1.python读取excel表格数据(打印行或列)
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import xlrd
# 文件的名字
file_name = "G:\szsmworkspace\\test\\a.xlsx"
# 打开文件
bk = xlrd.open_workbook(file_name)
# 代开sheet1
sh = bk.sheet_by_name("Sheet1")
# 获取行数 1141行
row_num = sh.nrows
# 获取列数 32列
col_num = sh.ncols
row_list = []
col_list = []
for i in range(1, row_num): # 1 是从第二行开始输出数据
# 获取第i行的正行的数据
row_data = sh.row_values(i)
# 把数据加入到row_list中
row_list.append(row_data)
for i in range(1, col_num):
# 获取第i列的数据
col_data = sh.col_values(i)
col_list.append(col_data)
# # 打印每一行的内容,打印出的为列表的形式
# for row in row_list:
# print(row)
# 打印每一列的内容,每一列的数据放在列表当中
for col in col_list:
print(col)
2.python读取excel表中的地址并验证是否能打开
#!/usr/bin/python
# -*- coding: UTF-8 -*-
"""
功能:获取excel表中的url地址,并批量自动开发所有url,输出是否能访问
"""
import re
import time
import urllib.request
import xlrd
import sys # 用于从外部传入参数
# 文件的名字
file_name = sys.argv[1] # 参数第一个
# file_name = "G:\szsmworkspace\\test\\a.xlsx"
# 打开文件
bk = xlrd.open_workbook(file_name)
# 代开sheet1
sh = bk.sheet_by_name("Sheet1")
# 获取行数 1141行
row_num = sh.nrows
# 获取列数 32列
col_num = sh.ncols
row_list = []
col_list = []
link_list_num = []
def getUrl():
"""
获取excel表中的所有url
:return: list
"""
for i in range(2, row_num): # 1 是从第二行开始输出数据
# 获取第i行的正行的数据
row_data = sh.row_values(i)
# 需要注意的是该方法需要list中的元素为字符型,若是整型,则需要先转换为字符型后再转为str类型。
row_data_str = str(row_data)
# print(row_data_str)
link_list = re.findall( # 使用正则把所有的连接放入list中
'[a-zA-z]+://[^\s]*/',
row_data_str)
# print(type(link_list)) # <class 'list'>
if len(link_list) != 0: # 只把不为空的放进去
link_list_num.append(link_list)
urlOpen()
def urlOpen():
"""
检索网页能不能打开
"""
opener = urllib.request.build_opener()
opener.addheaders = [('User-agent', 'Mozilla/49.0.2')]
for i in link_list_num:
print(i[0])
for j in range(0, len(i)):
tempUrl = i[j]
try:
opener.open(tempUrl)
print(tempUrl + '没问题')
except urllib.error.HTTPError:
print(tempUrl + '访问页面出错')
time.sleep(2)
except urllib.error.URLError:
print(tempUrl + '访问页面出错')
time.sleep(2)
time.sleep(0.1)
getUrl()
3.Python对Excel的读写主要有xlrd、xlwt、xlutils、openpyxl、xlsxwriter几种。
1.xlrd主要是用来读取excel文件
import xlrd
workbook = xlrd.open_workbook(u'有趣装逼每日数据及趋势.xls')
sheet_names= workbook.sheet_names()
for sheet_name in sheet_names:
sheet2 = workbook.sheet_by_name(sheet_name)
print sheet_name rows = sheet2.row_values(3) # 获取第四行内容
cols = sheet2.col_values(1) # 获取第二列内容
print rows
print cols
2.xlwt主要是用来写excel文件
import xlwt
wbk = xlwt.Workbook()
sheet = wbk.add_sheet('sheet 1')
sheet.write(0,1,'test text')#第0行第一列写入内容
wbk.save('test.xls')
3.xlutils结合xlrd可以达到修改excel文件目的
import xlrd
from xlutils.copy import copy
workbook = xlrd.open_workbook(u'有趣装逼每日数据及趋势.xls')
workbooknew = copy(workbook)
ws = workbooknew.get_sheet(0)
ws.write(3, 0, 'changed!')
workbooknew.save(u'有趣装逼每日数据及趋势copy.xls')
4.openpyxl可以对excel文件进行读写操作
from openpyxl import Workbook
from openpyxl import load_workbook
from openpyxl.writer.excel import ExcelWriter
workbook_ = load_workbook(u"新歌检索失败1477881109469.xlsx")
sheetnames =workbook_.get_sheet_names() #获得表单名字
print sheetnames
sheet = workbook_.get_sheet_by_name(sheetnames[0])
print sheet.cell(row=3,column=3).value
sheet['A1'] = '47'
workbook_.save(u"新歌检索失败1477881109469_new.xlsx")
wb = Workbook()
ws = wb.active
ws['A1'] = 4
wb.save("新歌检索失败.xlsx")
5.xlsxwriter可以写excel文件并加上图表
import xlsxwriter
def get_chart(series):
chart = workbook.add_chart({'type': 'line'})
for ses in series:
name = ses["name"]
values = ses["values"]
chart.add_series({
'name': name,
'categories': 'A2:A10',
'values':values
})
chart.set_size({'width': 700, 'height': 350})
return chart
if __name__ == '__main__':
workbook = xlsxwriter.Workbook(u'H5应用中心关键数据及趋势.xlsx')
worksheet = workbook.add_worksheet(u"每日PV,UV")
headings = ['日期', '平均值']
worksheet.write_row('A1', headings)
index=0
for row in range(1,10):
for com in [0,1]:
worksheet.write(row,com,index)
index+=1
series = [{"name":"平均值","values":"B2:B10"}]
chart = get_chart(series)
chart.set_title ({'name': '每日页面分享数据'})
worksheet.insert_chart('H7', chart)
workbook.close()