Python脚本开发练习

打印乘法口诀表

#!/usr/bin/python
#coding=utf-8

print("Hello,World....")
print("你好，欢迎来到Python的世界....")

i=1;
while i <= 9 :
    #print i
    j=1
    while j <= i:
        #print i,j
        print "%d*%d=%d"%(j,i,j*i),
        j+=1
    print('
')
    i+=1

结果:

Python文件处理

#!/usr/bin/python
#coding=utf-8
import sys
import os
import shutil

#创建目录
def mkdir(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if not isExists:
       os.makedirs(path)

#写文件
def Write(filename,context,model):
    #去除首位空格
    filename = filename.strip()
    #读取目录名称
    path = os.path.dirname(filename)
    #如果目录不存在则创建目录
    mkdir(path)
    #读取文件名称
    name = os.path.basename(filename)
    fp = open(filename,model)
    fp.write(context+'
')
    fp.close()
    print name

#删除文件
def deleteFile(filename):
    filename = filename.strip()
    if os.path.exists(filename):
       os.remove(filename)

#删除目录
def deleteDir(path,model):
    if os.path.exists(path):
       if model == 'rf':
          #强制删除目录以及目录下所有文件
          shutil.rmtree(path)
       else:
          #只有目录为空的时候才可以删除
          os.removedirs(path)
mkdir('/etl/etldata/tmp/p')
deleteDir('/etl/etldata/tmp','rf')
mkdir('/etl/etldata/script/python/test')
Write('/etl/etldata/script/python/p/testfile.csv','1','w');
Write('/etl/etldata/script/python/p/testfile.csv','2','a');
#deleteFile('/etl/etldata/script/python/p/testfile.csv')
deleteDir('/etl/etldata/script/python/p','rf')
#deleteDir('/etl/etldata/script/python1/test','rf')

 Python面向对象

#定义Student类
class Student:

    #定义getName方法,获取姓名
    def getName(self):
        print("My Name is Jim")
    #定义getAge方法,获取年龄
    def getAge(self):
        print("My Age is 18")

#实例化一个对象
s = Student()
s.getName()
s.getAge()

#添加属性
s.addres = '大连'
#获取属性
print(s.addres)

#coding:utf-8

#print("Hello,world")

#定义Student类
class Student:

    #定义初始化函数
    def __init__(self,name="InitName",weight=60,height=170):
        self.name = name
        self.weight = weight
        self.height = height
        self.age = 18.6

    def __str__(self):
        return self.name

    #定义getName方法,获取姓名
    def getName(self):
        print("My Name is %s" % (self.name) )
    #定义getAge方法,获取年龄
    def getAge(self):
        print("My Age is %f" % (self.age))

#实例化一个对象
s = Student('Jim')
print type(s)
s.getName()
s.getAge()
print(s.weight)
print(s)

#coding:utf-8
import xlrd
import os
import sys 
import cx_Oracle
import time
import sys
import codecs
import shutil
reload(sys)
sys.setdefaultencoding('utf-8')

#定义连接oracle数据库函数
def conn_orcl(hostname='192.168.0.18',user='jim',passwd='jim',database='orcl'):
    print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": Start connect to Oracle..."
    #user
    #passwd
    #hostname = 192.168.0.18 
    #database = 'orcl'
    conn_str=user+'/'+passwd+'@'+hostname+'/'+database
    try:
        conn = cx_Oracle.connect(conn_str)
    #conn = cx_Oracle.connect('scott/tiger1@192.168.0.18/orcl')
        print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": connect to %s Succeed" % (database)
        return conn
    except:
        print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": Connect to %s Failed" % (database)
        return
        
#执行sql语句【增加、删除、修改】       
def sqlDML(sql,db):
    #include: insert,update,delete
    cr = db.cursor()
    try:
        cr.execute(sql)
        cr.close()
        db.commit()
        print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": Excute Succeed"
    except:
        print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": Excute Failed"
        
#查询语句，返回元组tuple
def sqlSelect(sql,db):
    c = db.cursor()
    try:
        c.execute(sql)
        print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": Excute Succeed"
        return c
    except:
        print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": Excute Failed"
        return 

#创建目录
def mkdir(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if not isExists:
       os.makedir(path)

#递归创建目录
def mkdirs(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if not isExists:
       os.makedirs(path)

#删除目录
def rmdir(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if isExists:
       os.rmdir(path)

#递归删除目录
def rmdirs(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if isExists:
       #os.removedirs(path)
       shutil.rmtree(path)

#删除文件
def deleteFile(filename):
    filename = filename.strip()
    if os.path.exists(filename):
       os.remove(filename)    

#写文件
def writeText(filename,context,model):
    #去除首位空格
    filename = filename.strip()
    #读取目录名称
    path = os.path.dirname(filename)
    #如果目录不存在则创建目录
    mkdir(path)
    #读取文件名称
    name = os.path.basename(filename)
    fp = open(filename,model)
    fp.write(context+'
')
    fp.close()
    
def excel_to_csv(exclefilename,sheetname,csvfilename):
    data = xlrd.open_workbook(exclefilename)
    table = data.sheet_by_name(sheetname)
    print "excel文件为：%s" % (exclefilename)
    print "sheet页名称为：%s" %(sheetname)
    #获取行数和列数
    nrows = table.nrows
    print "行数：",nrows
    
    ncols = table.ncols
    print "列数：", ncols
    
    #定义分割符
    format = ','
    #先删除目标csv文件
    deleteFile(csvfilename)
    #默认去掉首行标题
    for i in range(1,nrows):
        s=''
        for j in range(0,ncols):
            s = s + str(table.row_values(i)[j]) + format
            #print table.row_values(i)[j]
        #print s
        #保存成csv文件
        writeText(csvfilename,s,'a')
    print time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time())),": translate %s to %s Succeed" % (exclefilename,csvfilename)
        #print table.row_values(i)[0]


#将数据文件加载到oracle数据库中
def load_to_db(db,filename,tabname,colnum):
    s=''
    for i in range(1,colnum+1):
        if i == colnum:
           s = s + ':' + str(i)
        else:
           s = s + ':' + str(i) + ','
    sql = 'insert into %s values(%s)' %(tabname,s)
    print sql
    cr = db.cursor()
    f =  codecs.open(filename)
    lines = f.readlines()
    
    for i in range(0,len(lines)):
        s = []
        for j in range(0,colnum):
            s.append(str(lines[i].strip("
").split(',')[j]))
            #print s[j]
        #lines[i].strip("
").split(',')[0]
        cr.execute(sql,s)
        #print s
        f.close() 
    cr.close()
    db.commit()

excel_to_csv('/etl/etldata/script/car/20170920.xlsx','标签','/etl/etldata/script/python_test/lab.csv')       
db = conn_orcl('192.168.11.43','jim','jim')
sql = 'delete from car_lab'    
sqlDML(sql,db)    
load_to_db(db,'/etl/etldata/script/python_test/lab.csv','car_lab',12)



#db = conn_orcl('192.168.11.43','jim','jim')
#sql = 'create table car_info_1 as select * from car_info where 1=2'
#sql = 'select * from car'
#c = sqlSelect(sql,db)
#print type(c)

#excel_to_csv('/etl/etldata/script/car/20170919.xlsx','太平洋汽车','/etl/etldata/script/python_test/lab.csv')

'''
for x in c :
       #返回的是元组tuple
       print type(x),len(x)
       print x[0],x[1],x[2],x[3]
'''       
#sqlDML(sql,db)
#data = xlrd.open_workbook('car.xlsx')

#通过名称获取
#table = data.sheet_by_name(u'Sheet3')

#通过索引顺序获取
#table = data.sheets()[0]

#通过索引顺序获取
#table = data.sheet_by_index(0)

#获取整行和整列的值（数组）
#table.row_values(i)
#table.col_values(i)

#获取行数和列数
#nrows = table.nrows
#ncols = table.ncols

 Python常用函数收集汇总:

#coding:utf-8
#filename:tools.py
#pyton常用函数收集汇总
import time
import sys
import os
import shutil
reload(sys)
sys.setdefaultencoding( "utf-8" )


#获取常用时间格式的函数
#'%Y-%m-%d' 2017-11-18
#'%Y%m%d'   20171118
#%Y%m%d%H'  2017111817
#空或其他   2017-11-18 17:26:35
def getTime(*format):
    now = ''
    try:
        format = format[0]
    except :
        pass 
    if format == '%Y-%m-%d':
        now = time.strftime('%Y-%m-%d',time.localtime(time.time()))
    elif format == '%Y%m%d':
        now = time.strftime('%Y%m%d',time.localtime(time.time()))
    elif format == '%Y%m%d%H':
        now = time.strftime('%Y%m%d%H',time.localtime(time.time()))
    else :
        now = time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time()))
    return now 
    

#创建目录
def mkdir(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if not isExists:
       os.makedirs(path)

#写字符到到文件中
def writeFile(filename,context,model):
    #去除首位空格
    filename = filename.strip()
    #读取目录名称
    path = os.path.dirname(filename)
    #如果目录不存在则创建目录
    mkdir(path)
    #读取文件名称
    name = os.path.basename(filename)
    fp = open(filename,model)
    fp.write(context+'
')
    fp.close()
    #print name

#删除文件
def deleteFile(filename):
    filename = filename.strip()
    if os.path.exists(filename):
       os.remove(filename)
         
#删除目录
def deleteDir(path,model):
    if os.path.exists(path):
       if model == 'rf':
          #强制删除目录以及目录下所有文件
          shutil.rmtree(path)
       else:
          #只有目录为空的时候才可以删除
          os.removedirs(path)
          
#判断文件是否存在
def isExistsFile(filename):
    result = False
    result = os.path.isfile(filename)
    return result
    
#读取文件内容
def getLines(filename):
    file_object = open(filename,'rb')
    lines = file_object.readlines()
    return lines

#获取本身脚本名称
def getSelfName():
    return sys.argv[0]
    
print getSelfName()

from selenium import webdriver
from pyquery import PyQuery as pq

#获取网页 urllib2获取
def getHtml(url):
    request = urllib2.Request(url)
    response = urllib2.urlopen(request,data=None)
    #html = unicode(response.read(),'utf-8')
    html = unicode(response.read(),'gbk')
    return html

    
#获取网页 PhantomJS获取
def getHtml2(url):
    driver = webdriver.PhantomJS(executable_path='/home/shutong/phantomjs/bin/phantomjs')
    driver.get(url)
    html = driver.page_source 
    driver.quit()
    return html 

 Python操作phantomjs

#coding:utf-8
import os
import re
import sys
import time
sys.path.append('/home/shutong/crawl/script/media') 
from tools import *
#import tushare as ts
from selenium import webdriver
from selenium.webdriver.common.keys import Keys

reload(sys)
sys.setdefaultencoding('utf-8')


driver = webdriver.PhantomJS()
url = "https://www.baidu.com/"
driver.get(url)
driver.get_screenshot_as_file('1.png')
elem = driver.find_element_by_id("kw")
elem.send_keys(u"北京")
driver.get_screenshot_as_file('2.png')
elem.send_keys(Keys.RETURN)
time.sleep(5)
driver.refresh()
driver.get_screenshot_as_file('3.png')

Python常用工具函数

#coding:utf-8
#filename:tools.py
#pyton常用函数收集汇总
import time
import sys
import os
import shutil
import MySQLdb
import urllib2
from pyquery import PyQuery as pq
from lxml import etree
import urllib
import sys 
import httplib
import datetime
import json
from selenium import webdriver
from urlparse import urljoin 
httplib.HTTPConnection._http_vsn = 10
httplib.HTTPConnection._http_vsn_str = 'HTTP/1.0'

#设置utf-8模式
reload(sys)
sys.setdefaultencoding( "utf-8" )


#获取常用时间格式的函数
#'%Y-%m-%d' 2017-11-18
#'%Y%m%d'   20171118
#%Y%m%d%H'  2017111817
#空或其他   2017-11-18 17:26:35
def getTime(*format):
    now = ''
    try:
        format = format[0]
    except :
        pass 
    if format == '%Y-%m-%d':
        now = time.strftime('%Y-%m-%d',time.localtime(time.time()))
    elif format == '%Y%m%d':
        now = time.strftime('%Y%m%d',time.localtime(time.time()))
    elif format == '%Y%m%d%H':
        now = time.strftime('%Y%m%d%H',time.localtime(time.time()))
    else :
        now = time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time()))
    return now 
    
    
#创建目录
def mkdir(path):
    #去除首位空格
    path = path.strip()
    #去除尾部符号
    path = path.rstrip('\') 
    #判断路径是否存在
    isExists = os.path.exists(path)
    if not isExists:
       #os.mkdirs(path)
       os.makedirs(path) 
#写文件
def Write(filename,context,model):
    #去除首位空格
    filename = filename.strip()
    #读取目录名称
    path = os.path.dirname(filename)
    #如果目录不存在则创建目录
    mkdir(path)
    #读取文件名称
    name = os.path.basename(filename)
    fp = open(filename,model)
    fp.write(context+'
')
    fp.close()
    #print name
#写字符到到文件中
def writeFile(filename,context,model):
    #去除首位空格
    filename = filename.strip()
    #读取目录名称
    path = os.path.dirname(filename)
    #如果目录不存在则创建目录
    mkdir(path)
    #读取文件名称
    name = os.path.basename(filename)
    fp = open(filename,model)
    fp.write(context+'
')
    fp.close()
    #print name

#删除文件
def deleteFile(filename):
    filename = filename.strip()
    if os.path.exists(filename):
       os.remove(filename)
         
#删除目录
def deleteDir(path,model):
    if os.path.exists(path):
       if model == 'rf':
          #强制删除目录以及目录下所有文件
          shutil.rmtree(path)
       else:
          #只有目录为空的时候才可以删除
          os.removedirs(path)
          
#判断文件是否存在
def isExistsFile(filename):
    result = False
    result = os.path.isfile(filename)
    return result
    
#读取文件内容
def getLines(filename):
    file_object = open(filename,'rb')
    lines = file_object.readlines()
    return lines
 
#处理字符
def repstr(name):
    name = str(name).replace('（','(').replace('）',')').replace(',',':')
    return str(name).strip() 
    
#保存字符串
def saveFile(filename,*name):
    format = ','
    context = repstr(name[0])
    for i in name[1:]:
        context = context + format + repstr(i)
    Write(filename,context,'a')

#保存字符串
def saveFile2(filename,*name):
    format = ','
    context = name[0]
    for i in name[1:]:
        context = context + format + str(i)
    context = str(context).replace('（','(').replace('）',')')
    Write(filename,context,'a')

#给数组去重
def uniqList(v_list):
    return list(set(v_list))

#获取网页函数1
def getHtml(url,*code):
    headers = {'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20100101 Firefox/23.0'}  
    request = urllib2.Request(url,headers=headers)
    response = urllib2.urlopen(request,data=None,timeout=60)
    if code:
        if code[0] == 'gbk':
            html = unicode(response.read(),'gbk')
        else:
            html = unicode(response.read(),str(code[0]))
    else:
        html = unicode(response.read(),'utf-8')
    return html

#获取网页函数2
def getHtml_JS(url,*path):
    driver = ''
    if path:
       print path[0]
       driver = webdriver.PhantomJS(executable_path=path[0])
    else:
       driver = webdriver.PhantomJS(executable_path='/home/shutong/phantomjs/bin/phantomjs')
    #driver.set_page_load_timeout(60)
    driver.get(url)
    html = driver.page_source
    driver.quit()
    return html    


#定义MySql数据库连接
def conn_mysql(host='192.168.11.43',user='root',passwd='root',db='edw'):
    conn = ''
    try:
        conn= MySQLdb.connect(
        host= host,
        port = 3306,
        user=user,
        passwd=passwd,
        db =db,
        )
        #print "连接mysql成功"
    except :
        #pass 
        print "连接mysql失败"
    return conn

#执行sql语句返回结果    
def excute_sql(conn,sql):
    #conn = conn_mysql(host='192.168.122.194',user='root',passwd='123456',db='label')
    cur = conn.cursor()
    cur.execute('set character_set_client = utf8')
    cur.execute('set character_set_server = utf8')
    cur.execute('set character_set_connection = utf8')
    cur.execute('set character_set_results = utf8')
    cur.execute('set collation_connection = utf8_general_ci')
    cur.execute('set collation_server = utf8_general_ci')
    result = cur.fetchmany(cur.execute(sql))
    cur.close()
    conn.commit()
    conn.close()
    return result
    
    
#处理url
def process_url(url,url_value):
    if url_value.startswith('http://'):
        pass 
    else:
        url_value = urljoin(url,url_value)
    return str(url_value)
#参数:
#1.filename 输出文件
#2.industry_id 行业ID
#3.url_type_id 
#4.v_url_name
#5.v_url_value
#6.web_type_id pc端[0]/移动端[1]
def process_data(inputfile,outputfile,industry_id,url_type_id,v_url_name,v_url_value,web_type_id):
    for line in getLines(inputfile):
        line = line.strip()
        url_name = ''
        url_value = ''
        web_type_id = str(web_type_id)
        web_name_id = line.split(',')[-2]
        date_id = line.split(',')[-1]
        #开始处理数据
        url_name = line.split(',')[v_url_name]
        url_value = str(line.split(',')[v_url_value]).replace('http://','')
        saveFile(outputfile,industry_id,url_type_id,url_name,url_value,web_type_id,web_name_id,date_id)

#获取本身脚本名称
def getSelfName():
    return sys.argv[0]