We Keep Coding

openpyxl read Table to python

I'm trying to read an excel Table object into python and can't find any syntax for doing so.
It would be useful to read a whole table into e.g. a dict of dicts (I'm trying not to pull in pandas as a dependency for this particular project).
I can't find any way of doing this.

Below code will read through the table row by row, Also you can specify the range
import openpyxl
wb = openpyxl.load_workbook('example.xlsx')
sheet = wb.active
sheet['A1':'B7']
for i1,i2 in sheet:
print("{0:8} {1:8}".format(i1.value,i2.value))
Output:
Student_name Marks
Tony Stark 47
Loki 59
Oddin 73
Nick Fury 62
Samaul 75
Peter Parkar 80

I got it working as follows:
import openpyxl
def all_tables_data(filename: str) -> dict:
"""
Get values for all tables in a spreadsheet.
Returns a dict of tables, keyed by table name.
Table values are given as lists of lists.
"""
workbook = openpyxl.load_workbook(filename)
tables_by_name = {}
table_worksheets = {}
for worksheet in workbook.worksheets:
for table in worksheet._tables:
tables_by_name[table.name] = table
table_worksheets[table.name] = worksheet
def get_vals(table_name: str) -> list:
worksheet = table_worksheets[table_name]
cell_range = worksheet[tables_by_name[table_name].ref]
return [[cell.value for cell in row] for row in cell_range]
return {table_name: get_vals(table_name) for table_name in tables_by_name}
if __name__ == "__main__":
FILENAME = "my_spreadsheet.xlsx"
TABLES = all_tables_data(FILENAME)
print(TABLES)
I'm interested in converting tables to dicts.
Often the rows/entries in a table may have >1 key.
Assuming the table has a header row, I also cobbled the code below together.
It can be used to convert a table to a dict of rows, with each row being a dict of values, keyed by the column headers.
class WorkbookWithTables:
def __init__(self, workbook):
self.workbook = workbook
self.tables_by_name = {}
self.table_worksheets = {}
for worksheet in self.workbook.worksheets:
for table in worksheet._tables:
self.tables_by_name[table.name] = table
self.table_worksheets[table.name] = worksheet
#classmethod
def from_file(cls, filename):
_workbook = openpyxl.load_workbook(filename)
return cls(_workbook)
def table_to_dict(self, table_name, n_keys=1):
worksheet = self.table_worksheets[table_name]
cell_range = worksheet[self.tables_by_name[table_name].ref]
table_dict = {}
value_headers = tuple(cell.value for cell in cell_range[0][n_keys:])
for row in cell_range[1:]:
if n_keys == 1:
key = row[0].value
else:
key = tuple(partial_key.value for partial_key in row[:n_keys])
values = {
value_headers[i]: cell.value
for i, cell in enumerate(row[n_keys:])
}
table_dict[key] = values
return table_dict
if __name__ == "__main__":
FILENAME = "my_spreadsheet.xlsx"
WB = WorkbookWithTables.from_file(FILENAME)
MY_SINGLE_KEYED_TABLE = WB.table_to_dict("my_single_keyed_table")
MY_DOUBLE_KEYED_TABLE = WB.table_to_dict("my_double_keyed_table", 2)

write python list of dicts to xlsx using openpyxl

i try to write this list of dicts into xlsx file using openpyxlsx
products= [{'id':46329',
'discription':'AD BLeu',
'marque':'AZERT',
'category':'liquid',
'family': 'ADBLEU',
'photos':'D:\\hamzawi\\hamza\\image2py\\46329_1.png'},
{dict2 ...},
{dictn...}
]
# creat a workbook
filena = "produitimage.xlsx"
workbook = Workbook()
sheet = workbook.active
#add headers
sheet.append(["Product ID", "Product Name", "Marque",
"Category", "Family", "Photos"])
for product in products:
for item in product.items():
for row, entry in enumerate(item, start=3):
sheet.cell(row=row, column=1, value=entry)
#add some images
images = [item['photos'] for item in products]
for image in images:
logo = Image(image)
#logo.height = 150
#logo.width = 150
sheet.add_image(logo)
workbook.save(filename=filena)
i got xlsx file with only headers no data

Question: append list of dict
import openpyxl
products = [{'id':46329,
'discription':'AD BLeu',
'marque':'AZERT',
'category':'liquid',
'family': 'ADBLEU',
'photos':'D:\\hamzawi\\hamza\\image2py\\46329_1.png'}
]
# Dictionarys are not in order by default
# Define a `list` of `keys` in desired order
fieldnames = ['id', 'discription', 'marque', 'category', 'family', 'photos']
# create a new workbook
wb = openpyxl.Workbook()
ws = wb.active
# append headers
ws.append(["Product ID", "Product Name", "Marque", "Category", "Family", "Photos"])
# append data
# iterate `list` of `dict`
for product in products:
# create a `generator` yield product `value`
# use the fieldnames in desired order as `key`
values = (product[k] for k in fieldnames)
# append the `generator values`
ws.append(values)
# show Worksheet Values
for row_values in ws.iter_rows(values_only=True):
for value in row_values:
print(value, end='\t')
print()
Output:
Product ID Product Name Marque Category Family Photos
46329 AD BLeu AZERT liquid ADBLEU D:\hamzawi\hamza\image2py\46329_1.png
If you want the image, instead of the image file path, change the following:
# remove 'photos' from fieldnames
fieldnames = \
['id', 'discription', 'marque', 'category', 'family']
# you need the Row index, add a `enumerate(..., 2)`
for row, product in enumerate(products,2):
values = (product[k] for k in fieldnames)
sheet.append(values)
# after append the `values` add the image
# Here, Column 'F'
ws.add_image(Image(product['photos']), 'F{}'.format(row))

There are some problems in your code.
First, you are incrementing next_row value in the loop where you setting it, so increment doesn't have effect and every iteration the value of next_row equals 3.
Second, you are trying to write a list of dict values to excel cell, but I think you want it will be written as a row. So you need to just append it as you did with header above the loops:
for product in products:
sheet.append(list(product.values()))
If you need to insert an image in last cell in a row you may rewrite loop that way:
for row_index, product in enumerate(products):
values = list(product.values())
sheet.append(values[:-1])
col_row = get_column_letter(len(values)) + str(row_index+1)
photo_path = values[-1]
sheet.add_image(Image(photo_path), col_row)

Filtering text from a Pdf using PyPDF2 to Excel Sheet with nothing Showing

import PyPDF2
import re
import xlsxwriter
docsFile = open('image0001.pdf','rb')
pdfReader = PyPDF2.PdfFileReader(docsFile)
loanNumberlist = []
loan2Matchlist = []
poolNumlist = []
borrowerNamelist = []
wb = xlsxwriter.Workbook('docInfo.xlsx')
ws = wb.add_worksheet('sheet2')
row = 0
columnHeaders = ['Borrower Name', 'Loan Number', 'LD Loan Number', 'Pool #']
for col, colname in enumerate(columnHeaders, start=0):
ws.write(row, col, colname)
class pdfExtract:
def __init__(self, pg):
self.pg = pg
def extractShit(self):
pageObj = pdfReader.getpage(self.pg)
pgData = pageObj.extractText()
loanNumber = re.split('\\bLoan #:\\b', pgData)[-1]
loanNumberlist.append(loanNumber)
loan2Match = re.match(r"?:/\d{0,10}", pgData)[-1]
loan2Matchlist.append(loan2Match)
poolNumber = re.split('\\bPool #:\\b',pgData)[-1]
poolNumlist.append(poolNumber)
borrowerName =re.split('\\bBorrower #:\\b',pgData)[-1]
borrowerNamelist.append(borrowerName)
for page in range(0, 223):
pdfExtract(page)
for row, rowvar in enumerate(borrowerNamelist, start=1):#write Borrower name
col = 0
ws.write_string(row, col, rowvar)
for row, lnNM in enumerate(loanNumberlist, start=1):#write loan number 1
col = 1
ws.write_number(row, col, lnNM)
for row, lnNM2 in enumerate(loan2Matchlist, start=1):#write loan number 2
col = 2
ws.write_number(row, col, lnNM2)
for row, plNm in enumerate(poolNumlist, start=1):#write pool number
col = 3
ws.write_number(row, col, plNm)
wb.close()
So, I wrote this program to grab data from a pdf file and return 4 things in each page and put them into an excel file. That looks like:
Loan #: 0065192080/3000009289
Pool#: AK1576
Borrower: David h Theman
I have to grab each page get the first loan number, then the second loan number(after the “/“). Then the rest.
It runs through, but all I get to see on the excel file is the headers no data and no errors.
I thought it was how I'm returning the data or how I'm writing it, but it has no changes. Would it have to do with my For loops? The regex code I got from different answers on here. I've changed how I write it to the excel file, but no luck.

Excel Python using openpyxl

I extracted informations from ERP database of my company and with these data I have to add them to a sheet already created. But unfortunately my problem is being in how to use these commands.. The openpyxl documentation is not help me :(
This is an example of my sheet.
import sys
import datetime
from openpyxl import load_workbook
data = datetime.datetime.now()
wb = load_workbook('/home/multipla/Documentos/test.xlsx')
ws = wb.active
for i in ws['B3':'F12']:
for j in i:
print j
#Edit:
Write these cell "Hands On":
ws["B3"].value = '2324'
ws["C3"].value = 'Patty'
ws["D3"].value = ''
ws["E3"].value = "YES"
ws["F3"].value = "Reading"
Tried to automatize that process, by making a For Loop to go through each cell and write them...
#Edit2

If you have a list of dictionaries with your properties, that is:
object_1 = dict()
object_1['ID'] = 1337
object_1['NAME'] = 'Pencil'
...
object_2 = dict()
object_2['ID'] = 1338
object_2['NAME'] = 'Eraser'
...
object_list = list()
object_list.append(object_1)
object_list.append(object_2)
Then you could do something like this:
def add_object(ob, row):
ws.cell(column=2, row=row).value = ob['ID']
ws.cell(column=3, row=row).value = ob['NAME']
ws.cell(column=4, row=row).value = ob['Y']
ws.cell(column=5, row=row).value = ob['X']
ws.cell(column=6, row=row).value = ob['ISSUE']
def add_object_list(ob_list):
for i, ob in enumerate(ob_list):
add_object(ob, i + 3)
add_object_list(object_list)
Result:

Csv - Inserting missing rows

I have a huge file, which has some missing rows. The data needs to be rooted at Country.
The input data is like:
csv_str = """Type,Country,State,County,City,
1,USA,,,
2,USA,OH,,
3,USA,OH,Franklin,
4,USA,OH,Franklin,Columbus
4,USA,OH,Franklin,Springfield
4,USA,WI,Dane,Madison
"""
which needed to be:
csv_str = """Type,Country,State,County,City,
1,USA,,,
2,USA,OH,,
3,USA,OH,Franklin,
4,USA,OH,Franklin,Columbus
4,USA,OH,Franklin,Springfield
4,USA,WI,,
4,USA,WI,Dane,
4,USA,WI,Dane,Madison
"""
The key as per my logic is Type field, where if I cannot find a County (type 3) for a City (type 4), then insert a row with fields upto County.
Same with County. If I cannot find a State (type 2) for a County (type 3), then insert a row with fields upto State.
With my lack of understanding the facilities in python, I was trying more of a brute-force approach. It is bit problematic as I need lot of iteration over the same file.
I was also tried google-refine, but couldn't get it work. Doing manually is quite error prone.
Any help appreciated.
import csv
import io
csv_str = """Type,Country,State,County,City,
1,USA,,,
2,USA,OH,,
3,USA,OH,Franklin,
4,USA,OH,Franklin,Columbus
4,USA,OH,Franklin,Springfield
4,USA,WI,Dane,Madison
"""
found_county =[]
missing_county =[]
def check_missing_county(row):
found = False
for elm in found_county:
if elm.Type == row.Type:
found = True
if not found:
missing_county.append(row)
print(row)
reader = csv.reader(io.StringIO(csv_str))
for row in reader:
check_missing_county(row)

I've knocked up the following based on my understanding of the question:
import csv
import io
csv_str = u"""Type,Country,State,County,City,
1,USA,,,
2,USA,OH,,
3,USA,OH,Franklin,
4,USA,OH,Franklin,Columbus
4,USA,OH,Franklin,Springfield
4,USA,WI,Dane,Madison
"""
counties = []
states = []
def handle_missing_data(row):
try:
rtype = int(row[0])
except ValueError:
return []
rtype = row[0]
country = row[1]
state = row[2]
county = row[3]
rows = []
# if a state is present and it hasn't a row of it's own
if state and state not in states:
rows.append([rtype, country, state, '', ''])
states.append(state)
# if a county is present and it hasn't a row of it's own
if county and county not in counties:
rows.append([rtype, country, state, county, ''])
counties.append(county)
# if the row hasn't already been added add it now
if row not in rows:
rows.append(row)
return rows
csvf = io.StringIO(csv_str)
reader = csv.reader(csvf)
for row in reader:
new_rows = handle_missing_data(row)
for new_row in new_rows:
print new_row