问题
In the openpyxl documentation there is an example of how to place a table into a workbook but there are no examples of how to find back the tables of a workbook. I have an XLS file that has named tables in it and I want to open the file, find all of the tables and parse them. I cannot find any documentation on how to do this. Can anyone help?
In the meantime I worked it out and wrote the following class to work with openpyxl:
class NamedArray(object):
''' Excel Named range object
Reproduces the named range feature of Microsoft Excel
Assumes a definition in the form <Worksheet PinList!$A$6:$A$52 provided by openpyxl
Written for use with, and initialised by the get_names function
After initialisation named array can be used in the same way as for VBA in excel
Written for openpyxl version 2.4.1, may not work with earlier versions
'''
C_CAPS = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
def __init__(self, wb, named_range_raw):
''' Initialise a NameArray object from the named_range_raw information in the given workbook
'''
self.sheet, cellrange_str = str(named_range_raw).split('!')
self.sheet = self.sheet.replace("'",'') # remove the single quotes if they exist
self.loc = wb[self.sheet]
if ':' in cellrange_str:
self.has_range = True
self.has_value = False
lo, hi = cellrange_str.split(':')
self.ad_lo = lo.replace('$','')
self.ad_hi = hi.replace('$','')
else:
self.has_range = False
self.has_value = True
self.ad_lo = cellrange_str.replace('$','')
self.ad_hi = self.ad_lo
self.row = self.get_row(self.ad_lo)
self.max_row = self.get_row(self.ad_hi)
self.rows = self.max_row - self.row + 1
self.min_col = self.col_to_n(self.ad_lo)
self.max_col = self.col_to_n(self.ad_hi)
self.cols = self.max_col - self.min_col + 1
def size_of(self):
''' Returns two dimensional size of named space
'''
return self.cols, self.rows
def value(self, row=1, col=1):
''' Returns the value at row, col
'''
assert row <= self.rows , 'invalid row number given'
assert col <= self.cols , 'invalid column number given'
return self.loc.cell(self.n_to_col(self.min_col + col-1)+str(self.row + row-1)).value
def __str__(self):
''' printed description of named space
'''
locs = 's ' + self.ad_lo + ':' + self.ad_hi if self.is_range else ' ' + self.ad_lo
return('named range'+ str(self.size_of()) + ' in sheet ' + self.sheet + ' @ location' + locs)
def __contains__(self, val):
rval = False
for row in range(1,self.rows+1):
for col in range(1,self.cols+1):
if self.value(row,col) == val:
rval = True
return rval
def vlookup(self, key, col):
''' excel style vlookup function
'''
assert col <= self.cols , 'invalid column number given'
rval = None
for row in range(1,self.rows+1):
if self.value(row,1) == key:
rval = self.value(row, col)
break
return rval
def hlookup(self, key, row):
''' excel style hlookup function
'''
assert row <= self.rows , 'invalid row number given'
rval = None
for col in range(1,self.cols+1):
if self.value(1,col) == key:
rval = self.value(row, col)
break
return rval
@classmethod
def get_row(cls, ad):
''' get row number from cell string
Cell string is assumed to be in excel format i.e "ABC123" where row is 123
'''
row = 0
for l in ad:
if l in "1234567890":
row = row*10 + int(l)
return row
@classmethod
def col_to_n(cls, ad):
''' find column number from xl address
Cell string is assumed to be in excel format i.e "ABC123" where column is abc
column number is integer represenation i.e.(A-A)*26*26 + (B-A)*26 + (C-A)
'''
n = 0
for l in ad:
if l in cls.C_CAPS:
n = n*26 + cls.C_CAPS.find(l)+1
return n
@classmethod
def n_to_col(cls, n):
''' make xl column address from column number
'''
ad = ''
while n > 0:
ad = cls.C_CAPS[n%26-1] + ad
n = n // 26
return ad
def get_names(workbook, filt='', debug=False):
''' Create a structure containing all of the names in the given workbook
filt is an optional parameter and used to create a subset of names starting with filt
useful for IO_ring_spreadsheet as all names start with 'n_'
if present, filt characters are stipped off the front of the name
'''
named_ranges = workbook.defined_names.definedName
name_list = {}
for named_range in named_ranges:
name = named_range.name
if named_range.attr_text.startswith('#REF'):
print('WARNING: named range "', name, '" is undefined')
elif filt == '' or name.startswith(filt):
name_list[name[len(filt):]] = NamedArray(workbook, named_range.attr_text)
if debug:
with open("H:\\names.txt",'w') as log:
for item in name_list:
print (item, '=', name_list[item])
log.write(item.ljust(30) + ' = ' + str(name_list[item])+'\n')
return name_list
回答1:
I agree that the documentation does not really help, and the public API also seems to have only add_table() method.
But then I found an openpyxl Issue 844 asking for a better interface, and it shows that worksheet has an _tables property.
This is enough to get a list of all tables in a file, together with some basic properties:
from openpyxl import load_workbook
wb = load_workbook(filename = 'test.xlsx')
for ws in wb.worksheets:
print("Worksheet %s include %d tables:" % (ws.title, len(ws._tables)))
for tbl in ws._tables:
print(" : " + tbl.displayName)
print(" - name = " + tbl.name)
print(" - type = " + (tbl.tableType if isinstance(tbl.tableType, str) else 'n/a')
print(" - range = " + tbl.ref)
print(" - #cols = %d" % len(tbl.tableColumns))
for col in tbl.tableColumns:
print(" : " + col.name)
Note that the if/else construct is required for the tableType, since it can return NoneType (for standard tables), which is not convertible to str.
回答2:
Building on @MichalKaut's answer, I created a simple function that returns a dictionary with all tables in a given workbook. It also puts each table's data into a Pandas DataFrame.
from openpyxl import load_workbook
import pandas as pd
def get_all_tables(filename):
""" Get all tables from a given workbook. Returns a dictionary of tables.
Requires a filename, which includes the file path and filename. """
# Load the workbook, from the filename
wb = load_workbook(filename=file, read_only=False, keep_vba=False, data_only=True, keep_links=False)
# Initialize the dictionary of tables
tables_dict = {}
# Go through each worksheet in the workbook
for ws_name in wb.sheetnames:
print("")
print(f"worksheet name: {ws_name}")
ws = wb[ws_name]
print(f"tables in worksheet: {len(ws._tables)}")
# Get each table in the worksheet
for tbl in ws.tables.values():
print(f"table name: {tbl.name}")
# First, add some info about the table to the dictionary
tables_dict[tbl.name] = {
'table_name': tbl.name,
'worksheet': ws_name,
'num_cols': len(tbl.tableColumns),
'table_range': tbl.ref}
# Grab the 'data' from the table
data = ws[tbl.ref]
# Now convert the table 'data' to a Pandas DataFrame
# First get a list of all rows, including the first header row
rows_list = []
for row in data:
# Get a list of all columns in each row
cols = []
for col in row:
cols.append(col.value)
rows_list.append(cols)
# Create a pandas dataframe from the rows_list.
# The first row is the column names
df = pd.DataFrame(data=rows_list[1:], index=None, columns=rows_list[0])
# Add the dataframe to the dictionary of tables
tables_dict[tbl.name]['dataframe'] = df
return tables_dict
# File location:
file = r"C:\Users\sean\spreadsheets\full_of_tables.xlsx"
# Run the function to return a dictionary of all tables in the Excel workbook
tables_dict = get_all_tables(filename=file)
回答3:
The answer to this has changed.
ws objects now contain the tables accessor which acts as a dictionary. Updated answer is:
tmp = [ws.tables for ws in wb.worksheets]
tbls = [{v.name:v} for t in tmp for v in t.values()]
回答4:
I'm not sure what you mean by parsing but read-support for worksheet tables has been possible since version 2.4.4. If you have questions about the details then I suggest you ask your question on the openpyxl mailing list as that is a more suitable place for this kind of discussion.
回答5:
I don't think this is possible. I seems to work similarly to images; if you read and save a file with a table it will get striped.
来源：https://stackoverflow.com/questions/43941365/openpyxl-read-tables-from-existing-data-book-example