Python实现抓取网页生成Excel文件的方法示例

#-*- encoding:utf-8 -*-import sysimport localeimport stringimport tracebackimport datetimeimport urllib2from pyquery import PyQuery as pq# 确定运行环境的encodingreload(sys);sys.setdefaultencoding('utf8');f = open('gongsi.csv', 'w');for i in range(1,24):  d = pq(url="http://www.yourwebname.com/?Code=HANGYELINGYU&myFlag=allShow&SiteID=122&PageIndex=%d"%(i));  itemsa=d('dl dt a') #取title元素  itemsb=d('dl dd') #取title元素  for j in range(0,len(itemsa)):    f.write("%s,/"%s/"/n"%(itemsa[j].get('title'),itemsb[j*2].text));  #end for#end forf.close();