xlsx의 경우 이전에 https://web.archive.org/web/20180216070531//programming/4371163/reading-xlsx-files-using-python으로 게시 된 솔루션이 마음에 듭니다 . 표준 라이브러리의 모듈 만 사용합니다.
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
추가 된 개선 사항은 시트 이름으로 콘텐츠를 가져오고 re를 사용하여 열을 가져오고 공유 문자열이 사용되는지 확인하는 것입니다.
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