How to write values to excel using python3?
import xlsxwriter
from openpyxl import load_workbook
import re
input_file = "No. ; HP 0136510545","good"
for line in input_file:
if "HP" in line:
s= line
hp = re.findall('\d+', s)
print(hp)
data = [["hp"],[hp]]
workbook = xlsxwriter.Workbook('Input.xlsx')
workbook.close()
wb = load_workbook("Input.xlsx")
ws = wb.worksheets[0]
for row_data in data:
ws.append(row_data)
wb.save("excel_file.xlsx")
Expected Result:
0136510545
Got Result:
['0136510545']
I got error as cannot convert to excel i dono why but when i try to write as sheet1.write(0,0,hp) it will work whats wrong in my code? pls help me
just change as follows:
data = [["hp"],hp]
Related
If the ninth column doesn't contains the name of city ISTANBUL, then I need to be able to delete
the entire row. i wrote the code it works but it doesn't delete row.
from openpyxl import Workbook, load_workbook
from openpyxl.utils import get_column_letter
wb = load_workbook('deneme.xlsx')
ws = wb.active
for row in range(1, 3313):
for col in [9]:
char = get_column_letter(col)
if ws[char + str(row)].value is not 'İSTANBUL':
ws.delete_rows(row)
wb.save('deneme.xlsx')
Here it is solution i just found.
import pandas as pd
df = pd.read_excel('staji.xlsx') #here you can put your file path
filt = (df['ŞEHİR'] == 'İSTANBUL') # put your condition ŞEHİR=column name.
df[filt].to_excel('den1.xlsx')
I want to read and merge only visible cells in Excel, but I failed.
Also, I've tried openpyxl but didn't work. (Find my second code)
Is there any other ways to read only visible cells and paste on new excel?
I want to read only visible cells because sometimes they need to be filtered or hidden.
Please kindly advise me.
What kind of module should I put in?
If every excel module cannot do that, please also let me know.
My current code:
import os
import glob
import xlwings as xw
import xlrd
import xlsxwriter
xw.App().visible = False
path = os.getcwd()
x=input('name：') + '.xlsx'
target_xls = os.path.join(path,x)
data = []
for file in glob.glob(path+'\*.*'):
if file.endswith((".xls", ".xlsm", ".xlsx")):
wb = xlrd.open_workbook(file)
for sheet in wb.sheets():
for rownum in range(sheet.nrows):
data.append(sheet.row_values(rownum))
workbook = xlsxwriter.Workbook(target_xls)
worksheet = workbook.add_worksheet()
for i in range(len(data)):
print(range(len(data)))
for j in range(len(data[i])):
worksheet.write(i, j, data[i][j])
workbook.close()
My openpyxl code:
import os
import glob
import xlwings as xw
import xlrd
import xlsxwriter
from openpyxl import load_workbook
xw.App().visible = False
path = os.getcwd()
x = input('name：') + '.xlsx'
target_xls = os.path.join(path, x)
data = []
wb = load_workbook('sample.xlsx')
ws = wb['Sheet1']
for row in ws:
if ws.row_dimensions[row[0].row].hidden == False:
for cell in row:
data.append(cell.value)
workbook = xlsxwriter.Workbook(target_xls)
worksheet = workbook.add_worksheet()
for i in range(len(data)):
print(range(len(data)))
for j in range(len(data[i])):
worksheet.write(i, j, data[i][j])
workbook.close()
I want to read excel like below:
And output into:
#Reference: xlrd manual: https://media.readthedocs.org/pdf/xlrd/latest/xlrd.pdf
#Python Forum Reference: https://python-forum.io/Thread-Identify-Hidden-rows-in-xls
import xlrd
print("Read the VALUE and ROW VISIBILITY from cells A1:A6 in a .xls file from 'Sheet2'.")
print()
######################################################
# Access .xls file (Excel 2003 and before)
excel_filename = "HiddenRow3OnSheet2.xls"
# Open the workbook
#NOTE: Traceback error if 'formatting_info=True' is NOT INCLUDED
xl_workbook = xlrd.open_workbook(excel_filename, formatting_info=True)
#Set the focus on 'Sheet2'
my_sheet_name = "Sheet2"
xl_sheet = xl_workbook.sheet_by_name(my_sheet_name)
print("File: {}".format(excel_filename))
for irow in range(xl_sheet.nrows):
ihidden = xl_sheet.rowinfo_map[irow].hidden #Row Visibility 0=Visible 1=Hidden
if ihidden == True:
shidden = "VISIBLE"
else:
shidden = "HIDDEN"
svalue = xl_sheet.cell(irow,0).value
print("Value: {} Row Visibility: {}".format(svalue, shidden))
######################################################
# Access .xlsx file (Excel 2007 and later)
excel_filename = "HiddenRow3OnSheet2.xlsx"
# Open the workbook
#NOTE: 'formatting_info=True' is NOT SUPPORTED for .xlsx files
xl_workbook = xlrd.open_workbook(excel_filename)
#Set the focus on 'Sheet2'
my_sheet_name = "Sheet2"
xl_sheet = xl_workbook.sheet_by_name(my_sheet_name)
print()
print("File: {}".format(excel_filename))
for irow in range(xl_sheet.nrows):
svalue = xl_sheet.cell(irow,0).value
print("Value: {} Row Visibility: {}".format(svalue, "Not Available for .xlsx files"))
I have developed the following code and fetched the matched output using a for loop.I need to print these output elements in separate column using python.
excel file name - Sample_data.xlsx
first column - WBS_CODE
second column - PROJECT_CODE
first column and second column are matched and then printed in separate column (column F) using python code. Please find my below code,
import pandas as pd
A = pd.read_excel("D:\python_work\Sample_data.xlsx", sheet_name = '31Sep')
code = A['WBS_CODE'].tolist()
B = pd.read_excel("D:\python_work\Sample_data.xlsx", sheet_name = '4Dec')
code1 = B['PROJECT_CODE'].tolist()
for x in code1:
if x in code:
print(x)
else:
print("NA")
output:
NA
NA
NA
APP-ACI-PJ-APAC-EMEA-ENG
NA
NA
I have found a way to export the output and print them in a separate column in excel sheet. Below is the solution,
import pandas as pd
from openpyxl import load_workbook
# Reading the Excel file columns
A = pd.read_excel("D:\python_work\Sample_data.xlsx", sheet_name='4Dec')
code = A['PROJECT_CODE'].tolist()
B = pd.read_excel("D:\python_work\Sample_data.xlsx", sheet_name='31Sep')
code1 = B['WBS_CODE'].tolist()
# Comparison of columns
class test:
def loop(self):
result = []
for x in code1:
if x in code:
result.append(x)
else:
y = "NA"
result.append(y)
print(result)
# Printing data into Excel
try:
book = load_workbook('D:\python_work\Aew1.xlsx')
writer = pd.ExcelWriter('D:\python_work\Aew1.xlsx', engine='openpyxl')
writer.book = book
writer.sheets = dict((ws.title, ws) for ws in book.worksheets) # loading all the worksheets in opened Excel
df = pd.DataFrame.from_dict({'Column1': result})
df.to_excel(writer, sheet_name='Sheet1', startcol=19)
writer.save()
except FileNotFoundError:
print("File Not found: 'Check the Name or Existence of file specified/'")
except PermissionError:
print("File Opened/No-Access: Check whether you have access to file or file is opened")
test().loop()
steps that solved:
1. Appended the for loop output to a list
2. used openpyxl library to print the output to a column in excel worksheet.
Thanks guyz for help and support. Have a good day
I am trying to write a function to read data from excel file using python. My function should read rows from excel sheet one at a time. Below is my code which will print 1st row.
import xlrd
from xlrd import open_workbook, cellname
book = open_workbook('./Excel/Book1.xls')
def read_excel(sheetName):
sheet = book.sheet_by_name(sheetName)
row = sheet.nrows
for i in range(1):
rows = sheet.row_values(i+1)
print(rows)
file = r'd:\pythonTest.xlsx '
import xlrd
wb = xlrd.open_workbook(file)
sheet = wb.sheet_by_index(0)
# For row 0 and column 0
sheet.cell_value(0, 0)
# Extracting number of columns
print(sheet.ncols)
print(sheet.nrows)
print(sheet.row_values(1))
for i in range(sheet.nrows):
print(sheet.cell_value(i, 0), sheet.cell_value(i, 1))
I have the following code, and I am trying to write a data frame into an "existing" worksheet of an Excel file (referred here as test.xlsx). Sheet3 is the targeted sheet where I want to place the data, and I don't want to replace the entire sheet with a new one.
df = pd.DataFrame({'Data': [10, 20, 30, 20, 15, 30, 45]})
book = load_workbook('test.xlsx')
writer = pd.ExcelWriter('test.xlsx')
writer.book = book
writer.sheets = dict((ws.title, ws) for ws in book.worksheets) # *I am not sure what is happening in this line*
df.to_excel(writer,"Sheet3",startcol=0, startrow=20)
When I am running the code line by line, I am getting this error for the last line:
AttributeError: 'Workbook' object has no attribute 'add_worksheet'. Now why am I seeing this error when I am not trying to add worksheet ?
Note: I am aware of this similar issue Python How to use ExcelWriter to write into an existing worksheet but its not working for me and I can't comment on that post either.
You can use the append_df_to_excel() helper function, which is defined in this answer:
Usage:
append_df_to_excel('test.xlsx', df, sheet_name="Sheet3", startcol=0, startrow=20)
Some details:
**to_excel_kwargs - used in order to pass additional named parameters to df.to_excel() like i did in the example above - parameter startcol is unknown to append_df_to_excel() so it will be treated as a part of **to_excel_kwargs parameter (dictionary).
writer.sheets = {ws.title:ws for ws in writer.book.worksheets} is used in order to copy existing sheets to writer openpyxl object. I can't explain why it's not done automatically when reading writer = pd.ExcelWriter(filename, engine='openpyxl') - you should ask authors of openpyxl module about that...
You can use openpyxl as the engine when you are creating an instance of pd.ExcelWriter.
import pandas as pd
import openpyxl
df1 = pd.DataFrame({'A':[1, 2, -3],'B':[1,2,6]})
book = openpyxl.load_workbook('examples/ex1.xlsx') #Already existing workbook
writer = pd.ExcelWriter('examples/ex1.xlsx', engine='openpyxl') #Using openpyxl
#Migrating the already existing worksheets to writer
writer.book = book
writer.sheets = {x.title: x for x in book.worksheets}
df1.to_excel(writer, sheet_name='sheet4')
writer.save()
Hope this works for you.
openpyxl has support for Pandas dataframes so you're best off using it directly. See http://openpyxl.readthedocs.io/en/latest/pandas.html for more details.
Based on https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.to_excel.html
This did work for me (pandas version 1.3.5)
import pandas as pd
df1 = pd.DataFrame({'a':[0,1,2], 'b':[1,2,3],'c':[2,3,4]})
df2 = pd.DataFrame({'aa':[10,11,12], 'bb':[11,12,13],'cc':[12,13,14]})
with pd.ExcelWriter('test.xlsx') as writer:
for i, df in enumerate([df1, df2]):
df.to_excel(writer,sheet_name=f'sheet_{i}', index=False)