I'm writing a script to sent proxies file from a directory to telegram channel. With the help of some good folks I was able to complete it almost
from telegram import Bot, InputMediaDocument
BOT_TOKEN = "xxx"
CHAT_ID = xxx
def main():
bot = Bot(BOT_TOKEN)
file_paths = (
"proxy/proxies/http.txt",
"proxy/proxies/socks4.txt",
"proxy/proxies/socks5.txt"
)
path_http = "proxy/proxies/http.txt"
with open(path_http,'rb') as file_http:
http_count = len(file_http.readlines())
file_http.close()
path_socks4 = 'proxy/proxies/socks4.txt'
with open(path_socks4,'rb') as file_socks4:
socks4_count = len(file_socks4.readlines())
file_socks4.close()
path_socks5 = 'proxy/proxies/socks5.txt'
with open(path_socks5,'rb') as file_socks5:
socks5_count = len(file_socks5.readlines())
file_socks5.close()
text = f"Total HTTPs:{http_count}\nTotal SOCKS4:{socks4_count}\nTotal SOCKS5:{socks5_count}"
media_group = list()
for f in file_paths:
with open(f, "rb") as fin:
caption = text if f == "proxy/proxies/http.txt" else ''
fin.seek(0)
media_group.append(InputMediaDocument(fin, caption=caption))
bot.send_media_group(CHAT_ID, media=media_group)
if __name__ == "__main__":
main()
Issues occurred
media_group = list()
^
IndentationError: unindent does not match any outer indentation level
what I'm trying is to send those 3 proxy files with a caption to the first proxy file
There are a few issues with your code:
The lack of proper indentation
Improper closing of brackets
The SyntaxError that you're getting on the line path_http = 'proxy/proxies/http.txt' is because you didn't close the brackets from the previous line (the line where you initialised the variable file_paths).
I also foresee that you'll face issues when you try to open the file with the open function. You can look up some examples here: https://www.programiz.com/python-programming/file-operation
with the help of some good folks I make it work, If there are any easy versions fell free to share
from telegram import Bot, InputMediaDocument
BOT_TOKEN = "xxxxx"
CHAT_ID = -1000000
def http():
path_http = 'proxy/proxies/http.txt'
with open(path_http, 'rb') as file_http:
http_count = len(file_http.readlines())
return http_count
def socks4():
path_socks4 = 'proxy/proxies/socks4.txt'
with open(path_socks4, 'rb') as file_socks4:
socks4_count = len(file_socks4.readlines())
return socks4_count
def socks5():
path_socks5 = 'proxy/proxies/socks5.txt'
with open(path_socks5, 'rb') as file_socks5:
socks5_count = len(file_socks5.readlines())
return socks5_count
http_count = http()
socks4_count = socks4()
socks5_count = socks5()
text = f"Total HTTPs:{http_count}\nTotal SOCKS4:{socks4_count}\nTotal SOCKS5: {socks5_count}"
def main():
bot = Bot(BOT_TOKEN)
file_paths = (
"proxy/proxies/http.txt",
"proxy/proxies/socks4.txt",
"proxy/proxies/socks5.txt"
)
media_group = list()
for f in file_paths:
with open(f, "rb") as fin:
caption = text if f == "proxy/proxies/socks5.txt" else ''
fin.seek(0)
media_group.append(InputMediaDocument(fin, caption=caption))
bot.send_media_group(CHAT_ID, media=media_group)
if __name__ == "__main__":
main()
`file_paths = (
"proxy/proxies/http.txt",
"proxy/proxies/socks4.txt",
"proxy/proxies/socks5.txt"
`
invalid syntax error probably because ) doesn't exist in the end.
try adding (" ") caption = text if f == "proxy/proxies/http.txt" else '' because it is a string.
I have been trying to save a CSV file with information to add to db. And, is necessary to remove the single quotes, and ")". I already tried doing the replace but, didn't worked.
Also, I am doing this by an admin view. I add the csv file with informations to create objects on my db. And, it's from multiple tables. I don't know if I am using the right code or logic for this.
def upload_csv(self,request):
form = CSVImportForm(request.POST, request.FILES)
if request.method == "POST":
csv_file = request.FILES['csv_upload']
file_data = csv_file.read().decode("utf-8")
csv_data = file_data.split("\n")
csv_data = file_data.replace("'", "")
try :
for x in csv_data:
fields = x.split(",")
print(fields)
create_hospital = {}
create_hospital['hospital_name'] = fields[0],
create_hospital['hospital_website'] = fields[1],
create_hospital['hospital_fiscalAddress'] = fields[2],
create_hospital['hospital_shippingAddress'] = fields[3],
create_hospital['hospital_region'] = fields[4],
create_hospital['country'] = fields[5],
create_hospital['hospital_contactPerson'] = fields[6],
create_hospital['hospital_contactPhone'] = fields[7],
create_hospital['hospital_contactEmail'] = fields[8],
create_hospital['hospital_ImageLogo'] = fields[9]
created_hospital = HospitalViewRoleForUsers.objects.create(**create_hospital)
create_users = {}
create_users['FKLab_User'] = fields[0],
create_users['user_type'] = "1",
create_users['email'] = fields[11],
create_users['password'] = BaseUserManager().make_random_password(8),
create_users['name'] = fields[10],
# create_users['FKLab_User'] = created_hospital.id
# create_users['user_type'] = "1"
# create_users['email'] = fields[14],
# create_users['password'] = BaseUserManager().make_random_password(8),
# create_users['name'] = fields[13],
# create_users['FKLab_User'] = created_hospital.id
# create_users['user_type'] = "1"
# create_users['email'] = fields[17],
# create_users['password'] = BaseUserManager().make_random_password(8),
# create_users['name'] = fields[16],
created_users = CustomUser.objects.bulk_create(create_users)
create_roles = {}
create_roles['user_id'] = created_users[0],
create_roles['roles'] = fields[12],
created_roles = RoleHospital.objects.create(create_roles)
except Exception as e:
print("%s", e)
data = {"form": form}
return render(request, "admin/csv_upload.html", data)
Things are being add, except the fact that it adds with single quote and parenthesis.
e.g. : ('salkdklas',)
Thank you.
I would like to create different Word-Documents using a template and an excel-input-file.
So I read the xlsx-file, change the content of the template, and want to save several Docx-files. I use the following code which generally works fine for the first document (anything gets replaced and stored as expected). But in the following documents, there is always the same content as in the first document. I tried to reassign the for every row in the excel-sheet the document with
docWork = doc
But it seems that somehow this initialization is not working.
This is the full code I am using:
from docx import Document
import os, sys
import xlwings as xw
import time
from DateTime import DateTime
if __name__ == '__main__':
print(f"Start Program V8...")
SAVE_INTERVAL = 5
WAIT = 3
FN = "dataCreateCover.xlsx"
path = os.path.abspath(os.path.dirname(sys.argv[0]))
fn = os.path.join(path, FN)
print(f"Read {fn}...")
wb = xw.Book (fn)
ws = wb.sheets[0]
inpData = ws.range ("A2:Z5000").value
inpData = [x for x in inpData if x[0] != None]
tday = str(datetime.today().date())
print(f"Read DOCX-Files...")
FNDOC = "template.docx"
fnDoc = os.path.join(path, FNDOC)
print(f"Path for DOCX: {fnDoc}...")
doc = Document(fnDoc)
for elem in inpData:
dictWords = {}
docWork = doc
elem = [x for x in elem if x != None]
for idxElem, valElem in enumerate(elem):
dictWords[f"[section{idxElem + 1}]"] = valElem
for idx,para in enumerate(docWork.paragraphs):
for k,v in dictWords.items():
if k in para.text:
inline = para.runs
for item in inline:
if k in item.text:
item.text = item.text.replace(k, v)
print(f"Replaced {k} with {v}...")
break
docFN = f"{tday}_{elem[1]}.docx"
docWork.save(docFN)
print(f"Document <{docFN}> created - pls press <enter> to close the window...")
How can I use the docx-template and write different word-docs as output?
I am creating my own bootloader for an ATXmega128A4U. To use the bootloader I want to transform the ELF-file of the firmware into a memory map used in the the ATXmega.
For that I use python and the modul "pyelftools". The documentation of it is poor and so I run into a problem: I do not know what information I can use to get the address, offset etc. from the data at the sections.
My goal is to create a bytearray, copy the data/code into it and transfer it to the bootlaoder. Below is my code:
import sys
# If pyelftools is not installed, the example can also run from the root or
# examples/ dir of the source distribution.
sys.path[0:0] = ['.', '..']
from elftools.common.py3compat import bytes2str
from elftools.elf.elffile import ELFFile
# 128k flash for the ATXmega128a4u
flashsize = 128 * 1024
def process_file(filename):
with open(filename, 'rb') as f:
# get the data
elffile = ELFFile(f)
dataSec = elffile.get_section_by_name(b'.data')
textSec = elffile.get_section_by_name(b'.text')
# prepare the memory
flashMemory = bytearray(flashsize)
# the data section
startAddr = dataSec.header.sh_offset
am = dataSec.header.sh_size
i = 0
while i < am:
val = dataSec.stream.read(1)
flashMemory[startAddr] = val[0]
startAddr += 1
i += 1
# the text section
startAddr = textSec.header.sh_offset
am = textSec.header.sh_size
i = 0
while i < am:
print(str(startAddr) + ' : ' + str(i))
val = textSec.stream.read(1)
flashMemory[startAddr] = val[0]
startAddr += 1
i += 1
print('finished')
if __name__ == '__main__':
process_file('firmware.elf')
Hope someone can tell me how to solve this problem.
I manged to solve the problem.
don't read the data manualy from the stream by "textSec.stream.read" use "textSec.data()" instead. Internaly (see "sections.py") a seek operation in the file is done. Afterwards the data is read. The result will be the valid data chunk.
The following code reads the code(text) section of a atxmega firmware and copies it into a bytearray which has the layout of the flash of an atxmega128a4u device.
#vlas_tepesch: the hex conversation is not needed and the the 64k pitfall is avoided.
sys.path[0:0] = ['.', '..']
from elftools.common.py3compat import bytes2str
from elftools.elf.elffile import ELFFile
# 128k flash for the ATXmega128a4u
flashsize = 128 * 1024
def __printSectionInfo (s):
print ('[{nr}] {name} {type} {addr} {offs} {size}'.format(
nr = s.header['sh_name'],
name = s.name,
type = s.header['sh_type'],
addr = s.header['sh_addr'],
offs = s.header['sh_offset'],
size = s.header['sh_size']
)
)
def process_file(filename):
print('In file: ' + filename)
with open(filename, 'rb') as f:
# get the data
elffile = ELFFile(f)
print ('sections:')
for s in elffile.iter_sections():
__printSectionInfo(s)
print ('get the code from the .text section')
textSec = elffile.get_section_by_name(b'.text')
# prepare the memory
flashMemory = bytearray(flashsize)
# the text section
startAddr = textSec.header['sh_addr']
val = textSec.data()
flashMemory[startAddr:startAddr+len(val)] = val
# print memory
print('finished')
if __name__ == '__main__':
process_file('firmware.elf')
Tanks for the comments!
The task:
The firm I have gotten a summer-job for has an expanding test-database that consists of an increasing number of subfolders for each project, that includes everything from .jpeg files to the .xlsx's I am interested in. As I am a bit used to Python from earlier, I decided to give it a go at this task. I want to search for exceldocuments that has "test spreadsheet" as a part of its title(for example "test spreadsheet model259"). All the docs I am interested in are built the same way(weight is always "A3" etc), looking somewhat like this:
Model: 259
Lenght: meters 27
Weight: kg 2500
Speed: m/s 25
I want the user of the finished program to be able to compare results from different tests with each other using my script. This means that the script must see if there is an x-value that fits both criteria at once:
inputlength = x*length of model 259
inputweight = x*weight of model 259
The program should loop through all the files in the main folder. If such an X exists for a model, I want the program to return it to a list of fitting models. The x-value will be a variable, different for each model.
As the result I want a list of all files that fits the input, their scale(x-value) and possibly a link to the file.
For example:
Model scale Link
ModelA 21.1 link_to_fileA
ModelB 0.78 link_to_fileB
The script
The script I have tried to get to work so far is below, but if you have other suggestions of how to deal with the task I'll happily accept them. Don't be afraid to ask if I have not explained the task well enough. XLRD is already installed, and I use Eclipse as my IDE. I've been trying to get it to work in many ways now, so most of my script is purely for testing.
Edited:
#-*- coding: utf-8 -*-
#Accepts norwegian letters
import xlrd, os, fnmatch
folder = 'C:\eclipse\TST-folder'
def excelfiles(pattern):
file_list = []
for root, dirs, files in os.walk(start_dir):
for filename in files:
if fnmatch.fnmatch(filename.lower(), pattern):
if filename.endswith(".xls") or filename.endswith(".xlsx") or filename.endswith(".xlsm"):
file_list.append(os.path.join(root, filename))
return file_list
file_list = excelfiles('*tst*') # only accept docs hwom title includes tst
print excelfiles()
How come I only get one result when I am printing excelfiles() after returning the values, but when I exchange "return os.path.join(filename)" with "print os.path.join(filename)" it shows all .xls files? Does this mean that the results from the excelfiles-function is not passed on? Answered in comments
''' Inputvals '''
inputweight = int(raw_input('legg inn vekt')) #inputbox for weight
inputlength = int(raw_input('legg inn lengd')) #inputbox for lenght
inputspeed = int(raw_input('legg inn hastighet')) #inputbox for speed
'''Location of each val from the excel spreadsheet'''
def locate_vals():
val_dict = {}
for filename in file_list:
wb = xlrd.open_workbook(os.path.join(start_dir, filename))
sheet = wb.sheet_by_index(0)
weightvalue = sheet.cell_value(1, 1)
lenghtvalue = sheet.cell_value(1, 1)
speedvalue = sheet.cell_value(1, 1)
val_dict[filename] = [weightvalue, lenghtvalue, speedvalue]
return val_dict
val_dict = locate_vals()
print locate_vals()
count = 0
Any ideas of how I can read from each of the documents found by the excelfiles-function? "funcdox" does not seem to work. When I insert a print-test, for example print weightvalue after the weightvalue = sheet.cell(3,3).value function, I get no feedback at all. Errormessages without the mentioned print-test:Edited to the script above, which creates a list of the different values + minor changes that removed the errormessages
Script works well until this point
Made some minor changes to the next part. It is supposed to scale an value from the spreadsheet by multiplying it with a constant (x1). Then I want the user to be able to define another inputvalue, which in turn defines another constant(x2) to make the spreadsheetvalue fit. Eventually, these constants will be compared to find which models will actually fit for the test.
'''Calculates vals from excel from the given dimensions'''
def dimension(): # Maybe exchange exec-statement with the function itself.
if count == 0:
if inputweight != 0:
exec scale_weight()
elif inputlenght != 0:
exec scale_lenght()
elif inputspeed != 0:
exec scale_speed()
def scale_weight(x1, x2): # Repeat for each value.
for weightvalue in locate_vals():
if count == 0:
x1 * weightvalue == inputweight
count += 1
exec criteria2
return weightvalue, x1
elif count == 2:
inputweight2 = int(raw_input('Insert weight')) #inputbox for weight
x2 * weightvalue == inputweight2
return weightvalue, x2
The x1 and x2 are what I want to find with this function, so I want them to be totally "free". Is there any way I can test this function without having to insert values for x1 and x2 ?
def scale_lenght(): # Almost identical to scale_weight
return
def scale_speed(): # Almost identical to scale_weight
return
def criteria2(weight, lenght, speed):
if count == 1:
k2 = raw_input('Criteria two, write weight, length or speed.')
if k2 == weight:
count += 1
exec scale_weight
elif k2 == lenght:
count += 1
exec scale_lenght
elif k2 == speed:
count += 1
exec scale_speed
else:
return
Do you see any easier way to deal with this problem?(Hope I managed to explain it well enough. The way I have written the code so far is quite messy, but since I'm not that experienced I'll just have to make it work first, and then clean it up if I have the time.
Since probably none of the values will exactly fit for both x-constants, I thought I'd use approx_Equal to deal with it:
def approx_Equal(x1, x2, tolerance=int(raw_input('Insert tolerance for scaling difference')),err_msg='Unacceptable tolerance', verbose = True ): # Gives the approximation for how close the two values of x must be for
if x1 == x2:
x = x1+ (x2-x1)/2
return x
Eventually, I'd like a diagram of all the variables used + a link-to-file and name for each document.
No sure how I will do this, so any tips are greatly appreciated.
Thanks!
In answer to the first question "How come I only get one result when I am printing excelfiles()" this is because your return statement is within the nested loop, so the function will stop on the first iteration. I would try building up a list instead and then return this list, you could also combine this with the issue of checking the name e.g. :
import os, fnmatch
#globals
start_dir = os.getenv('md')
def excelfiles(pattern):
file_list = []
for root, dirs, files in os.walk(start_dir):
for filename in files:
if fnmatch.fnmatch(filename.lower(), pattern):
if filename.endswith(".xls") or filename.endswith(".xlsx") or filename.endswith(".xlsm"):
file_list.append(os.path.join(root, filename))
return file_list
file_list = excelfiles('*cd*')
for i in file_list: print i
Obviously, you'll need to replace the cd with your own search text, but keep the * either side and replace the start_dir with your own. I have done the match on filename.lower() and entered the search text in lower case to make the matching case in-sensitive, just remove the .lower() if you don't want this. I have also allowed for other types of Excel files.
Regarding reading data from Excel files I have done this before to create an automated way of converting basic Excel files into csv format. You are welcome to have a look at the code below and see if there is anything you can use from this. The xl_to_csv function is where the data is read from the Excel file:
import os, csv, sys, Tkinter, tkFileDialog as fd, xlrd
# stop tinker shell from opening as only needed for file dialog
root = Tkinter.Tk()
root.withdraw()
def format_date(dt):
yyyy, mm, dd = str(dt[0]), str(dt[1]), str(dt[2])
hh, mi, ss = str(dt[3]), str(dt[4]), str(dt[5])
if len(mm) == 1:
mm = '0'+mm
if len(dd) == 1:
dd = '0'+dd
if hh == '0' and mi == '0' and ss == '0':
datetime_str = dd+'/'+mm+'/'+yyyy
else:
if len(hh) == 1:
hh = '0'+hh
if len(mi) == 1:
mi = '0'+mi
if len(ss) == 1:
ss = '0'+ss
datetime_str = dd+'/'+mm+'/'+yyyy+' '+hh+':'+mi+':'+ss
return datetime_str
def xl_to_csv(in_path, out_path):
# set up vars to read file
wb = xlrd.open_workbook(in_path)
sh1 = wb.sheet_by_index(0)
row_cnt, col_cnt = sh1.nrows, sh1.ncols
# set up vars to write file
fileout = open(out_path, 'wb')
writer = csv.writer(fileout)
# iterate through rows and cols
for r in range(row_cnt):
# make list from row data
row = []
for c in range(col_cnt):
#print "...debug - sh1.cell(",r,c,").value set to:", sh1.cell(r,c).value
#print "...debug - sh1.cell(",r,c,").ctype set to:", sh1.cell(r,c).ctype
# check data type and make conversions
val = sh1.cell(r,c).value
if sh1.cell(r,c).ctype == 2: # number data type
if val == int(val):
val = int(val) # convert to int if only no decimal other than .0
#print "...debug - res 1 (float to str), val set to:", val
elif sh1.cell(r,c).ctype == 3: # date fields
dt = xlrd.xldate_as_tuple(val, 0) # date no from excel to dat obj
val = format_date(dt)
#print "...debug - res 2 (date to str), val set to:", val
elif sh1.cell(r,c).ctype == 4: # boolean data types
val = str(bool(val)) # convert 1 or 0 to bool true / false, then string
#print "...debug - res 3 (bool to str), val set to:", val
else:
val = str(val)
#print "...debug - else, val set to:", val
row.append(val)
#print ""
# write row to csv file
try:
writer.writerow(row)
except:
print '...row failed in write to file:', row
exc_type, exc_value, exc_traceback = sys.exc_info()
lines = traceback.format_exception(exc_type, exc_value, exc_traceback)
for line in lines:
print '!!', line
print 'Data written to:', out_path, '\n'
def main():
in_path, out_path = None, None
# set current working directory to user's my documents folder
os.chdir(os.path.join(os.getenv('userprofile'),'documents'))
# ask user for path to Excel file...
while not in_path:
print "Please select the excel file to read data from ..."
try:
in_path = fd.askopenfilename()
except:
print 'Error selecting file, please try again.\n'
# get dir for output...
same = raw_input("Do you want to write the output to the same directory? (Y/N): ")
if same.upper() == 'Y':
out_path = os.path.dirname(in_path)
else:
while not out_path:
print "Please select a directory to write the csv file to ..."
try:
out_path = fd.askdirectory()
except:
print 'Error selecting file, please try again.\n'
# get file name and join to dir
f_name = os.path.basename(in_path)
f_name = f_name[:f_name.find('.')]+'.csv'
out_path = os.path.join(out_path,f_name)
# get data from file and write to csv...
print 'Attempting read data from', in_path
print ' and write csv data to', out_path, '...\n'
xl_to_csv(in_path, out_path)
v_open = raw_input("Open file (Y/N):").upper()
if v_open == 'Y':
os.startfile(out_path)
sys.exit()
if __name__ == '__main__':
main()
Let me know if you have any questions on this.
Finally, regarding the output I would consider writing this out to a html file in a table format. Let me know if you want any help with this, I will have some more sample code that you could use part of.
UPDATE
Here is some further advice on writing your output to a html file. Here is a function that I have written and used previously for this purpose. Let me know if you need any guidance on what you would need to change for your implementation (if anything). The function expects a nested object in the data argument e.g. a list of lists or list of tuples etc. but should work for any number of rows / columns:
def write_html_file(path, data, heads):
html = []
tab_attr = ' border="1" cellpadding="3" style="background-color:#FAFCFF; text-align:right"'
head_attr = ' style="background-color:#C0CFE2"'
# opening lines needed for html table
try:
html.append('<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" ')
html.append('"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> ')
html.append('<html xmlns="http://www.w3.org/1999/xhtml">')
html.append('<body>')
html.append(' <table'+tab_attr+'>')
except:
print 'Error setting up html heading data'
# html table headings (if required)
if headings_on:
try:
html.append(' <tr'+head_attr+'>')
for item in heads:
html.append(' '*6+'<th>'+str(item)+'</th>')
html.append(' </tr>')
except:
exc_type, exc_value, exc_traceback = sys.exc_info()
lines = traceback.format_exception(exc_type, exc_value, exc_traceback)
print 'Error writing html table headings:'
print ''.join('!! ' + line for line in lines)
# html table content
try:
for row in data:
html.append(' <tr>')
for item in row:
html.append(' '*6+'<td>'+str(item)+'</td>')
html.append(' </tr>')
except:
print 'Error writing body of html data'
# closing lines needed
try:
html.append(' </table>')
html.append('</body>')
html.append('</html>')
except:
print 'Error closing html data'
# write html data to file
fileout = open(path, 'w')
for line in html:
fileout.write(line)
print 'Data written to:', path, '\n'
if sql_path:
os.startfile(path)
else:
v_open = raw_input("Open file (Y/N):").upper()
if v_open == 'Y':
os.startfile(path)
headings_on is a global that I have set to True in my script, you will also need to import traceback for the error handling to work as it is currently specified.