Reading an Excel named range into a pandas DataFrame
·
Answer a question
How can you read the data from a named range in Excel into a pandas DataFrame?
Unfortunately, the canonical function pandas.read_excel()
is designed to only read entire sheets within a workbook.
Answers
Maybe someday pandas will support this natively. Until then, I use a helper function:
import pandas as pd
import openpyxl
def data_frame_from_xlsx(xlsx_file, range_name):
""" Get a single rectangular region from the specified file.
range_name can be a standard Excel reference ('Sheet1!A2:B7') or
refer to a named region ('my_cells')."""
wb = openpyxl.load_workbook(xlsx_file, data_only=True, read_only=True)
if '!' in range_name:
# passed a worksheet!cell reference
ws_name, reg = range_name.split('!')
if ws_name.startswith("'") and ws_name.endswith("'"):
# optionally strip single quotes around sheet name
ws_name = ws_name[1:-1]
region = wb[ws_name][reg]
else:
# passed a named range; find the cells in the workbook
full_range = wb.get_named_range(range_name)
if full_range is None:
raise ValueError(
'Range "{}" not found in workbook "{}".'.format(range_name, xlsx_file)
)
# convert to list (openpyxl 2.3 returns a list but 2.4+ returns a generator)
destinations = list(full_range.destinations)
if len(destinations) > 1:
raise ValueError(
'Range "{}" in workbook "{}" contains more than one region.'
.format(range_name, xlsx_file)
)
ws, reg = destinations[0]
# convert to worksheet object (openpyxl 2.3 returns a worksheet object
# but 2.4+ returns the name of a worksheet)
if isinstance(ws, str):
ws = wb[ws]
region = ws[reg]
# an anonymous user suggested this to catch a single-cell range (untested):
# if not isinstance(region, 'tuple'): df = pd.DataFrame(region.value)
df = pd.DataFrame([cell.value for cell in row] for row in region)
return df
更多推荐
所有评论(0)