当前位置:首页 >> 脚本专栏

python读取html中指定元素生成excle文件示例

Python2.7编写的读取html中指定元素,并生成excle文件

复制代码 代码如下:
#coding=gbk
import string
import codecs
import os,time
import xlwt
import xlrd
from bs4 import BeautifulSoup
from xlrd import open_workbook

class LogMsg:
        def __init__(self,logfile,Level=0):
                try:
                        import logging
                        #self.logger = None
                        self.logger = logging.getLogger()
                        self.hdlr = logging.FileHandler(logfile)
                        formatter = logging.Formatter("[%(asctime)s]: %(message)s","%Y%m%d %H:%M:%S")
                        self.hdlr.setFormatter(formatter)
                        self.logger.addHandler(self.hdlr)
                        #logger.setLevel()
                        if Level == 10:
                                self.logger.setLevel(logging.DEBUG)
                        elif Level == 20:
                                self.logger.setLevel(logging.INFO)
                        elif Level == 30:
                                self.logger.setLevel(logging.WARNING)
                        elif Level == 40:
                                self.logger.setLevel(logging.ERROR)
                        elif Level == 50:
                                self.logger.setLevel(logging.CRITICAL)
                        else:
                                self.logger.setLevel(logging.NOTSET)
                except:
                        print "log init error!"
                        exit(1)

        def output(self,logInfo):
                Level = self.logger.getEffectiveLevel()
                try:
                        if Level == 10:
                                self.logger.debug(logInfo)
                        elif Level == 20:
                                self.logger.info(logInfo)
                        elif Level == 30:
                                self.logger.warning(logInfo)
                        elif Level == 40:
                                self.logger.error(logInfo)
                        elif Level == 50:
                                self.logger.critical(logInfo)
                        else:
                                self.logger.info(logInfo)
                except:
                        print "log output error!"
                        exit(1)

        def close(self):
                try:
                #logging.shutdown([self.hdlr])
                        self.logger.removeHandler(self.hdlr)
                except:
                        print "log closed error!"
                        exit(1)

Logtime = time.strftime("%Y%m%d%H%M%S",time.localtime())
logFileTime = time.strftime("%Y%m%d",time.localtime())
Logfile = '/data/pyExample/logs/htmlparser_%s.log' % logFileTime
log = LogMsg(Logfile,20)


DATAPATH = '/data/pyExample/'
XLSname = 'dangjian_'+Logtime+'.xls'


if __name__ == '__main__':
   

    wbk = xlwt.Workbook(encoding = 'gbk')
    sheet = wbk.add_sheet('基本内容导入模板')
    sheet.write(0,0,'内容类型 ')
    sheet.write(0,1,'栏目名称')
    sheet.write(0,2,'栏目编号')
    sheet.write(0,3,'内容名称')
    sheet.write(0,4,'时长')
    sheet.write(0,5,'关键字')
    sheet.write(0,6,'看点')
    sheet.write(0,7,'作者')
    sheet.write(0,8,'来源')
    sheet.write(0,9,'子内容1')
    sheet.write(0,10,'子内容2')
    xlsContent = []  
    files = os.listdir(DATAPATH)
    k = 0
    for f in files: 
        if os.path.splitext(f)[1] == '.html':
            content=[]
            log.output('当前文件:'+f)
            htmlFile =codecs.open(DATAPATH+f,'r','gbk')
            lines = htmlFile.readlines()
            if not lines:
                log.output ('not line')
            for line in lines:
                if line.strip()=='\n':
                    log.output('该处是空行')
                else:
                    line = line.replace(' ','')
                    soup  = BeautifulSoup(line)
                    for tdd in soup.findAll('td'): 
                        #print tdd.text.encode("gbk")
                        content.append(tdd.text.encode("gbk"))      
                #print line.encode('gbk')
            htmlFile.close()   
            for i in content:
                print content.index(i),',',i
                log.output(i)
                log.output(content.index(i))
            print '----------------------------------------'
           

            folderName =  content[6]
            contentName=  content[4]      
            duration =    filter(str.isdigit, content[16])
            int_duration = string.atoi(duration)*60
            str_duration = "%i"%int_duration
            keyWord =     content[6]
            desciption =  content[36]
            videoName_1 = content[10]
            print folderName
            print contentName
            print str_duration
            print keyWord
            print desciption
            print videoName_1
            log.output('输出xls数据:'+','+folderName+',,'+contentName+','+str_duration+','+keyWord+','+desciption+',管理员,华数编辑,'+videoName_1+',,')
            print k           
            sheet.write(k+1,0,'')
            sheet.write(k+1,1,folderName)
            sheet.write(k+1,2,'')
            sheet.write(k+1,3,contentName)
            sheet.write(k+1,4,str_duration)
            sheet.write(k+1,5,keyWord)
            sheet.write(k+1,6,desciption)
            sheet.write(k+1,7,'管理员')
            sheet.write(k+1,8,'华数编辑')
            sheet.write(k+1,9,videoName_1)
            sheet.write(k+1,10,'')
            k+=1

    wbk.save(DATAPATH + XLSname)       

    print '========================================='