I have 2 PLCs with serial port. one is mitsubishi Q00Jcpu mc protocol, another is omron hostlink protocol.
I tried to use python pyserial lib to write to the PLC and read response.
But failed, I tried to use a serial tool to test and got nice response,
serial tool success communicate with PLC, I read CIO address start 100 and size 2, it got 12345678, that is a true result.
my code :
import serial
omr = serial.Serial(port='COM4', baudrate=9600, timeout=0.5)
omr.parity=serial.PARITY_EVEN
omr.bytesize = 7
omr.stopbits =2
resp = omr.write(b'\x40\x30\x30\x46\x41\x30\x30\x30\x30\x30\x30\x30\x30\x30\x30\x31\x30\x31\x42\x30\x30\x30\x36\x34\x30\x30\x30\x30\x30\x32\x30\x35\x2a\x0d')
print(resp) # print 34
resp = omr.write(b'#00FA0000000000101B0006400000205*\CR')
print(resp) # print 36
It seems return the len of write data, I tried both hex and ascii, all failed.
I figured it how, the return of serial.write is not the result. If need the response from device, should use read_until(), not sure weather this is a good way, please let me know if you have any suggestions.
Anyway, the class i make, can read the omron PLC by giving different params, hope it can help someone.
DEMO:
import serial
# cmd = '0101B00064000001'
class OMR_SERIAL_TOOL:
def __init__(self,port,baudrate):
self.omr = serial.Serial(port=port, baudrate=baudrate, timeout=0.5)
self.omr.parity=serial.PARITY_EVEN
self.omr.bytesize = 7
self.omr.stopbits =2
self.head ='#00FA000000000'
#staticmethod
def get_xor(frame):
res = ord(frame[0])
for i in frame[1:]:
res ^= ord(i)
res = str(res)
if len(res) == 1:
res = '0'+res
return res
def omr_read(self,head,cmd):
xor = OMR_SERIAL_TOOL.get_xor(head+cmd)
self.omr.write('{}{}{}*\r'.format(head,cmd,xor).encode())
resp = self.omr.read_until("\r".encode())
return str(resp[23:-4],encoding='utf-8')
test = OMR_SERIAL_TOOL('COM4',9600)
res = test.omr_read(test.head,cmd='0101B00064000002')
print(res) # 12345678 , which is the correct response
BOOM! VERSION 1.0
import serial
class OMR_SERIAL_TOOL:
def __init__(self,port,baudrate,mode):
self.omr = serial.Serial(port=port, baudrate=baudrate, timeout=0.5)
self.omr.parity=serial.PARITY_EVEN
self.omr.bytesize = 7
self.omr.stopbits =2
# fins mdoe
if mode == 'fins':
self.head ='#00FA000000000'
self.cmd_map = {
"MEMORY_AREA_READ":"0101",
"MEMORY_AREA_WRITE":"0102",
"MEMORY_AREA_FILL":"0103",
"MULTI_MEMORY_AREA_READ":"0104",
"MEMORY_AREA_TRANSFER":"0105"
}
# cs/cj mode
self.io_memory_area_code_map={
"CIO_bit":"30",
"WR_bit":"31",
"HR_bit":"32",
"AR_bit":"33",
"CIO_word":"B0",
"WR_word":"B1",
"HR_word":"B2",
"AR_word":"B3"
}
#staticmethod
def get_xor(frame):
res = ord(frame[0])
for i in frame[1:]:
res ^= ord(i)
res = str(res)
if len(res) == 1:
res = '0'+res
res = str(hex(int(res)))[2:]
upcase_res = ''
for i in res:
if i.isdigit():
upcase_res += i
elif i.isalpha():
upcase_res += i.upper()
if len(upcase_res) == 1:
upcase_res = '0'+upcase_res
return upcase_res
def omr_read(self,cmd,code,address,size):
address = str(hex(address))[2:]
size = str(hex(size))[2:]
while len(address) < 4:
address = '0' + address
while len(size) < 4:
size = '0' + size
frame = self.head+cmd+code+address+'00'+size
xor = OMR_SERIAL_TOOL.get_xor(frame)
#print(frame+xor)
self.omr.write('{}{}*\r'.format(frame,xor).encode())
resp = self.omr.read_until("\r".encode())
return str(resp[23:-4],encoding='utf-8')
omr_client = OMR_SERIAL_TOOL('COM4',9600,'fins')
cmd = omr_client.cmd_map['MEMORY_AREA_READ']
code = omr_client.io_memory_area_code_map['CIO_word']
res = omr_client.omr_read(cmd,code,address=500,size=1)
I tested it good on CIO read, please let me know if you find any bugs.
Related
I have the following code that I've been asked to 'tidy up'. At the moment I think its not optimal, so I'd like some advice on how to make it so please.
I have 4 voltages received as MQTT messages (power1,power2 etc.), corresponding to 4 different measuring stations, each of which is a value I append to a new array 'power'. If the values lie between 'Vtrig' and 'Vlow', they are appended to another array 'flags', whose length, when exceeding a certain value (Flag_length), triggers a flag I can send out as an MQTT message, so that way if I get multiple values outside of the required range I'm notified. Otherwise, the array is emptied and we start again.
Here's what I wrote so far:
import smbus
import time
import csv
from datetime import datetime
import paho.mqtt.client as paho
MQTT_HOST = '10.10.20.122'
MQTT_PORT = 1883
MQTT_CLIENT_ID = 'lowerStation'
TOPIC = 'pwrTest/testData'
TOPIC_TOM = 'pwrTest/Error'
TOPICeval = 'pwrTest/testEval'
Vtrig = 12
Vlow = 0.1
Flag_length = 7
flags0=[]
flags1=[]
flags2=[]
flags3=[]
client = paho.Client(MQTT_CLIENT_ID)
client.connect(MQTT_HOST, MQTT_PORT)
# Serial numbers to Volito connected to measureing station, station 1 to 4
SN = [109, 78, 86, 60]
def on_connect(client, userdata, flags, rc):
if rc==0:
print('connected')
else:
print('Bad connection code =', rc)
broker = '10.10.20.122'
client.connect(broker) #connect to broker
client.on_connect = on_connect #bind call back function
print('Connecting to broker', broker)
But this is really the relevant part.
payload = str(power1) + "," + "Station1," + "SN" +str(SN[0])
client.publish(TOPIC, payload)
payload = str(power2) + "," + "Station2," + "SN" +str(SN[1])
client.publish(TOPIC, payload)
payload = str(power3) + "," + "Station3," + "SN" +str(SN[2])
client.publish(TOPIC, payload)
payload = str(power4) + "," + "Station4," + "SN" +str(SN[3])
client.publish(TOPIC, payload)
power = []
power.append(datetime.now().strftime("%d/%m/%Y %H:%M:%S"))
power.append(power1)
power.append(power2)
power.append(power3)
power.append(power4)
for x in power[1:2]:
if x <Vtrig and x> Vlow:
flags0.append(x)
elif x>= Vtrig:
flags0 = []
if len(flags0) > Flag_length:
payload = '5.0,' + "Station1," + "SN" +str(SN[0])
flags0 = []
client.publish(TOPICeval,payload)
for x in power[2:3]:
if x <Vtrig and x> Vlow:
flags1.append(x)
elif x>= Vtrig:
flags1 = []
if len(flags1) > Flag_length:
payload = '5.0,' + "Station2," + "SN" +str(SN[1])
flags1 = []
client.publish(TOPICeval,payload)
for x in power[3:4]:
if x <Vtrig and x> Vlow:
flags2.append(x)
elif x>= Vtrig:
flags2 = []
if len(flags2) > Flag_length:
payload ='5.0,' + "Station3," + "SN" +str(SN[2])
flags2 = []
client.publish(TOPICeval,payload)
for x in power[4:5]:
if x <Vtrig and x> Vlow:
flags3.append(x)
elif x>= Vtrig:
flags3 = []
if len(flags3) > Flag_length:
payload ='5.0,' + "Station4," + "SN" +str(SN[3])
flags3 = []
client.publish(TOPICeval,payload)
print('running')
time.sleep(10)
As you can see I repeat the same code for each entry, is there a better way of writing this in a for loop?
Nice spot on simplification. I think you could do it like this.
Even better you should probably start using functions or debugging your code will be a nightmare in the future.
buffer = {} #a dict but probably other ways to do it
for index,value in enumerate(power):
if value<Vtrig and value>Vlow: #your conditional checks
buffer[index].append(value) #appends to the index of your power list
elif value>= Vtrig: #conditional checks
buffer[index] = [] #clearing the 'flag' list for index
if len(buffer[index])> Flag_length:#your conditional check
payload = '5.0, Station{}, SN{}'.format(index+1,SN[index])
#index from 0 so i think you want + 1 here for station and SN to equal the index
buffer[index] = [] #clearing again
client.publish(TOPICeval,payload) #publishihing whatever you wanted
On another note, consider creating a class and creating functions. Would make your code much more readable.
I'm unable to generate all entries in Kaltura. An ApiException with the message "Unable to generate list. max matches value was reached" (Error: QUERY_EXCEEDED_MAX_MATCHES_ALLOWED) gets triggered.
I tried to work around such issue by setting my sessionPrivileges to disableentitlement
class class_chk_integrity():
client = None
pagesize = 0
def __init__(self,worker_num, progress):
self.pagesize = 30
self.worker_num = worker_num
self.progress = progress
config = KalturaConfiguration(2723521)
config.serviceUrl = "https://www.kaltura.com/"
self.client = KalturaClient(config)
ks = self.client.session.start("KALTURA_ADMIN_SECRET",
"email#email.com",
KalturaPluginsCore.KalturaSessionType.ADMIN,
"KALTURA_PARTNER_ID",
432000,
"disableentitlement")
self.client.setKs(ks)
I also tried to filter based on the id's. However, I can't manage to put the filter.idNotIn to work properly.
def get_total_reg(self, cont, lastEntryIds, lastEntryCreatedAt):
filter = KalturaPluginsCore.KalturaBaseEntryFilter()
if lastEntryIds != "":
filter.idNotIn = lastEntryIds
filter.orderBy = KalturaBaseEntryOrderBy.CREATED_AT_DESC
pager = KalturaPluginsCore.KalturaFilterPager()
pageIndex = 1
entriesGot = 0
pager.pageSize = self.pagesize
pager.setPageIndex = pageIndex
result = self.client.baseEntry.list(filter, pager)
totalCount = result.totalCount
if totalCount > 10000:
totalCount = 9970
if totalCount <= 0:
cont = False
while entriesGot < totalCount:
pager.pageSize = self.pagesize
pageIndex += 1
pager.pageIndex = pageIndex
result = self.client.baseEntry.list(filter, pager)
entriesGot += len(result.objects)
for e in result.objects:
if lastEntryIds == "":
lastEntryIds.append(e.id)
else:
lastEntryIds.append(e.id)
lastEntryCreatedAt = e.createdAt
return result.totalCount, self.pagesize, cont, lastEntryIds, lastEntryCreatedAt
This is my how I'm calling the functions
if __name__ == '__main__':
try:
log = _ServiceUtils.log()
log.setup('all', 'integrity')
cont = True
lastEntryIds = []
lastEntryCreatedAt = 0
while cont is True:
kmc = class_chk_integrity(0,0)
kmc_total_reg, kmc_page_size, cont, lastEntryIds, lastEntryCreatedAt = kmc.get_total_reg(cont, lastEntryIds, lastEntryCreatedAt)
interval = 10
max_threads = math.ceil(kmc_total_reg / (interval * kmc_page_size))
# max_threads = 1
threads_list = []
print('TOTAL REG : %s | PAGE_SIZE : %s | INTERVAL : %s | THREADS : %s' % (kmc_total_reg,kmc_page_size,interval,max_threads))
progress = class_progress_thread(max_threads)
for index in range(0,max_threads):
page_ini = index * interval
page_end = index * interval + interval
progress.add_worker_progress(index,datetime.now())
threads_list.append(threading.Thread(target=thread_chk_integrity, args=(index, log, index * interval + 1,index * interval + interval,progress)))
threads_list.append(threading.Thread(target=thread_output_progress, args=(progress,max_threads)))
for thread in threads_list:
thread.start()
for thread in threads_list:
thread.join()
while not progress.stop(): time.sleep(30)
except KeyboardInterrupt:
try:
sys.exit(0)
except SystemExit:
os._exit(0)
I'd appreciate any help with this.
Thank you for your attention.
if totalCount > 10000:
totalCount = 9970
I'm curious to know why you are changing the totalCount this way.
Short answer - paging works as long as the result set is up to 10K.
To work around that, sort the result by creation date (as you did), and when you get to 10K, start with a new search where the created_at date in the filter is the last value you got in the previous search. Reset your paging of course.
I have a raspberry pi that I have turned into an Eddystone URL beacon and I wish to read the URL on my laptop using python because I have to use the URL further in my web app.
The only way that I have had any success scanning for beacons on Windows 10 using Python is with the Windows Runtime Python Projection (Python/WinRT)
Here is an example scanning and printing the data for Eddystone, iBeacon, and AltBeacon:
import asyncio
import uuid
import winrt.windows.devices.bluetooth.advertisement as winBLE
from winrt.windows.storage.streams import DataReader
async def discover():
def process_eddystone(data):
_url_prefix_scheme = ['http://www.', 'https://www.',
'http://', 'https://', ]
_url_encoding = ['.com/', '.org/', '.edu/', '.net/', '.info/',
'.biz/', '.gov/', '.com', '.org', '.edu',
'.net', '.info', '.biz', '.gov']
tx_pwr = int.from_bytes([data[1]], 'big', signed=True)
if data[0] == 0x00:
namespace_id = int.from_bytes(data[2:12], 'big')
instance_id = int.from_bytes(data[12:18], 'big')
print(f'\t\tEddystone UID: {namespace_id} '
f'- {instance_id} \u2197 {tx_pwr}')
elif data[0] == 0x10:
prefix = data[2]
encoded_url = data[3:]
full_url = _url_prefix_scheme[prefix]
for letter in encoded_url:
if letter < len(_url_encoding):
full_url += _url_encoding[letter]
else:
full_url += chr(letter)
print(f'\t\tEddystone URL: {full_url} \u2197 {tx_pwr}')
def process_ibeacon(data, beacon_type='iBeacon'):
beacon_uuid = uuid.UUID(bytes=bytes(data[2:18]))
major = int.from_bytes(bytearray(data[18:20]), 'big', signed=False)
minor = int.from_bytes(bytearray(data[20:22]), 'big', signed=False)
tx_pwr = int.from_bytes([data[22]], 'big', signed=True)
print(f'\t\t{beacon_type}: {beacon_uuid} - {major} '
f'- {minor} \u2197 {tx_pwr}')
def on_advert(sender, evt):
for s_data_buf in evt.advertisement.data_sections:
if s_data_buf.data_type == 0x16:
data_reader = DataReader.from_buffer(s_data_buf.data)
s_data = data_reader.read_bytes(s_data_buf.data.length)
if s_data[0:2] == [0xaa, 0xfe]:
process_eddystone(s_data[2:])
for m_data_buf in evt.advertisement.manufacturer_data:
if m_data_buf.company_id == 0x004c:
data_reader = DataReader.from_buffer(m_data_buf.data)
m_data = data_reader.read_bytes(m_data_buf.data.length)
if m_data[0] == 0x02:
process_ibeacon(m_data)
elif m_data_buf.company_id == 0xffff:
data_reader = DataReader.from_buffer(m_data_buf.data)
m_data = data_reader.read_bytes(m_data_buf.data.length)
if m_data[0:2] == [0xbe, 0xac]:
process_ibeacon(m_data, 'AltBeacon')
watcher = winBLE.BluetoothLEAdvertisementWatcher()
watcher.add_received(on_advert)
watcher.start()
await asyncio.sleep(25)
watcher.stop()
asyncio.run(discover())
See the code below, "J2".
In the xml j2 as you can see "Y=getY" it's doing that for each id+pproxy(multithreading)
Now what I want is, I want it to continue changing id and k2= but use the same Y for only 3 times. Then after that get a new Y and do the same..
So for example
<j2 Y="one value" id="3 multi threads pass trough" k="3 multi threads"
and then after that <j2 Y="new y value because only 3 ids can pass through one Y" id="same again" k="same again">
j2 = str('<j2 cb="'+rcv.attrib["c"]+'" Y="'+str(Y[0])+'" l5="'+str(Y[1]).strip()+'" l4="583" l3="463" l2="0" q="1" y="'+rcv.attrib['i']+'" k="'+k+'" k3="0" p="0" c="'+str(info[2])+'" f="0" u="'+str(uid)+'" d0="0" n=" " a="0" h="" v="0" />\0')
The Y value should be the same while 3 ids pass through it, then when 3 have passed through it, grab a new Y value.
Take a look at this script:
import socket, socks
import xml.etree.ElementTree as tree
import time, random, urllib2
import threading
from itertools import izip
def gB(data,first,last):
x=len(first)
begin = data.find(first) + x
end = data.find(last,begin)
return data[begin:end]
def isInt(buf):
try:
i = int(buf)
return True
except:
return False
def ip(roomname):
if isInt(roomname):
room = roomname
else:
room = gB(urllib2.urlopen('http://xat.com/'+roomname).read(),'FlashVars="id=','&xc=')
room = int(room)
x = urllib2.urlopen('http://xat.com/web_gear/chat/ip.htm?'+str(time.time())).read()
x = tree.fromstring(x)
xSock = x.attrib['xSock'].split(',')
rSock = []
while len(rSock) < 4:
rSock.append(xSock[len(rSock) * 4 + random.randint(0,1)])
return rSock[(room & 96) >> 5],int(10007 + (room % 32)),room
def parseID(auser3):
auser3 = auser3.split('&')
userid = auser3[1].split('=')[1]
k1 = auser3[2].split('=')[1]
k2 = auser3[3].split('=')[1]
return [userid,k1,k2]
return l5
def getY(au, p0, p1, p2, p3, yi):
sock = socket.socket(socket.AF_INET,socket.SOCK_STREAM)
sock.settimeout(10)
sock.connect(("127.0.0.1",1337))
sock.send(au+"_"+p0+"_"+p1+"_"+p2+"_"+p3+"_"+yi)
data = sock.recv(1270)
parse = data.split("\"")
sock.close()
print "Y => "+parse[1]+" L5 => "+parse[3]
return [parse[1], parse[3]]
def raider(a3,p):
info = ip(chat)
try:
socks.setdefaultproxy(socks.PROXY_TYPE_SOCKS4, p[0], int(p[1]))
socket.test = socks.socksocket
xat = socket.test(socket.AF_INET, socket.SOCK_STREAM, socket.SOL_TCP)
xat.settimeout(10)
xat.connect((info[0],int(info[1])))
xat.send('<y r="'+str(info[2])+'" />\0')
bypass = xat.recv(1024)
print "\nRecv --> "+bypass+"\n"
rcv = tree.fromstring(bypass.strip("\0"))
if 'i' not in rcv.attrib:
raise Exception("YUP")
import pprint
pprint.pprint(a3)
uid = a3[0]
k = a3[1]
if 'au' in rcv.attrib:
Y = getY(rcv.attrib["au"], rcv.attrib["p"].split("_")[0],rcv.attrib["p"].split("_")[1],rcv.attrib["p"].split("_")[2],rcv.attrib["p"].split("_")[3], rcv.attrib["i"])
j2 = str('<j2 cb="'+rcv.attrib["c"]+'" Y="'+str(Y[0])+'" l5="'+str(Y[1]).strip()+'" l4="583" l3="463" l2="0" q="1" y="'+rcv.attrib['i']+'" k="'+k+'" k3="0" p="0" c="'+str(info[2])+'" f="0" u="'+str(uid)+'" d0="0" n=" " a="0" h="" v="0" />\0')
xat.send(j2)
print "\nSend [Bypass] --> "+j2+"\n"
else:
Y = getY(str(0), rcv.attrib["p"].split("_")[0],rcv.attrib["p"].split("_")[1],rcv.attrib["p"].split("_")[2],rcv.attrib["p"].split("_")[3], rcv.attrib["i"])
j2 = str('<j2 cb="'+rcv.attrib["c"]+'" l5="'+str(Y[1]).strip()+'" l4="583" l3="463" l2="0" q="1" y="'+rcv.attrib['i']+'" k="'+k+'" k3="0" p="0" c="'+str(info[2])+'" f="0" u="'+str(uid)+'" d0="0" n=" " a="0" h="" v="0" />\0')
xat.send(j2)
print "\nSend --> "+j2+"\n"
while 1:
time.sleep(1)
xat.send('<m t=" | XAT IS CORRUPT | " u="'+uid+'" />\0')
except:
pass
chat = raw_input("Chat to raid: ")
ids = [i.strip() for i in open('ids.txt','r')]
proxies = [i.strip() for i in open('socks.txt','r')]
for (i,j) in izip(ids,proxies):
i = parseID(i)
j = j.split(':')
threading.Thread(target=raider,args=(i,j)).start()
At beginning i wanna say i'm newbie in use Python and everything I learned it came from tutorials.
My problem concerning reference to the value. I'm writing some script which is scrapping some information from web sites. I defined some function:
def MatchPattern(count):
sock = urllib.urlopen(Link+str(count))
htmlSource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
root = etree.HTML(htmlSource)
result = etree.tostring(root, pretty_print=True, method="html")
expr1 = check_reg(root)
expr2 = check_practice(root)
D_expr1 = no_ks(root)
D_expr2 = Registred_by(root)
D_expr3 = Name_doctor(root)
D_expr4 = Registration_no(root)
D_expr5 = PWZL(root)
D_expr6 = NIP(root)
D_expr7 = Spec(root)
D_expr8 = Start_date(root)
#-----Reg_practice-----
R_expr1 = Name_of_practise(root)
R_expr2 = TERYT(root)
R_expr3 = Street(root)
R_expr4 = House_no(root)
R_expr5 = Flat_no(root)
R_expr6 = Post_code(root)
R_expr7 = City(root)
R_expr8 = Practice_no(root)
R_expr9 = Kind_of_practice(root)
#------Serv_practice -----
S_expr1 = TERYT2(root)
S_expr2 = Street2(root)
S_expr3 = House_no2(root)
S_expr4 = Flat_no2(root)
S_expr5 = Post_code2(root)
S_expr6 = City2(root)
S_expr7 = Phone_no(root)
return expr1
return expr2
return D_expr1
return D_expr2
return D_expr3
return D_expr4
return D_expr5
return D_expr6
return D_expr7
return D_expr8
#-----Reg_practice-----
return R_expr1
return R_expr2
return R_expr3
return R_expr4
return R_expr5
return R_expr6
return R_expr7
return R_expr8
return R_expr9
#------Serv_practice -----
return S_expr1
return S_expr2
return S_expr3
return S_expr4
return S_expr5
return S_expr6
return S_expr7
So now inside the script I wanna check value of the expr1 returned by my fynction. I don't know how to do that. Can u guys help me ? Is my function written correct ?
EDIT:
I can't add answer so I edit my current post
This is my all script. Some comments are in my native language but i add some in english
#! /usr/bin/env python
#encoding:UTF-8-
# ----------------------------- importujemy potrzebne biblioteki i skrypty -----------------------
# ------------------------------------------------------------------------------------------------
import urllib
from lxml import etree, html
import sys
import re
import MySQLdb as mdb
from TOR_connections import *
from XPathSelection import *
import os
# ------------------------------ Definiuje xPathSelectors ------------------------------------------
# --------------------------------------------------------------------------------------------------
# -------Doctors -----
check_reg = etree.XPath("string(//html/body/div/table[1]/tr[3]/td[2]/text())") #warunek Lekarz
check_practice = etree.XPath("string(//html/body/div/table[3]/tr[4]/td[2]/text())") #warunek praktyka
no_ks = etree.XPath("string(//html/body/div/table[1]/tr[1]/td[2]/text())")
Registred_by = etree.XPath("string(//html/body/div/table[1]/tr[4]/td[2]/text())")
Name_doctor = etree.XPath("string(//html/body/div/table[2]/tr[2]/td[2]/text())")
Registration_no = etree.XPath("string(//html/body/div/table[2]/tr[3]/td[2]/text())")
PWZL = etree.XPath("string(//html/body/div/table[2]/tr[4]/td[2]/text())")
NIP = etree.XPath("string(//html/body/div/table[2]/tr[5]/td[2]/text())")
Spec = etree.XPath("string(//html/body/div/table[2]/tr[18]/td[2]/text())")
Start_date = etree.XPath("string(//html/body/div/table[2]/tr[20]/td[2]/text())")
#-----Reg_practice-----
Name_of_practise = etree.XPath("string(//html/body/div/table[2]/tr[1]/td[2]/text())")
TERYT = etree.XPath("string(//html/body/div/table[2]/tr[7]/td[2]/*/text())")
Street = etree.XPath("string(//html/body/div/table[2]/tr[8]/td[2]/text())")
House_no = etree.XPath("string(//html/body/div/table[2]/tr[9]/td[2]/*/text())")
Flat_no = etree.XPath("string(//html/body/div/table[2]/tr[10]/td[2]/*/text())")
Post_code = etree.XPath("string(//html/body/div/table[2]/tr[11]/td[2]/*/text())")
City = etree.XPath("string(//html/body/div/table[2]/tr[12]/td[2]/*/text())")
Practice_no = etree.XPath("string(//html/body/div/table[3]/tr[4]/td[2]/text())")
Kind_of_practice = etree.XPath("string(//html/body/div/table[3]/tr[5]/td[2]/text())")
#------Serv_practice -----
TERYT2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[2]/td[2]/*/text())")
Street2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[3]/td[2]/text())")
House_no2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[4]/td[2]/*/text())")
Flat_no2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[5]/td[2]/i/text())")
Post_code2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[6]/td[2]/*/text())")
City2 = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[7]/td[2]/*/text())")
Phone_no = etree.XPath("string(//html/body/div/table[3]/tr[14]/td/table/tr[8]/td[2]/text())")
# --------------------------- deklaracje zmiennych globalnych ----------------------------------
# ----------------------------------------------------------------------------------------------
decrease = 9
No = 1
Link = "http://rpwdl.csioz.gov.pl/rpz/druk/wyswietlKsiegaServletPub?idKsiega="
# --------------------------- funkcje zdefiniowane ----------------------------------
# ----------------------------------------------------------------------------------------------
def MatchPattern(count):
sock = urllib.urlopen(Link+str(count))
htmlSource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
root = etree.HTML(htmlSource)
result = etree.tostring(root, pretty_print=True, method="html")
expr1 = check_reg(root)
expr2 = check_practice(root)
D_expr1 = no_ks(root)
D_expr2 = Registred_by(root)
D_expr3 = Name_doctor(root)
D_expr4 = Registration_no(root)
D_expr5 = PWZL(root)
D_expr6 = NIP(root)
D_expr7 = Spec(root)
D_expr8 = Start_date(root)
#-----Reg_practice-----
R_expr1 = Name_of_practise(root)
R_expr2 = TERYT(root)
R_expr3 = Street(root)
R_expr4 = House_no(root)
R_expr5 = Flat_no(root)
R_expr6 = Post_code(root)
R_expr7 = City(root)
R_expr8 = Practice_no(root)
R_expr9 = Kind_of_practice(root)
#------Serv_practice -----
S_expr1 = TERYT2(root)
S_expr2 = Street2(root)
S_expr3 = House_no2(root)
S_expr4 = Flat_no2(root)
S_expr5 = Post_code2(root)
S_expr6 = City2(root)
S_expr7 = Phone_no(root)
return expr1
return expr2
return D_expr1
return D_expr2
return D_expr3
return D_expr4
return D_expr5
return D_expr6
return D_expr7
return D_expr8
#-----Reg_practice-----
return R_expr1
return R_expr2
return R_expr3
return R_expr4
return R_expr5
return R_expr6
return R_expr7
return R_expr8
return R_expr9
#------Serv_practice -----
return S_expr1
return S_expr2
return S_expr3
return S_expr4
return S_expr5
return S_expr6
return S_expr7
# --------------------------- ustanawiamy polaczenie z baza danych -----------------------------
# ----------------------------------------------------------------------------------------------
con = mdb.connect('localhost', 'root', '******', 'SANBROKER', charset='utf8');
# ---------------------------- początek programu -----------------------------------------------
# ----------------------------------------------------------------------------------------------
with con:
cur = con.cursor()
cur.execute("SELECT Old_num FROM SANBROKER.Number_of_records;")
Old_num = cur.fetchone()
count = Old_num[0]
counter = input("Input number of rows: ")
# ----------------------- pierwsze połączenie z TORem ------------------------------------
# ----------------------------------------------------------------------------------------
#connectTor()
#conn = httplib.HTTPConnection("my-ip.heroku.com")
#conn.request("GET", "/")
#response = conn.getresponse()
#print(response.read())
while count <= counter: # co dziesiata liczba
# --------------- pierwsze wpisanie do bazy danych do Archive --------------------
with con:
cur = con.cursor()
cur.execute("UPDATE SANBROKER.Number_of_records SET Archive_num=%s",(count))
# ---------------------------------------------------------------------------------
if decrease == 0:
MatchPattern(count)
# Now I wanna check some expresions (2 or 3)
# After that i wanna write all the values into my database
#------- ostatnie czynności:
percentage = count / 100
print "rekordów: " + str(count) + " z: " + str(counter) + " procent dodanych: " + str(percentage) + "%"
with con:
cur = con.cursor()
cur.execute("UPDATE SANBROKER.Number_of_records SET Old_num=%s",(count))
decrease = 10-1
count +=1
else:
MatchPattern(count)
# Now I wanna check some expresions (2 or 3)
# After that i wanna write all the values into my database
# ------ ostatnie czynności:
percentage = count / 100
print "rekordów: " + str(count) + " z: " + str(counter) + " procent dodanych: " + str(percentage) + "%"
with con:
cur = con.cursor()
cur.execute("UPDATE SANBROKER.Number_of_records SET Old_num=%s",(count))
decrease -=1
count +=1
Well, I'm assuming check_reg is a function that returns a boolean (either True or False).
If that's the case, to check the return:
if expr1:
print "True."
else:
print "False"
There's more than one way to do it, but basically, if expr1: is all you need to do the checking.
To capture the return value of a function, assign the function to a name with an equal sign, like this:
return_value = somefunction(some_value)
print('The return value is ',return_value)
Keep in mind that when the first return statement is encountered, the function will exit. So if you have more than one return statement after each other, only the first will execute.
If you want to return multiple things, add them to a list and then return the list.
Here is an improved version of your function:
def match_pattern(count):
sock = urllib.urlopen(Link+str(count))
htmlsource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
# root = etree.HTML(htmlSource) - duplicate line
# result = etree.tostring(root, pretty_print=True, method="html")
function_names = [check_reg, check_practice, no_ks, Registered_by, \
Name_doctor, Registration_no, PWZL, NIP, Spec, Start_date, \
Name_of_practise, TERYT, Street, House_no2, Flat_no, \
Post_code2, City2, Phone_no]
results = []
for function in function_names:
results.append(function(root))
return results
r = match_pattern(1)
print r[0] # this will be the result of check_reg(root)
The code you have posted is quite ambigous. Can you please fix the ident to let us know what belongs to the function and which part is the script.
A function can returns only one value. You cannot do :
return something
return something_else
return ...
The function will ends when first value will be returned.
What you can do is returning a list, tuple or dict containing all your values.
For instance :
return (something,something_else,...)
or
return [something,something_else,...]
In your case, it seems better to create a class that would have all values you want as attributes, and turn this function into a method that would set the attributes values.
class Example(object):
def __init__ ( self , link , count ):
sock = urllib.urlopen(link+str(count))
htmlSource = sock.read()
sock.close()
root = etree.HTML(htmlSource)
root = etree.HTML(htmlSource)
result = etree.tostring(root, pretty_print=True, method="html")
self.expr1 = check_reg(root)
self.expr2 = check_practice(root)
self.D_expr1 = no_ks(root)
...
self.D_expr8 = Start_date(root)
#-----Reg_practice-----
self.R_expr1 = Name_of_practise(root)
...
self.R_expr9 = Kind_of_practice(root)
#------Serv_practice -----
self.S_expr1 = TERYT2(root)
...
self.S_expr7 = Phone_no(root)
Then you will be able to use this class like :
exampleInstance = Example ( "link you want to use" , 4 ) # the second argument is your 'count' value
# Now you can use attributes of your class to get the values you want
print exampleInstance . expr1
print exampleInstance . S_expr7