python之xml和excel学习

dom解析

python 复制代码

from xml.dom.minidom import parse
import xml.dom.minidom

# 使用minidom解析器打开 XML 文档
DOMTree = xml.dom.minidom.parse("xxx.xml")
collection = DOMTree.documentElement

# 根据标签名称获取
movies = collection.getElementsByTagName("fistTag")[0]
movies = movies.getElementsByTagName('secondTag')
rpmList = []
for movie in movies:
    # 内容获取方式xxx.childNodes[0].data
    strs = movie.childNodes[0].data.split(',')
    for str in strs:
        rpmList.append(str.strip())

另还有sax解析，可更好产生bean类

python 复制代码

from openpyxl import load_workbook


class RpmData:
    def __init__(self, name, incFileNum):
        self.name = name
        self.incFileNum = incFileNum

def get_index(char):
    return ord(char) - ord('A')
import re
def get_rpm_package_name(rpm_name):
    # 正则表达式匹配RPM包名
    match = re.match(r"^(?P<name>[^-]+)-(?P<version>[^-]+)-(?P<release>.+)\.rpm$", rpm_name)
    if match:
        return match.group('name')
    else:
        raise ValueError("Invalid RPM package name format")

def extract_name(rpm_package_name):
    parts = rpm_package_name.split('-')
    return '-'.join(parts[:len(parts)-2])

wb = load_workbook(r'xxx.xlsx')
sheet = wb['rpm视图']


# os.remove("sample.xlsx")

from openpyxl import Workbook
# 创建一个新的工作簿
dest_wb = Workbook()
# ws = dest_wb.create_sheet(title="rpm视图")
ws = dest_wb.active

x=1
y=1

for row in sheet.iter_rows(min_row=3):
    incFileNum = row[get_index('Q')].value
    if incFileNum <= 0.0:
        continue
    rpmName = extract_name(row[get_index('A')].value)
    if rpmName in rpmList:
        y=1
        for cell in row:
            
            # destCell = ws[cell.coordinate]
            destCell = ws.cell(row=x, column=y)
            destCell.value = cell.value
            y+=1
            # cell.parent = ws
        # ws.append(row)
        x+=1
    # rpmDataList.append(RpmData(row[get_index('A')].value, row[get_index('Q')].value))
    # for cell in row:
    #     print(cell.value)
dest_wb.save("sample.xlsx")

当原excel有引用时，实际只要cell.parent = ws，就可复制，但文件格式会有点问题

python文件的时候竟然报SyntaxError: (unicode error) 'unicodeescape' codec can't decode bytes in position 2-3: tr这个错误，其实引起这个错误的原因就是转义的问题

df = pd.read_excel(r'xxx.xlsx')

xlrd.biffh.XLRDError: Excel xlsx file； not supported

高版本不支持xlsx