python自动化--模块操作之re、MySQL、Excel

1 import re
2
3 # re.match只匹配字符串的开始，如果字符串开始不符合正则表达式，则匹配失败，函数返回None
4 print(re.match("www","wwwwccc").group())   #在起始位置匹配
5 print(re.match("www","wcccwww"))           #不在起始位置匹配，返回None
6
7 # re.search扫描整个字符串并返回第一个成功的匹配
8 print(re.search("haha","woshihahanishishui").group())
9
10 # re.findall从左到右扫描字符串，按顺序返回匹配，如果无匹配结果则返回空列表
11 print(re.findall("\d","one1two2three3four4"))
12 print(re.findall("\d","onetwothreefour"))
13
14 # sub用于替换字符串中的匹配项
15 print(re.sub("g..t","good","goot geet up"))
16 # split返回切割后的列表
17 print(re.split("\+","123+456*789+abcd"))

1 # ['AD123453', 'AC342123', 'AR343212']
2 # [A-Z]{2}\d{6}
3
4 # ^(13|14|15|17|18)\d{9}
5 # ^1[34578]\d{9}

1 import mysql.connector
2 config = {
3     "host":"127.0.0.1",
4     "user":"root",
5     "passwd":"vertrigo",
6     "port":3306,
7     "db":"test",
8     "charset":"utf8"
9 }
10
11 try:
12     db = mysql.connector.connect(**config)
13 except mysql.connector.Error as e:
14     print("连接数据库失败！",str(e))

1  2 cursor = db.cursor(buffered=True)   #buffered=True会把结果集保存到本地并一次性返回，这样可以提高性能
3 try:
4     #第一种：直接字符串插入方式
5     # sql_insert1="insert into student (name, age) values ('xiao', 27)"
6     # cursor.execute(sql_insert1)
7
8     #第二种：元组连接插入方式
9     sql_insert2="insert into student (name, age) values (%s, %s)"
10     #此处的%s为占位符，而不是格式化字符串，所以age用%s
11     # data=('xiaoqiang',18)
12     # cursor.execute(sql_insert2,data)
13     data = [("xiao",20),
14             ("xian",25),
15             ("rourou",27),
16             ("juju",28)]
17     cursor.executemany(sql_insert2,data)
18
19     #如果表引擎为Innodb，执行完成后需执行commit进行事务提交
20     db.commit()
21     #cursor.execute('commit')
22 except mysql.connector.Error as e:
23     print('插入失败！', str(e))
24 finally:
25     cursor.close()
26     db.close()

1 cursor = db.cursor(buffered=True)
2 try:
3     sql_del = "delete from student where name=%s and age=%s"
4     data_del = [
5         ("cui",28),
6         ("hao",27)]
7     cursor.executemany(sql_del,data_del)
8     db.commit()
9 except mysql.connector.Error as e:
10     print("删除数据失败！",str(e))
11 finally:
12     cursor.close()
13     db.close()

1 cursor = db.cursor(buffered=True)
2 try:
3     sql_update = "update student set age = 28 where name='kai'"
4     cursor.execute(sql_update)
5     db.commit()
6 except mysql.connector.Error as e:
7     print('修改数据失败',str(e))
8 finally:
9     cursor.close()
10     db.close()

1 cursor = db.cursor(buffered=True)
2 try:
3     # sql_select1 = "select * from student where age>%s"
4     # cursor.execute(sql_select1,(1,))
5
6     sql_select2 = "select * from student where age>%s"
7     cursor.execute(sql_select2,(26,))
8     datas1 = cursor.fetchall()         #如果在后加上[1]代表是取第一条数据
9
10     cursor.execute(sql_select2,(20,))
11     datas2 = cursor.fetchone()[1]      #如果在后加上[1]代表是取第一个字段
12     datas3 = cursor.fetchmany(5)
13
14     print(datas1)
15     print(datas2)
16     print(datas3)
17 except mysql.connector.Error as e:
18     print("查询数据失败！",str(e))
19 finally:
20     cursor.close()
21     db.close()

1 import openpyxl
2 #打开文件
3 path_file = "D:/PycharmProjects/open.xlsx"
4 wp = openpyxl.load_workbook(path_file)
5
6 print("获取所有工作表名：",wp.get_sheet_names())
7 # sheet = wp.get_sheet_by_name("Sheet1")   #获取指定的工作表sheet
8 # print("获取指定的工作表名:",sheet.title)
9 sheet2 = wp.get_active_sheet()             #获取活动的工作表sheet,一般是当前打开的sheet页
10 print("获取活动的工作表名:",sheet2.title)
11
12
13 # 操作单元格:数据的读取与写入
14 # 获取单元格数据
15 print(sheet2['A1'].value)
16 print(sheet2.cell(row=2,column=1).value)    #获取第二行第一列的值
17
18 # 数据的写入
19 sheet2.cell(row=4,column=1).value = "工作总结"
20 sheet2['C3']='cs'
21
22 print("最大列数",sheet2.max_column)
23 print("最大行数",sheet2.max_row)
24
25 # wp.save('D:/PycharmProjects/open1.xlsx')     #另存为
26 wp.save("open.xlsx")                           #保存,默认保存在当前目录下
27 wp.save(path_file)                             #覆盖保存

python正则中的match是在字符串的起始位置进行匹配，如果起始位置匹配不成功就会报错。如下例子：
import re
print(re.match("www","wwccc").group())
python正则中的search是在字符串中匹配第一次匹配成功的字符串并返回。如下例子：
import re
print(re.search("ws","wwcccwss").group())

<.*>意思为：匹配以<为开始的所有的字符，遇到回车换行中断匹配
<.*>结果为：<div><span>test</span></div>
<.*?>意思为：匹配以<为开始的字符串，出现一次就返回
<.*?>结果为：
<div>
<span>
<span>
<div>

abc = ("http://www.baidu.cn/archive/6688431.html")
print(abc.split('.')[-1])