtCore.QObject):
started = QtCore.pyqtSignal()
finished = QtCore.pyqtSignal()
message = QtCore.pyqtSignal(object)
msg = ""
#QtCore.pyqtSlot()
def writeToDatabase(self, final_pivot):
self.started.emit()
Config = configparser.ConfigParser(interpolation=None)
try:
config_file = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'config.ini')
Config.read_string(open(config_file).read())
config_values = ConfigSection("Global", Config)
driver = config_values.get('driver')
server = config_values.get('server')
database = config_values.get('database')
username = config_values.get('username')
password = config_values.get('password')
con_str = ("Driver={" + driver + "};"
"Server=" + server + ";"
"Database=" + database + ";"
"UID=" + username + ";"
"PWD=" + password + ";")
cnxn = pyodbc.connect(con_str)
cursor = cnxn.cursor()
for i, row in final_pivot.iterrows():
sql = "INSERT INTO dbo.[FPP_Cleansed_MarketData] (ID,Region,Geography,Category,Company,Year,Adjusted_Sales,Sales_Units,Unit_Type) VALUES (" + "?," * (
len(row) - 1) + "?)"
cursor.execute(sql, tuple(row))
cnxn.commit()
except pyodbc.Error as ex:
sqlstate = ex.args[0]
if sqlstate == '28000':
msg = "Error: Error while logging in. Please check login credentials"
self.message.emit(msg)
credentials")
return -1
elif sqlstate == '23000':
msg = "Error: Trying to insert duplicate ID"
self.message.emit(msg)
return -1
else:
msg = "Error: Error encountered while inserting records into Data Warehouse"
self.message.emit(msg)
return -1
finally:
self.finished.emit()
class Windows_GUI(QtWidgets.QMainWindow):
def __init__(self, df):
QtWidgets.QMainWindow.__init__(self)
self.__threads = []
self.thread = QtCore.QThread(parent=self)
self.__threads.append(self.thread)
self.thread.start()
self.m_database_worker = DatabaseWorker()
self.m_database_worker.moveToThread(self.thread)
self.m_database_worker.started.connect(self.start_animation)
self.m_database_worker.message.connect(self.show_message)
wrapper = partial(self.m_database_worker.writeToDatabase,df)
QtCore.QTimer.singleShot(0, wrapper)
#QtCore.pyqtSlot()
def start_animation(self):
gif_path = "loading.gif"
self.loading_window = QtWidgets.QDialog()
self.loading_window.setWindowFlags(QtCore.Qt.SplashScreen)
self.loading_window.setAttribute(QtCore.Qt.WA_DeleteOnClose)
movie = QtGui.QMovie(gif_path, cacheMode=QtGui.QMovie.CacheAll)
movie_label = QtWidgets.QLabel(alignment=QtCore.Qt.AlignCenter)
movie_label.setFixedSize(100, 75)
movie_label.setMovie(movie)
text_label = QtWidgets.QLabel('Data is getting loaded into Data Warehouse. Please wait...')
text_label.setFont(QtGui.QFont('Arial',11))
vbox = QtWidgets.QHBoxLayout(self.loading_window)
vbox.addWidget(movie_label)
vbox.addWidget(text_label)
self.m_database_worker.finished.connect(self.close_window)
movie.start()
self.setVisible(False)
self.loading_window.show()
def show_message(self,msg):
try:
self.msg_box = QtWidgets.QMessageBox()
self.msg_box.setWindowTitle('Error')
self.msg_box.setIcon(QtWidgets.QMessageBox.Critical)
self.msg_box.information(self, 'Message', msg)
#self.msg_box.setText("Hello Rock the Brahma Bull")
self.msg_box.move(self.frameGeometry().center())
self.msg_box.exec_()
except Exception as e:
print(e)
def close_window(self):
for thread in self.__threads:
thread.quit()
thread.wait()
self.close()
if __name__ == "__main__":
import sys
import pandas as pd
app = QtWidgets.QApplication(sys.argv)
df = pd.read_excel('test.xlsx')
df['ID'] = ['Project_id_' + str(i) for i in range(len(df))]
df = df[['ID', 'Regions', 'Geographies', 'Categories', 'Companies', 'Year', 'Sales', 'Sales_Unit','Currency Conversion']]
w = Windows_GUI(df)
w.show()
sys.exit(app.exec_())
Related
I have a python program that uses mysql.connector to login to a server and execute the query and saving the sql result in excel file. i use pyqt for my gui and when i press the button the gui is freezing. i have created the qthread and worker class but when i import the executor function and pressing the button the program is running and the gui is starting to freeze, what am i doing wrong?
how can i implement the multithreading?
from cmath import inf
from multiprocessing import connection
from operator import index
import os
from sqlite3 import Cursor
from unittest.result import failfast
from datetime import datetime
import mysql.connector
from mysql.connector import errorcode
import pandas as pd
#importing Queries
from Queries import *
#Location Ip's
from locations import locs
from locations import usr,passwd,db
startDate='2022-04-01'
endDate='2022-04-15'
logfailedls = 'logfailed.txt'
logsuccessls = 'logsuccess.txt'
class bcolors:
HEADER = '\033[95m'
OKBLUE = '\033[94m'
OKCYAN = '\033[96m'
OKGREEN = '\033[92m'
WARNING = '\033[93m'
FAIL = '\033[91m'
ENDC = '\033[0m'
BOLD = '\033[1m'
UNDERLINE = '\033[4m'
def executor(QUERY):
alldf = None
for type,info in locs.items():
if not os.path.isdir('%s/'%(type)):
os.makedirs('%s/'%(type))
ls = os.listdir('{}/'.format(type))
if logfailedls in ls:
os.remove('{}/{}'.format(type,logfailedls))
if logsuccessls in ls:
os.remove('{}/{}'.format(type,logsuccessls))
for ip,locName in info.items():
try:
cnx = mysql.connector.connect(user=usr, password=passwd,host=ip, database=db)
if cnx.is_connected():
print("Connection Succesfull to {}".format(locName))
logsuccess = open('{}/logsuccess.txt'.format(type),'a')
logsuccess.write('{} : {}-{}\n'.format(datetime.now().strftime("%Y-%m-%d %H:%M:%S"),ip,locName))
logsuccess.close()
location = cnx.cursor(buffered=True)
location.execute("SELECT loccod FROM docparameters d limit 1")
loc = location.fetchone()[0]
cursor = cnx.cursor()
cursor.execute(QUERY)
df = pd.DataFrame(cursor.fetchall())
if alldf is not None:
alldf = alldf.append(df)
else:
alldf = df
print(df)
field_names = [ i[0] for i in cursor.description]
print(field_names)
xlswriter = pd.ExcelWriter('{}/{}.xls'.format(type,loc),engine='openpyxl')
df.to_excel(xlswriter)
xlswriter.save()
cnx.close()
except mysql.connector.Error as err:
if err.errno == errorcode.ER_ACCESS_DENIED_ERROR:
print("Something wrong with your username or password")
elif err.errno == errorcode.ER_BAD_DB_ERROR:
print("DATABASE does not exist")
else:
print(err)
print("Connectin Failed to %s"%(loc))
logfailed = open("{}/logfailed.txt".format(type),'a')
logfailed.write('{} : {}-{}\n'.format(datetime.now().strftime("%Y-%m-%d %H:%M:%S"),ip,locName))
logfailed.close()
else:
cnx.close()
return [alldf,field_names]
def saveToExcel(query,filename):
xlswriter = pd.ExcelWriter("%s.xls"%(filename),engine='openpyxl')
queryDatas = executor(query)
export = queryDatas[0]
export.columns = queryDatas[1]
export.to_excel(xlswriter,index=False)
xlswriter.save()
#saveToExcel(union,'UNION 15%')
#saveToExcel(hnb,'HBC 25%')
#saveToExcel(SCB,'SCB')
this is my pyqt gui program
from concurrent.futures import Executor
import traceback
from unittest import result
from PyQt5.QtGui import *
from PyQt5.QtWidgets import *
from PyQt5.QtCore import *
import sys
import time
import copy
from connector import *
class WorkerSignals(QObject):
finished = pyqtSignal()
error = pyqtSignal(tuple)
result = pyqtSignal(object)
class Worker(QThread):
def __init__(self,fn,*args,**kwargs):
super(Worker,self).__init__()
self.fn = fn
self.args = args
self.kwargs = kwargs
self.signals = WorkerSignals()
#pyqtSlot()
def run(self):
try:
result = self.fn(*self.args,**self.kwargs)
except:
traceback.print_exc()
exctype, value = sys,sys.exc_info()[:2]
self.signals.error.emit((exctype,value,traceback.format_exc()))
else:
self.signals.result.emit(result)
finally:
self.signals.finished.emit()
class MainWindow(QMainWindow):
def __init__(self, *args, **kwargs):
super(MainWindow, self).__init__(*args, **kwargs)
self.threadpool = QThreadPool()
print("multithreading with maximum %d threads" % self.threadpool.maxThreadCount())
self.counter = 0
layout = QVBoxLayout()
self.l = QLabel("Start")
b = QPushButton("DANGER!")
b.pressed.connect(self.oh_no)
c = QPushButton("?")
c.pressed.connect(self.change_message)
layout.addWidget(self.l)
layout.addWidget(b)
layout.addWidget(c)
w = QWidget()
w.setLayout(layout)
self.setCentralWidget(w)
self.show()
def change_message(self):
self.message = "OH NO"
def print_output(self,s):
print(s)
def thread_complete(self):
print("THREAD COMPLETE!")
def oh_no(self):
worker = Worker(executor(SCB))
worker.signals.result.connect(self.print_output)
worker.signals.finished.connect(self.thread_complete)
self.threadpool.start(worker)
app = QApplication([])
window = MainWindow()
app.exec_()
I wrote a Flask app that is working fine, and I wanted that while it is running, a separate background thread should parallel to it doing some stuff. The problem is, doing this doesn't spawn the thread at all, but I know that my code is right because using the exact same portion of the thread code on a simple python script works as intended.
app.py
weatherCollectorThread = WeatherDataCollectorThread()
...
if __name__ == '__main__':
try:
print("Starting Weather Collector Thread...")
weatherCollectorThread.start()
print("Starting the WebApp...")
app.run(debug=True)
except KeyboardInterrupt:
try:
weatherCollectorThread.stop()
except:
pass
WeatherDataCollectorThread Class
class WeatherDataCollectorThread:
def __init__(self):
self.weatherStations = DBHelper.get_weather_stations()
self.weatherApiKey = "REDACTED"
self.baseURL = "SOME URL"
self.isThreadRunning = False
self.result_log = open('results.log','a+')
def storeWeatherData(self,weather):
conn = DBHelper.get_connection()
cur = conn.cursor()
cur.execute("INSERT INTO weather_data(city,country,now_unixtime,last_updated_unixtime,temperature,isDay,condition_text,condition_icon,windspeed,winddir,pressure,precipitation,cloud,humidity) VALUES (?,?,?,?,?,?,?,?,?,?,?,?,?,?)",[weather['city'],weather['country'],weather['now_unixtime'],weather['last_updated_unixtime'],weather['temperature'],weather['isDay'],weather['condition_text'],weather['condition_icon'],weather['windspeed'],weather['winddir'],weather['pressure'],weather['precipitation'],weather['cloud'],weather['humidity']])
conn.commit()
conn.close()
def collectWeatherData(self):
self.isThreadRunning = True
while self.isThreadRunning:
for each_station in self.weatherStations:
if each_station['isWorking'] != 1:
continue
print("Sending request")
params = {'q':each_station['location'],'key':self.weatherApiKey}
resp = requests.get(url=self.baseURL,params=params)
print("Request received")
weatherData = json.loads(resp.text)
location = weatherData['location']
current = weatherData['current']
weather = {}
weather['city'] = location['name']
weather['country'] = location['country']
weather['now_unixtime'] = location['localtime_epoch']
weather['last_updated_unixtime'] = current['last_updated_epoch']
weather['temperature'] = current['temp_c']
weather['isDay'] = current['is_day']
weather['condition_text'] = current['condition']['text']
weather['condition_icon'] = current['condition']['icon']
weather['windspeed'] = current['wind_kph']
weather['winddir'] = current['wind_dir']
weather['pressure'] = current['pressure_mb']
weather['precipitation'] = current['precip_mm']
weather['cloud'] = current['cloud']
weather['humidity'] = current['humidity']
self.storeWeatherData(weather)
print("Data stored\n" + '-'*24)
self.result_log.write(resp.text + '\n')
sleep(60)
def start(self):
self.thread = Thread(target=self.collectWeatherData)
self.thread.start()
def join_instrument(self,session):
conn = DBHelper.get_connection()
cur = conn.cursor()
cur.execute("UPDATE weather_stations SET isWorking=1 WHERE weatherStationID=?",[session['weatherStationID']])
conn.commit()
conn.close()
def detach_instrument(self,session):
conn = DBHelper.get_connection()
cur = conn.cursor()
cur.execute("UPDATE weather_stations SET isWorking=0 WHERE weatherStationID=?",[session['weatherStationID']])
conn.commit()
conn.close()
def stop(self):
self.result_log.close()
self.isThreadRunning = False
So I figured out the solution.
You see, when you use flask run to run your web-app, it ignores every single function call in the script and parses through the decorators and starts the app on its own. So, if you do something like:
if __name__ == '__main__':
app.start()
someOtherFunction()
Neither the app.start() nor the someOtherFunction() would start.
So the solution?
Simply use python3 app.py to run the script.
... yes, it's that simple :|
I am trying to develop a websocket server with Python and tornado. This websocket server streams a large database result to the client for some visualization.
The problem that I am facing is that no client can connect until the long process (send_data) is finished. It is as if only one client can connect at a time.
Is websocket already an async process or should I implement an async process?
The following is my code:
import time
import random
import json
import datetime
import os
import sys
import cx_Oracle
import string
import re
import subprocess
import asyncio
from tornado import websocket, web, ioloop, escape
from datetime import timedelta
from random import randint
from pprint import pprint
from tornado.web import RequestHandler
os.environ['ORACLE_HOME'] = 'pathToOracleHome'
os.environ['LD_LIBRARY_PATH'] = "$ORACLE_HOME/lib"
def is_hex(a):
printable = set(string.printable) - set("\x0b\x0c")
return any(c not in printable for c in a)
def json_print(d):
print(json.dumps(d, indent=4))
def printf (format,*args):
sys.stdout.write (format % args)
def db(database_name='localhost/database'):
return cx_Oracle.connect('user', 'pwd', database_name)
def query_db(query, args=(), one=False):
cur = db().cursor()
cur.arraysize = 1500
cur.execute(query, args)
return cur
class SummaryWebSocketHandler(websocket.WebSocketHandler):
clients = []
def check_origin(self, origin):
return True
def on_message(self, message):
print ('message received')
def closeDbConn(self,cur):
cur.connection.close()
def query(self, sql):
cursor = query_db(sql)
self.send_data(cursor)
### THIS IS THE LONG PROCESS ###
def send_data(self, cur):
results = {}
columns = [column[0] for column in cur.description]
total = 0
while True:
Res = []
rows = cur.fetchmany()
if rows == []:
print('no more rows')
break;
for row in rows:
results = {}
for i, value in enumerate(row):
if value == None:
value = '-'
results[cur.description[i][0]] = value
Res.append(results)
self.write_message(json.dumps(Res))
total = total + len(rows)
print('total rows send', total)
self.write_message("finished sending all data")
self.on_close(cur)
def open(self, table):
print ('Connection established. \n')
print ('Query string '+table+'\n')
p = re.compile(r'fields=')
m = p.match(table)
matches = table.split("&")
print (matches)
param_string = ''
params = []
if matches:
for m in matches:
print('m', m);
param = ''
items = m.split('=')
if items[1] != '':
param = '--'+items[0]+' '+items[1]
params.append(param)
param_string = " ".join(params)
script = "php getStmt.php "+param_string
print (script)
proc = subprocess.Popen(script, shell=True,stdout=subprocess.PIPE)
sql = proc.stdout.read()
print (sql)
self.query(sql)
def on_close(self, cursor):
print ('Connection closed.')
cursor.close()
settings = {'auto_reload': True, 'debug': True}
if __name__ == "__main__":
print ("Starting websocket server program. Awaiting client requests to open websocket ...")
application = web.Application([(r"/\/table\/(.*)",SummaryWebSocketHandler),
]
,**settings)
application.listen(3001)
ioloop.IOLoop.instance().start()
While I was writing simple message-based fileserver and client, I got the idea about checking fileserver status, but don't know how to realize this: just try to connect and disconnect from server (and how disconnect immediately, when server is not running, if using this way?) or maybe twisted/autobahn have some things, which help to get server status without creating "full connection"?
a) fileserver.py
import os
import sys
import json
from twisted.internet import reactor
from autobahn.twisted.websocket import WebSocketServerFactory, WebSocketServerProtocol, listenWS
CONFIG_TEMPLATE = ''
CONFIG_DATA = {}
class MessageBasedServerProtocol(WebSocketServerProtocol):
"""
Message-based WebSockets server
Template contains some parts as string:
[USER_ID:OPERATION_NAME:FILE_ID] - 15 symbols for USER_ID,
10 symbols for OPERATION_NAME,
25 symbols for FILE_ID
other - some data
"""
def __init__(self):
path = CONFIG_DATA['path']
base_dir = CONFIG_DATA['base_dir']
# prepare to working with files...
if os.path.exists(path) and os.path.isdir(path):
os.chdir(path)
if not os.path.exists(base_dir) or not os.path.isdir(base_dir):
os.mkdir(base_dir)
os.chdir(base_dir)
else:
os.makedir(path)
os.chdir(path)
os.mkdir(base_dir)
os.chdir(base_dir)
# init some things
self.fullpath = path + '/' + base_dir
def __checkUserCatalog(self, user_id):
# prepare to working with files...
os.chdir(self.fullpath)
if not os.path.exists(user_id) or not os.path.isdir(user_id):
os.mkdir(user_id)
os.chdir(user_id)
else:
os.chdir(self.fullpath + '/' + user_id)
def onOpen(self):
print "[USER] User with %s connected" % (self.transport.getPeer())
def connectionLost(self, reason):
print '[USER] Lost connection from %s' % (self.transport.getPeer())
def onMessage(self, payload, isBinary):
"""
Processing request from user and send response
"""
user_id, cmd, file_id = payload[:54].replace('[', '').replace(']','').split(':')
data = payload[54:]
operation = "UNK" # WRT - Write, REA -> Read, DEL -> Delete, UNK -> Unknown
status = "C" # C -> Complete, E -> Error in operation
commentary = 'Succesfull!'
# write file into user storage
if cmd == 'WRITE_FILE':
self.__checkUserCatalog(user_id)
operation = "WRT"
try:
f = open(file_id, "wb")
f.write(data)
except IOError, argument:
status = "E"
commentary = argument
except Exception, argument:
status = "E"
commentary = argument
raise Exception(argument)
finally:
f.close()
# read some file
elif cmd == 'READU_FILE':
self.__checkUserCatalog(user_id)
operation = "REA"
try:
f = open(file_id, "rb")
commentary = f.read()
except IOError, argument:
status = "E"
commentary = argument
except Exception, argument:
status = "E"
commentary = argument
raise Exception(argument)
finally:
f.close()
# delete file from storage (and in main server, in parallel delete from DB)
elif cmd == 'DELET_FILE':
self.__checkUserCatalog(user_id)
operation = "DEL"
try:
os.remove(file_id)
except IOError, argument:
status = "E"
commentary = argument
except Exception, argument:
status = "E"
commentary = argument
raise Exception(argument)
self.sendMessage('[%s][%s]%s' % (operation, status, commentary), isBinary=True)
if __name__ == '__main__':
if len(sys.argv) < 2:
print "using python fileserver_client.py [PATH_TO_config.json_FILE]"
else:
# read config file
CONFIG_TEMPLATE = sys.argv[1]
with open(CONFIG_TEMPLATE, "r") as f:
CONFIG_DATA = json.load(f)
# create server
factory = WebSocketServerFactory("ws://localhost:9000")
factory.protocol = MessageBasedServerProtocol
listenWS(factory)
reactor.run()
b) client.py
import json
import sys
import commands
from twisted.internet import reactor
from autobahn.twisted.websocket import WebSocketClientFactory, WebSocketClientProtocol, connectWS
CONFIG_TEMPLATE = ''
CONFIG_DATA = {}
class MessageBasedClientProtocol(WebSocketClientProtocol):
"""
Message-based WebSockets client
Template contains some parts as string:
[USER_ID:OPERATION_NAME:FILE_ID] - 15 symbols for USER_ID,
10 symbols for OPERATION_NAME,
25 symbols for FILE_ID
other - some data
"""
def onOpen(self):
user_id = CONFIG_DATA['user']
operation_name = CONFIG_DATA['cmd']
file_id = CONFIG_DATA['file_id']
src_file = CONFIG_DATA['src_file']
data = '[' + str(user_id) + ':' + str(operation_name) + ':' + str(file_id) + ']'
if operation_name == 'WRITE_FILE':
with open(src_file, "r") as f:
info = f.read()
data += str(info)
self.sendMessage(data, isBinary=True)
def onMessage(self, payload, isBinary):
cmd = payload[1:4]
result_cmd = payload[6]
if cmd in ('WRT', 'DEL'):
print payload
elif cmd == 'REA':
if result_cmd == 'C':
try:
data = payload[8:]
f = open(CONFIG_DATA['src_file'], "wb")
f.write(data)
except IOError, e:
print e
except Exception, e:
raise Exception(e)
finally:
print payload[:8] + "Successfully!"
f.close()
else:
print payload
reactor.stop()
if __name__ == '__main__':
if len(sys.argv) < 2:
print "using python fileserver_client.py [PATH_TO_config.json_FILE]"
else:
# read config file
CONFIG_TEMPLATE = sys.argv[1]
with open(CONFIG_TEMPLATE, "r") as f:
CONFIG_DATA = json.load(f)
# connection to server
factory = WebSocketClientFactory("ws://localhost:9000")
factory.protocol = MessageBasedClientProtocol
connectWS(factory)
reactor.run()
Find solution this issue: using callLater or deferLater for disconnect from server, if can't connect, but when all was 'OK', just take server status, which he says.
import sys
from twisted.internet.task import deferLater
from twisted.internet import reactor
from autobahn.twisted.websocket import WebSocketClientFactory, WebSocketClientProtocol, connectWS
CONFIG_IP = ''
CONFIG_PORT = 9000
def isOffline(status):
print status
class StatusCheckerProtocol(WebSocketClientProtocol):
def __init__(self):
self.operation_name = "STATUS_SRV"
self.user_id = 'u00000000000000'
self.file_id = "000000000000000000000.log"
def onOpen(self):
data = '[' + str(self.user_id) + ':' + str(self.operation_name) + ':' + str(self.file_id) + ']'
self.sendMessage(data, isBinary=True)
def onMessage(self, payload, isBinary):
cmd = payload[1:4]
result_cmd = payload[6]
data = payload[8:]
print data
reactor.stop()
if __name__ == '__main__':
if len(sys.argv) < 3:
print "using python statuschecker.py [IP] [PORT]"
else:
# read preferences
CONFIG_IP = sys.argv[1]
CONFIG_PORT = int(sys.argv[2])
server_addr = "ws://%s:%d" % (CONFIG_IP, CONFIG_PORT)
# connection to server
factory = WebSocketClientFactory(server_addr)
factory.protocol = StatusCheckerProtocol
connectWS(factory)
# create special Deffered, which disconnect us from some server, if can't connect within 3 seconds
d = deferLater(reactor, 3, isOffline, 'OFFLINE')
d.addCallback(lambda ignored: reactor.stop())
# run all system...
reactor.run()
I'm trying to write a small python app, using PySide for the GUI and Twython as a Twitter API library, to catch a stream from Twitter.
The problem that I am having is that when I click "Start Monitoring Twitter" button, the UI freezes until the stream is complete, at which point the code continues to execute and disables the Start button and enables the Stop button. Here's the UI:
Everything else seems to work -- if I leave it, then the CSV file is created as I suspect -- the Twython components seem to be working as expected.
Line 151 is where the streaming from Twitter is engaged when I click start:
self.stream.statuses.filter(track=self.search_term)
How can I move the streaming to a separate thread and then use the Stop button on the UI to tell Twython to complete capturing the stream and exit?
I need to be able to send the MyStreamer instance to another thread and then send it the .disconnect() signal to have it terminate capturing the stream.
Here's the full code:
#!/usr/bin/env python
# -*- coding: utf-8 -*-
import sys
import platform
import PySide
from PySide.QtGui import QApplication, QMainWindow, QPushButton, QCheckBox, QTextEdit
from time import sleep
from ui_tweetstream import Ui_MainWindow
from twython import Twython
from twython import TwythonStreamer
import csv
class MainWindow(QMainWindow, Ui_MainWindow):
def __init__(self, parent=None):
super(MainWindow, self).__init__(parent)
self.setupUi(self)
# Set up Variables
self.tweet_fav_count = True
self.tweet_geocoordinates = True
self.tweet_id = True
self.tweet_language = True
self.tweet_orig_tweet_id = True
self.tweet_orig_username = True
self.tweet_retweeted = True
self.tweet_sensitive = True
self.tweet_source_app = True
self.tweet_timestamp = True
self.tweet_user_name = True
self.search_term = "#bigdata"
self.tweets_to_get = 1000
# Bind the interface
self.check_tweet_fav_count.clicked.connect(self.setTweetFavCount)
self.check_tweet_geocoordinates.clicked.connect(self.setTweetGeocoordinates)
self.check_tweet_id.clicked.connect(self.setTweetID)
self.check_tweet_language.clicked.connect(self.setTweetLanguage)
self.check_tweet_orig_tweet_id.clicked.connect(self.setTweetOrigTweetID)
self.check_tweet_orig_username.clicked.connect(self.setTweetOrigUsername)
self.check_tweet_retweeted.clicked.connect(self.setTweetRetweeted)
self.check_tweet_sensitive.clicked.connect(self.setTweetSensitive)
self.check_tweet_source_app.clicked.connect(self.setTweetSourceApp)
self.check_tweet_timestamp.clicked.connect(self.setTweetTimestamp)
self.check_tweet_user_name.clicked.connect(self.setTweetUsername)
self.button_start.clicked.connect(self.streamStart)
self.button_stop.clicked.connect(self.streamStop)
# Set the initial states
self.button_stop.setEnabled(False)
APP_KEY = ''
APP_SECRET = ''
OAUTH_TOKEN = ''
OAUTH_TOKEN_SECRET = ''
self.t = Twython(APP_KEY, APP_SECRET, OAUTH_TOKEN, OAUTH_TOKEN_SECRET)
self.stream = MyStreamer(APP_KEY,APP_SECRET,OAUTH_TOKEN,OAUTH_TOKEN_SECRET)
self.stream.init_mainWindow(self)
def streamStop(self):
print "Stopping stream"
# Enable other controls here
self.button_stop.setEnabled(False)
self.button_start.setEnabled(True)
self.setControlStates(True)
self.stream.stopStream()
def setControlStates(self, state):
self.check_tweet_fav_count.setEnabled(state)
self.check_tweet_geocoordinates.setEnabled(state)
self.check_tweet_id.setEnabled(state)
self.check_tweet_language.setEnabled(state)
self.check_tweet_orig_tweet_id.setEnabled(state)
self.check_tweet_orig_username.setEnabled(state)
self.check_tweet_retweeted.setEnabled(state)
self.check_tweet_sensitive.setEnabled(state)
self.check_tweet_source_app.setEnabled(state)
self.check_tweet_timestamp.setEnabled(state)
self.check_tweet_user_name.setEnabled(state)
self.search_box.setEnabled(state)
self.num_tweets_box.setEnabled(state)
# Functions for determining what to track
def setTweetFavCount(self):
self.tweet_fav_count = not self.tweet_fav_count
print "tweet_fav_count:", self.tweet_fav_count
def setTweetGeocoordinates(self):
self.tweet_geocoordinates = not self.tweet_geocoordinates
print "tweet_geocoordinates:", self.tweet_geocoordinates
def setTweetID(self):
self.tweet_id = not self.tweet_id
print "tweet_id:", self.tweet_id
def setTweetLanguage(self):
self.tweet_language = not self.tweet_language
print "tweet_language:", self.tweet_language
def setTweetOrigTweetID(self):
self.tweet_orig_tweet_id = not self.tweet_orig_tweet_id
print "tweet_orig_tweet_id:", self.tweet_orig_tweet_id
def setTweetOrigUsername(self):
self.tweet_orig_username = not self.tweet_orig_tweet_id
print "tweet_orig_username:", self. tweet_orig_username
def setTweetRetweeted(self):
self.tweet_retweeted = not self.tweet_retweeted
print "tweet_retweeted:", self.tweet_retweeted
def setTweetSensitive(self):
self.tweet_sensitive = not self.tweet_sensitive
print "tweet_sensitive:", self.tweet_sensitive
def setTweetSourceApp(self):
self.tweet_source_app = not self.tweet_source_app
print "tweet_source_app:", self.tweet_source_app
def setTweetTimestamp(self):
self.tweet_timestamp = not self.tweet_timestamp
print "tweet_timestamp:", self.tweet_timestamp
def setTweetUsername(self):
self.tweet_user_name = not self.tweet_user_name
print "tweet_user_name:", self.tweet_user_name
# Functions for starting and stopping the stream
def streamStart(self):
print "Starting stream"
self.setControlStates(False)
# Disable other controls here
self.button_start.setEnabled(False)
self.button_stop.setEnabled(True)
# Hack to try to disable the UI
# sleep(0.25)
# Get the active search term
self.search_term = self.search_box.text()
# Get the number of tweets
self.tweets_to_get = int(self.num_tweets_box.text())
# Set the streamer
self.stream.set_start_criteria(self.tweets_to_get)
self.stream.statuses.filter(track=self.search_term)
class MyStreamer(TwythonStreamer):
def init_mainWindow(self, the_main_window):
self.main_window = the_main_window
self.stop = False
self.header_done = False
def set_start_criteria(self, numTweets):
self.maxTweets = numTweets
self.tweetCount = 0
print "Number of tweets to get:", self.maxTweets
def stopStream(self):
self.stop = True
def on_success(self, data):
if 'text' in data:
self.tweetCount += 1
print "tweetCount:", self.tweetCount
#tweet = data['text'].encode('utf-8')
theTweet = data
writer = TweetMonkey()
writer.assignMainWindow(self.main_window, self.header_done)
self.header_done = True
writer.process(theTweet)
# Want to disconnect after the first result?
if self.stop is True or self.tweetCount >= self.maxTweets:
self.disconnect()
def on_error(self, status_code, data):
print status_code, data
class TweetMonkey:
def assignMainWindow(self,the_main_window, is_header_done):
self.main_window = the_main_window
self.header_done = is_header_done
def clean(self,text):
text = text.replace("\n","; ")
text = text.replace('"', "'")
text = text.replace(','," ")
return text
def create_header(self):
header = []
tweets = open("tweets.csv", 'ab+')
wr = csv.writer(tweets, dialect='excel')
if self.main_window.tweet_id is True:
header.append("id")
if self.main_window.tweet_language is True:
header.append("lang")
if self.main_window.tweet_user_name is True:
header.append("user_name")
header.append("tweet")
if self.main_window.tweet_retweeted is True:
header.append("retweeted")
if self.main_window.tweet_fav_count is True:
header.append("favorite_count")
if self.main_window.tweet_source_app is True:
header.append("source")
if self.main_window.tweet_orig_tweet_id is True:
header.append("in_reply_to_status_id")
if self.main_window.tweet_orig_username is True:
header.append("in_reply_to_screen_name")
# header.append("in_reply_to_user_id")
if self.main_window.tweet_sensitive is True:
header.append("possibly_sensitive")
if self.main_window.tweet_geocoordinates is True:
header.append("geo")
if self.main_window.tweet_timestamp is True:
header.append("created_at")
wr.writerow(header)
tweets.close()
def process(self, tweet):
if not self.header_done:
self.create_header()
self.header_done = True
# Create the file or append to the existing
theOutput = []
tweets = open("tweets.csv", 'ab+')
wr = csv.writer(tweets, dialect='excel')
if self.main_window.tweet_id is True:
theOutput.append(tweet['id'])
if self.main_window.tweet_language is True:
theOutput.append(tweet['lang'].encode('utf-8'))
if self.main_window.tweet_user_name is True:
theOutput.append(tweet['user']['name'].encode('utf-8', 'replace'))
theOutput.append(self.clean(tweet['text']).encode('utf-8', 'replace'))
if self.main_window.tweet_retweeted is True:
theOutput.append(tweet['retweeted'])
if self.main_window.tweet_fav_count is True:
theOutput.append(tweet['favorite_count'])
if self.main_window.tweet_source_app is True:
theOutput.append(self.clean(tweet['source']).encode('utf-8', 'replace'))
if self.main_window.tweet_orig_tweet_id is True:
theOutput.append(tweet['in_reply_to_status_id'])
if self.main_window.tweet_orig_username is True:
theOutput.append(tweet['in_reply_to_screen_name'])
#theOutput.append(tweet['in_reply_to_user_id'])
if self.main_window.tweet_sensitive is True:
if tweet.get('possibly_sensitive'):
theOutput.append(tweet['possibly_sensitive'])
else:
theOutput.append("False")
if self.main_window.tweet_geocoordinates is True:
if tweet['geo'] is not None:
if tweet['geo']['type'] == 'Point':
lat = str(tweet['geo']['coordinates'][0]) + " "
lon = str(tweet['geo']['coordinates'][1])
theOutput.append(lat + lon)
else:
theOutput.append(tweet['geo'])
else:
theOutput.append(tweet['geo'])
if self.main_window.tweet_timestamp is True:
theOutput.append(tweet['created_at'])
wr.writerow(theOutput)
tweets.close()
if __name__ == '__main__':
app = QApplication(sys.argv)
frame = MainWindow()
frame.show()
app.exec_()
I know this is an old post but I ran into a similar problem in a simple app I recently wrote, my solution was to use threading.
I used the worker from:
https://pymotw.com/2/threading/
and the method described in:
http://aadrake.com/using-twitter-as-a-stream-processing-source.html
Basically running the Twython stream as a separate thread feeding text to a queue then I run the rest of the program in a separate loop reading from the queue.