Write tables from Word (.docx) to Excel (.xlsx) using xlsxwriter

[BBT]

On Thursday, 28 May 2020 02:40:49 UTC+8, Peter Otten  wrote:
> BBT wrote:
> 
> > On Thursday, 28 May 2020 01:36:26 UTC+8, Peter Otten  wrote:
> >> BBT wrote:
> >> 
> >> > I am trying to parse a word (.docx) for tables, then copy these tables
> >> > over to excel using xlsxwriter. This is my code:
> >> > 
> >> > from docx.api import Document
> >> > import xlsxwriter
> >> >  
> >> > document = Document('/Users/xxx/Documents/xxx/Clauses Sample - Copy v1
> >> > - for merge.docx') tables = document.tables
> >> >  
> >> > wb = xlsxwriter.Workbook('C:/Users/xxx/Documents/xxx/test clause
> >> > retrieval.xlsx') Sheet1 = wb.add_worksheet("Compliance")
> >> > index_row = 0
> >> >  
> >> > print(len(tables))
> >> >  
> >> > for table in document.tables:
> >> > data = []
> >> > keys = None
> >> > for i, row in enumerate(table.rows):
> >> >     text = (cell.text for cell in row.cells)
> >> >  
> >> >     if i == 0:
> >> >         keys = tuple(text)
> >> >         continue
> >> >     row_data = dict(zip(keys, text))
> >> >     data.append(row_data)
> >> >     #print (data)
> >> >     #big_data.append(data)
> >> >     Sheet1.write(index_row,0, str(row_data))
> >> >     index_row = index_row + 1
> >> >  
> >> > print(row_data)
> >> >  
> >> > wb.close()
> >> > 
> >> > 
> >> > This is my desired output: https://i.stack.imgur.com/9qnbw.png
> >> > 
> >> > However, here is my actual output: https://i.stack.imgur.com/vpXej.png
> >> > 
> >> > I am aware that my current output produces a list of string instead.
> >> > 
> >> > Is there anyway that I can get my desired output using xlsxwriter?
> >> 
> >> I had to simulate docx.api. With that caveat the following seems to work:
> >> 
> >> import xlsxwriter
> >>  
> >> # begin simulation of
> >> # from docx.api import Document
> >> 
> >> class Cell:
> >>     def __init__(self, text):
> >>         self.text = text
> >> 
> >> class Row:
> >>     def __init__(self, cells):
> >>         self.cells = [Cell(c) for c in cells]
> >> 
> >> class Table:
> >>     def __init__(self, data):
> >>         self.rows = [
> >>             Row(row) for row in data
> >>         ]
> >> 
> >> class Document:
> >>     def __init__(self):
> >>         self.tables = [
> >>             Table([
> >>                 ["Hello", "Test"],
> >>                 ["est", "ing"],
> >>                 ["gg", "ff"]
> >>             ]),
> >>             Table([
> >>                 ["Foo", "Bar", "Baz"],
> >>                 ["ham", "spam", "jam"]
> >>             ])
> >>         ]
> >> 
> >> document = Document()
> >> 
> >> # end simulation
> >> 
> >> wb = xlsxwriter.Workbook("tmp.xlsx")
> >> sheet = wb.add_worksheet("Compliance")
> >>  
> >> offset = 0
> >> for table in document.tables:
> >>     for y, row in enumerate(table.rows):
> >>         for x, cell in enumerate(row.cells):
> >>             sheet.write(y + offset, x, cell.text)
> >>     offset +=  len(table.rows) + 1  # one empty row between tables
> >> 
> >> wb.close()
> > 
> > 
> > Hi Peter, thank you for your efforts :)
> > 
> > However, what if there are many tables in the word document, it would be
> > tedious to have to code the texts in the tables one by one. Can I instead,
> > call on the word document and let Python do the parsing for tables and its
> > contents?
> 
> I don't understand. You have docx.api available, so you can replace
> 
> the "simulation" part of my example with just these two lines: 
> 
> from docx.api import Document
> document = Document('/Users/xxx/Documents/xxx/Clauses Sample - Copy v1 - for merge.docx')
> 
> I should work -- it's just that I cannot be sure it will work because I could
> not test it.

I tried your code by replacing the Document portion:

import xlsxwriter

# begin simulation of
# from docx.api import Document

class Cell:
    def __init__(self, text):
        self.text = text

class Row:
    def __init__(self, cells):
        self.cells = [Cell(c) for c in cells]

class Table:
    def __init__(self, data):
        self.rows = [
            Row(row) for row in data
        ]

class Document:
    def __init__(self):
        self.tables = [
            Table([
                ["Hello", "Test"],
                ["est", "ing"],
                ["gg", "ff"]
            ]),
            Table([
                ["Foo", "Bar", "Baz"],
                ["ham", "spam", "jam"]
            ])
        ]

#document = Document()

# end simulation

document = Document('/Users/Ai Shan/Documents/CPFB Work/Clauses Sample - Copy v1 - for merge.docx')
wb = xlsxwriter.Workbook('C:/Users/Ai Shan/Documents/CPFB Work/test clause retrieval.xlsx')
Sheet1 = wb.add_worksheet("Compliance")

offset = 0
for table in document.tables:
    for y, row in enumerate(table.rows):
        for x, cell in enumerate(row.cells):
            sheet.write(y + offset, x, cell.text)
    offset +=  len(table.rows) + 1  # one empty row between tables

wb.close()


But I received an error:
TypeError: __init__() takes 1 positional argument but 2 were given