- Charts, Macros, Pictures, any other embedded object, including embedded worksheets.
- VBA modules
- Formulas, but results of formula calculations are extracted.
- Comments
- Hyperlinks
- Autofilters, advanced filters, pivot tables, conditional formatting, data validation
不支持密码保护的文件,此
图书馆。
旅行者提到了 COM 自动化的使用。几年前我自己也这么做过,所以要注意这是一个真正的 PITA。警告的数量是巨大的,文档是缺乏和恼人的。我遇到了许多奇怪的错误和陷阱,其中一些花了好几个小时才弄明白。
import pandas as pd
xls = pd.ExcelFile(r"yourfilename.xls") # use r before absolute file path
sheetX = xls.parse(2) #2 is the sheet number+1 thus if the file has only 1 sheet write 0 in paranthesis
var1 = sheetX['ColumnName']
print(var1[1]) #1 is the row number...
def xlsx(fname):
import zipfile
from xml.etree.ElementTree import iterparse
z = zipfile.ZipFile(fname)
strings = [el.text for e, el in iterparse(z.open('xl/sharedStrings.xml')) if el.tag.endswith('}t')]
rows = []
row = {}
value = ''
for e, el in iterparse(z.open('xl/worksheets/sheet1.xml')):
if el.tag.endswith('}v'): # Example: <v>84</v>
value = el.text
if el.tag.endswith('}c'): # Example: <c r="A3" t="s"><v>84</v></c>
if el.attrib.get('t') == 's':
value = strings[int(value)]
letter = el.attrib['r'] # Example: AZ22
while letter[-1].isdigit():
letter = letter[:-1]
row[letter] = value
value = ''
if el.tag.endswith('}row'):
rows.append(row)
row = {}
return rows
添加的改进包括按工作表名称获取内容、使用 re 获取列以及检查是否使用了共享字符串。
def xlsx(fname,sheet):
import zipfile
from xml.etree.ElementTree import iterparse
import re
z = zipfile.ZipFile(fname)
if 'xl/sharedStrings.xml' in z.namelist():
# Get shared strings
strings = [element.text for event, element
in iterparse(z.open('xl/sharedStrings.xml'))
if element.tag.endswith('}t')]
sheetdict = { element.attrib['name']:element.attrib['sheetId'] for event,element in iterparse(z.open('xl/workbook.xml'))
if element.tag.endswith('}sheet') }
rows = []
row = {}
value = ''
if sheet in sheets:
sheetfile = 'xl/worksheets/sheet'+sheets[sheet]+'.xml'
#print(sheet,sheetfile)
for event, element in iterparse(z.open(sheetfile)):
# get value or index to shared strings
if element.tag.endswith('}v') or element.tag.endswith('}t'):
value = element.text
# If value is a shared string, use value as an index
if element.tag.endswith('}c'):
if element.attrib.get('t') == 's':
value = strings[int(value)]
# split the row/col information so that the row leter(s) can be separate
letter = re.sub('\d','',element.attrib['r'])
row[letter] = value
value = ''
if element.tag.endswith('}row'):
rows.append(row)
row = {}
return rows
import xlrd
file=u'C:/Landau/task/6200.xlsx'
try:
book = xlrd.open_workbook(file,encoding_override="cp1251")
except:
book = xlrd.open_workbook(file)
print("The number of worksheets is {0}".format(book.nsheets))
print("Worksheet name(s): {0}".format(book.sheet_names()))
sh = book.sheet_by_index(0)
print("{0} {1} {2}".format(sh.name, sh.nrows, sh.ncols))
print("Cell D30 is {0}".format(sh.cell_value(rowx=29, colx=3)))
for rx in range(sh.nrows):
print(sh.row(rx))
InvalidFileException: openpyxl does not support the old .xls file format, please use xlrd to read this file, or convert it to the more recent .xlsx file format.