from geopy.geocoders import Nominatim
import openpyxl
wb = openpyxl.load_workbook('#######.xlsx')
ws = wb.active
geolocator = Nominatim(timeout=60)
for i in range(2,1810):
count1 = 0
count2 = 1
address = str(ws['B'+str(i)].value)
city = str(ws['C'+str(i)].value)
state = str(ws['D'+str(i)].value)
zipc = str(ws['F'+str(i)].value)
result = None
iden1 = address + ' ' + city + ' ' + state
iden2 = city + ' ' + zipc + ' ' + state
iden3 = city + ' ' + state
print(iden1, iden2, iden3)
print(geolocator.geocode(iden2).address)
try:
location1 = geolocator.geocode(iden1)
except:
pass
try:
location2 = geolocator.geocode(iden2)
except:
pass
try:
location3 = geolocator.geocode(iden3)
except:
pass
count = None
try:
county1 = str(location1.address)
county1_list = county1.split(", ")
#print(county1_list)
for q in county1_list:
if 'county' in q.lower():
if count == None:
count = q
except:
pass
try:
county2 = str(location2.address)
county2_list = county2.split(", ")
#print(county2_list)
for z in county2_list:
if 'county' in z.lower():
if count == None:
count = z
except:
pass
try:
county3 = str(location3.address)
county3_list = county3.split(", ")
#print(county3_list)
for j in county3_list:
if 'county' in j.lower():
if count == None:
count = j
except:
pass
print(i, count)
#ws['E'+str(i)] = count
if count == 50:
#wb.save("#####" +str(count2) +".xlsx")
count2 += 1
count1 = 0
Hello all, this code is pretty simple and uses geopy to extract county names using 3 different methods names iden1, iden2, and iden3 which are a combination of address, city, state, and zipcode. This ran fine for about 300 lines but began to repeat the same county, and after restarting the script, just spat out Nones. I put in the line print (geolocator.geocode(iden2).address) to find the error and got this error message.
Traceback (most recent call last):
File "C:/Users/#####/Downloads/Web content/#####/####_county.py",
line 19, in
print(geolocator.geocode(iden2).address) File "C:\Users#####\AppData\Local\Programs\Python\Python36-32\lib\site-packages\geopy\geocoders\osm.py",
line 193, in geocode
self._call_geocoder(url, timeout=timeout), exactly_one File "C:\Users#####\AppData\Local\Programs\Python\Python36-32\lib\site-packages\geopy\geocoders\base.py",
line 171, in _call_geocoder
raise GeocoderServiceError(message) geopy.exc.GeocoderServiceError: [WinError 10061] No connection could
be made because the target machine actively refused it
This script was working before but now does not. Is my IP being blocked from using goepy's database or something? Thanks for your help!
It looks like you're hitting their ratelimiting. It seems that they ask that you limit your API requests to 1/second. You can take a look here for their usage policy where they list alternatives to using their API as well as contraints.
Related
I was trying to make a basic data collector that will put information in excel and i was successful at doing so with the titles of the data sets but i cant figure out why it cant write the data entered into an excel file. Its far from done and i am fairly new to python (about a month into learning) so if my code looks terrible then my apologies but for any help thank you.
below is my full code and the error message along with it:
import xlsxwriter
import os
file = open("Datasheet.xlsx", "w+")
databook = xlsxwriter.Workbook("Datasheet.xlsx")
data = databook.add_worksheet()
titles = []
masterdata = {}
data_entry = 0
data_filled = 0
project_start = True
while project_start == True:
data_entires = input("How many data entries will you need? ")
if data_entires.isdigit() == False:
print("Sorry that is not a valid input please enter a numerical integer")
project_start = True
if data_entires.isdigit() == True:
project_start = False
while int(data_entires) != data_entry:
data_title = input("Please enter a title for a dataset ")
titles.append(data_title)
data_entry += 1
for value in range(len(titles)):
data.write(0, value + 1, titles[value])
# dictionary with created lists for the amount of titles made
for i in range(len(titles)):
dict = masterdata["list " + str(i + 1)] = []
for i in range(len(masterdata)):
data_in = True
while data_in == True:
data = input(f"Please input data for {titles[i]} ")
data_fill = masterdata["list " + str(i + 1)].append(data)
fin = input("Do you want to input more data? ")
if "yes" in fin:
data_in = True
if "no" in fin:
data_in = False
lis = [list(x) for x in masterdata.values()]
for part in lis:
l = list(str(part))
for value in l:
data.write(value + 1, value + 1, l[value])
#os.startfile("Datasheet.xlsx")
#databook.close()
Error message : "Traceback (most recent call last):
File "f'{filelocation}'", line 49, in
data.write(value + 1, value + 1, l[value])
AttributeError: 'str' object has no attribute 'write' "
I have a project I'm working on where I would like to query MariaDB via a file line by line. It is all written in python. The problem I'm having is it will only print the last line if found, not all matches. My expectation is that it prints to the terminal every time it finds a match. Any help is greatly appreciated.
import mysql.connector
import time
file1 = open("sample.unique.big", "r")
count = 0
mydb = mysql.connector.connect(
host="10.0.0.72",
user="admin",
password="#########",
database="#########"
)
start = time.time()
while True:
count += 1
# Get next line from file
line = file1.readline()
# if line is empty
# end of file is reached
if not line:
break
#print("{}".format(line.strip()))
#print("Line{}: {}".format(count, line.strip()))
mycursor = mydb.cursor()
sql = "SELECT * FROM ether2 use index (idx_privadd) WHERE privadd = %s"
adr = (line, )
mycursor.execute(sql, adr)
myresult = mycursor.fetchall()
for x in myresult:
print(x)
end = time.time()
print(end-start)
i achieved my desired results by first formating the readline. Secondly, an if statement for myresults. Completed code looks like
import mysql.connector
import time
file1 = open("sample.unique.big", "r")
count = 0
mydb = mysql.connector.connect(
host="10.0.0.72",
user="*****",
password="*****",
database="etherpro"
)
start = time.time()
while True:
count += 1
# Get next line from file
line = file1.readline()
#Format the line
search=("{}".format(line.strip()))
# if line is empty
# end of file is reached
if not line:
break
mycursor = mydb.cursor()
sql = "SELECT id FROM ether2 WHERE privadd = %s"
adr = (search, )
mycursor.execute(sql, adr)
myresults = mycursor.fetchone()
if myresults:
print("oh snap, the id is:",myresults)
end = time.time()
print(end-start)
I currently host the English Amiga Board (EAB) FTP, a FTP server filled with the classic Amiga computer goodies. It is open to everyone but users can also register their own account. I got help in creating a python script that checks that the username being registered at the FTP is a valid account on the EAB forums and that it has at least 50 posts.
However, I've now updated the server (fedora server) and the Python version was updated to 3.7.6. The script have now stopped working and I'm unable to reach the original author.
# python ./eab_post_count.py -u Turran
Traceback (most recent call last):
File "./eab_post_count.py", line 3, in <module>
import sys, re, urllib2
ModuleNotFoundError: No module named 'urllib2'
This script should return "0" if the user exists and have 50 posts.
While I script in some languages, python is not one of them so I would be grateful for any help to modify it to not use urllib2, which I understand is no longer valid for Python 3.
The script:
#!/usr/bin/env python
import sys, re, urllib2
titlecmd = "eab_post_count.py"
version = "1.15"
ignorecase = 0
lastpost = 0
userfound = False
if len(sys.argv) == 1: sys.argv[1:] = ["-h"]
def parseurl(url):
if not url:
print("Empty URL!")
sys.exit(3)
headers = { 'User-Agent' : 'Mozilla/5.0' }
request = urllib2.Request(url, None, headers)
try:
response = urllib2.urlopen(request)
except Exception:
print('URL open failed, EAB down?')
sys.exit(2)
content = response.read()
return content
def pagesearch(content, trigger, start, end):
sane = 0
needlestack = []
while sane == 0:
curpos = content.find(trigger)
if curpos >= 0:
testlen = len(content)
content = content[curpos:testlen]
curpos = content.find('"')
testlen = len(content)
content = content[curpos+1:testlen]
curpos = content.find(end)
needle = content[0:curpos]
result = content[len(start):curpos]
if needle.startswith(start):
needlestack.append(result)
else:
sane = 1
return needlestack
def unescape(s):
s = s.replace("<", "<")
s = s.replace(">", ">")
# this has to be last:
s = s.replace("&", "&")
return s
for idx, arg in enumerate(sys.argv):
if arg == '-h':
print(titlecmd + ' v' + version +' by modrobert in 2017')
print('Function: Returns the number of posts for a given EAB forum user.')
print('Syntax : ' + titlecmd + ' -u <username> [-i] [-l YYYY-MM-DD]')
print('Options : -h this help text.')
print(' : -i ignore case sensivity in user name.')
print(' -l last post after YYYY-MM-DD required.')
print(' -u followed by user name.')
print('Result : 0 = user found, 1 = user not found, 2 = EAB down, 3 = other fail.')
sys.exit(3)
if arg == '-u':
try:
username = sys.argv[idx+1]
except IndexError:
print('Missing username.')
sys.exit(3)
usernameurl = re.sub('[ ]', '%20', username)
if arg == '-i':
ignorecase = 1
if arg == '-l':
lastpost = 1
try:
lpdate = sys.argv[idx+1]
except IndexError:
print('Missing date.')
sys.exit(3)
try:
username
except NameError:
print('Username -u option required.')
sys.exit(3)
if lastpost:
eaburl = "http://eab.abime.net/memberlist.php?do=getall&pp=100&lastpostafter=" + lpdate + "&ausername=" + usernameurl
else:
eaburl = "http://eab.abime.net/memberlist.php?do=getall&pp=100&ausername=" + usernameurl
eabcontent = parseurl(eaburl)
countlist = pagesearch(eabcontent, 'td class', 'alt2">', '</td>')
userlist = pagesearch(eabcontent, 'member.php?', '>', '</a>')
for idx, item in enumerate(userlist):
# lets strip those fancy moderators and admins
userstr = re.sub('<[^<]+?>', '', item)
if ignorecase:
if unescape(str.lower(userstr)) == str.lower(username):
userfound = True;
break
else:
if unescape(str(userstr)) == username:
userfound = True;
break
if userfound == False:
print("User not found: " + username)
sys.exit(1)
usercount = idx
for idx, item in enumerate(countlist):
# hairy stuff below ;)
if idx < (3 * usercount):
continue
stripitem = re.sub('[,]', '', item)
try:
print(int(stripitem))
sys.exit(0)
except Exception:
continue
Thanks in advance!
outlook = Dispatch("Outlook.Application")
mapi = outlook.GetNamespace("MAPI")
your_folder = mapi.Folders['email#outlook.com'].Folders['Blah']
blah_inbox = your_folder.Items
f = open("email_txt.csv", "w")
for message in blah_inbox:
if message.Class == 43:
if message.SenderEmailType == 'EX':
print(message.Sender.GetExchangeUser().PrimarySmtpAddress)
f.write(message.Sender.GetExchangeUser().PrimarySmtpAddress)
else:
print(message.SenderEmailAddress)
I opened a new fie and wrote it to a csv, but I get the following result.
user1#outlook.comuser2#outlook.comuser3#outook.com.....
However, I need the result to be like the below
user1#outlook.com
user2#outlook.com
user3#outlook.com
The Simple solution is the following
f = open("email_txt.csv", "w")
for message in blah_inbox:
if message.Class == 43:
if message.SenderEmailType == 'EX':
print(message.Sender.GetExchangeUser().PrimarySmtpAddress)
f.write(message.Sender.GetExchangeUser().PrimarySmtpAddress + '\n')
else:
print(message.SenderEmailAddress)
I added a "\n" to the end of the write command
Alternatively, since my whole intention was to save in a CSV with some sort of headers. Below is what worked for me. This is the entire code.
Todays_Mail = dt.datetime.now() - dt.timedelta(hours=24)
Todays_Mail = Todays_Mail.strftime('%m/%d/%Y %H:%M %p')
# Connect to Outlook inbox
outlook = Dispatch("Outlook.Application")
mapi = outlook.GetNamespace("MAPI")
your_folder = mapi.Folders['email'].Folders['Blah']
blah_inbox = your_folder.Items
blah_inbox = blah_inbox.Restrict("[ReceivedTime] >= '" + Todays_Mail + "'")
f = open("email.csv", "w")
f.write('Emails,Index\n')
index = 0
for message in blah_inbox:
if message.Class == 43:
if message.SenderEmailType == 'EX':
print(message.Sender.GetExchangeUser().PrimarySmtpAddress)
f.write(message.Sender.GetExchangeUser().PrimarySmtpAddress + ',' + str(index) + '\n')
index = index + 1
else:
print(message.SenderEmailAddress)
f.close()
The above will give you two columns, one with the header Email, and the second would be a column with the header Index.
experts
I meet an value missing error in my code , but I think the variable in function are claimed. I don't know why it is happens.
$ python check_rsg_V0312.py
2018-03-20 13:05:49 === Script Start ===
2018-03-20 13:05:49 Monitoring via remote logon
The authenticity of host 'rpahost0 ([127.0.0.1]:7000)' can't be established.
RSA key fingerprint is 2d:f5:67:75:84:b6:24:45:e6:48:60:65:61:ca:69:f7.
Are you sure you want to continue connecting
(yes/no)? yes
Warning: Permanently added 'rpahost0' (RSA) to the list of known hosts.
Password:
Traceback (most recent call last):
File "check_rsg_V0312.py", line 89, in <module>
label = ssh_cmd(nLocalport, rsg_target, ouser, lookip, opasw, command,)
File "check_rsg_V0312.py", line 79, in ssh_cmd
print (ssh.before.decode(),ssh.after().decode())
TypeError: __init__() missing 1 required positional argument: 'value'
Below is my code, it is really strange that one error happens in ssh_cmd
function. detailed please review comments in code.
import os,time,pexpect,re, subprocess, smtplib
from email import encoders
from email.header import Header
from email.mime.text import MIMEText
#-----------------------------------------
dir = os.environ['HOME']
ouser = 'x02d726'
opasw = 'qwe12'
nLocalport = 7000
lookip = '127.0.0.1'
rsg_target = "rpahost0"
command = "ls -ltrh | grep tunnel | tail"
nstage = 0
mail_addr = 'cheng.huang#qq.com'
otp_file = dir + '/otplist/C591260'
otp_list = []
rsg_file = dir + '/.rsg_hosts'
known_hosts = dir + '/.ssh/known_hosts'
rsg_port = "auto"
#-----------------------------------------
def printlog(prompt):
year, mon, mday, hour, min, sec, wday, yday, isdst = time.localtime()
print("%04d-%02d-%02d %02d:%02d:%02d %s" % (year, mon , mday, hour, min,
sec, prompt))
def get_egw_name(ref_arr, key):
for oneline in ref_arr:
if (re.search(key, oneline)):
templine = oneline
oneline = re.sub('^\s+|\s+$','',oneline)
egw_ssg = re.split('\s+',oneline)[2]
result = re.split(':',egw_ssg)[0]
return result
def sendworker(to_addr):
from_addr = 'itk-bj.ericsson.se'
smtp_server = 'smtp.eamcs.ericsson.se'
msg = MIMEText('There is no otp left ,please input new OTP list',
'plain', 'utf-8')
msg['From'] = from_addr
msg['To'] = to_addr
msg['Subject'] = Header(u'OTP List is Blank', 'utf-8')
server = smtplib.SMTP(smtp_server, 25)
#server.set_debuglevel(1)
server.sendmail(from_addr, to_addr, msg.as_string())
server.quit()
def ssh_cmd(port, target, user, ip, pasw, cmd ):
printlog("=== Script Start ===")
printlog("Monitoring via remote logon")
time.sleep(1)
ssh = pexpect.spawn('/usr/bin/ssh -p %s -o HostKeyAlias=%s %s#%s %s' %
(port, target, user, ip, cmd ),timeout=6000)
try:
i = ssh.expect(['Password: ', 'continue connecting (yes/no)?'],
timeout=15)
if i == 0 :
print(ssh.before.decode(),ssh.after.decode())
ssh.sendline(pasw)
elif i == 1:
print(ssh.before.decode(),ssh.after.decode())
ssh.sendline('yes')
ssh.expect('Password: ')
print(ssh.before.decode(),ssh.after.decode())
ssh.sendline(pasw)
except pexpect.EOF:
print ("no connection EOF,please check RSG tunnel")
except pexpect.TIMEOUT:
print ("your pexpect has TIMEOUT")
else:
ssh.expect(pexpect.EOF)
print (ssh.before.decode(),ssh.after().decode()) # if I disable this line, there will be no error.
flag = ssh.before.decode()
return flag
ssh.close()
if __name__ == '__main__':
if os.path.exists(os.environ['HOME'] + "/.ssh/known_hosts"):
os.remove(known_hosts)
else:
pass
label = ssh_cmd(nLocalport, rsg_target, ouser, lookip, opasw, command)
if re.search('tunnel_check', str(label)):
nstage = 1
if (nstage == 0):
printlog("Tunnel was down and will re-establish now\n")
rsg = open (rsg_file,'r')
rsg_in = rsg.readlines()
rsg.close()
egwname = get_egw_name(rsg_in, rsg_target)
try :
otp = open(otp_file, 'r')
otp_arrary = otp.readlines()
otp.close()
for ot in otp_arrary:
ot = ot.strip()
ot = ot.replace('^\s*|\s*$', '')
otp_list.append(ot)
otp_num = len(otp_list) + 1
if (otp_num > 0):
os.remove(rsg_file)
try :
new_otp = otp_list[0]
except IndexError:
printlog('There is no otp left ,please input new OTP list')
sendworker(mail_addr)
sys.exit()
else:
out = open(rsg_file, 'w')
for line in rsg_in :
line = line.strip()
line = line.replace('^\s+|\s+$','')
if (re.match(egwname, line)):
temp_line = line
old_otp = re.split('\s+',temp_line)[5]
old_otp = old_otp.replace('^\s+|\s+$', '')
line = line.replace(old_otp, new_otp).replace('\\','')
printlog(line + "\n")
out.write(line + "\n")
out.close()
os.remove(otp_file)
time.sleep(1)
outotp = open(otp_file , 'w+')
i = 0
while (i < len(otp_list)):
outotp.write(otp_list[i] + "\n")
i += 1
outotp.close()
os.system("pkill -9 -f \"ssh\.\*-L " + str(nLocalport) + "\"")
os.system("sleep 10")
os.system("pkill -9 -f \"rtunnel\.\*-p " + str(nLocalport) + "\"")
os.system("nohup /opt/ericsson/itk/bin/rtunnel -d -q -g -p " + str(nLocalport) + "-rp auto " + rsg_target + " &")
os.system("sleep 10")
printlog("Kill the rtunnel process\n");
printlog("Tunnel is re-established again\n");
else:
sendworker(mail_addr)
except IOError:
print ("File is not accessible.")
else:
printlog("Tunnel OK")
As you see , after disable the line in Try... else... block, the code will be OK.
else:
ssh.expect(pexpect.EOF)
print (ssh.before.decode(),ssh.after().decode()) # if I disable this line, there will be no error.
flag = ssh.before.decode()
return flag
If you look carefully your traceback, you will find the problem:
Instead of:
print (ssh.before.decode(),ssh.after().decode())
you should write
print (ssh.before.decode(),ssh.after.decode())
after is a method which return string, not a function.
BTW, I think you should put decoding/encoding in your pexpect constructor.