python读取excel或pdf

python读取excel

import xlrd

file = 'TEST.xlsx'

def read_excel():

    wb = xlrd.open_workbook(filename=file)  # 打开文件
    print(wb.sheet_names())  # 获取所有表格名字
    
    sheet1 = wb.sheet_by_name('test1')  # 通过名字读取表格
    print(sheet1.name, sheet1.nrows, sheet1.ncols)

    for i in range(1, sheet1.nrows):
		print(sheet1.row_values(i))     #行
    
    for i in range(1, sheet1.ncols):
    	print(sheet1.col_values(i))     #列

    print(sheet1.cell(1,0).value)       #获取表格里的内容，三种方式
    print(sheet1.cell_value(1,0))
    print(sheet1.row(1)[0].value)

python读取pdf

import pdfplumber

path = 'TEST.pdf'
pdf = pdfplumber.open(path)

for page in pdf.pages:
    # 获取当前页面的全部文本信息，包括表格中的文字
    print(page.extract_text())                        

    for table in page.extract_tables():
        print(table)
        print('-----------------------')
        for row in table:
            print(row)
        print('-----------------------')

pdf.close()