概述
@author: good-temper
'''
import urllib2
import bs4
import time
def getPage(urlStr):
'''
获取页面内容
'''
content = urllib2.urlopen(urlStr).read()
return content
def getNextPageUrl(currPageNum):
#http://list.jd.com/9987-653-655-0-0-0-0-0-0-0-1-1-页码-1-1-72-4137-33.html
url = u'http://list.jd.com/9987-653-655-0-0-0-0-0-0-0-1-1-'+str(currPageNum+1)+'-1-1-72-4137-33.html'
#是否有下一页
content = getPage(url);
soup = bs4.BeautifulSoup(content)
list = soup.findAll('span',{'class':'next-disabled'});
if(len(list) == 0):
return url
return ''
def analyzeList():
pageNum = 0
list = []
url = getNextPageUrl(pageNum)
while url !='':
soup = bs4.BeautifulSoup(getPage(url))
Pagelist = soup.findAll('div',{'class':'p-name'})
for elem in Pagelist:
soup1 = bs4.BeautifulSoup(str(elem))
list.append(soup1.find('a')['href'])
pageNum = pageNum+1
print pageNum
url = getNextPageUrl(pageNum)
return list
def analyzeContent(url):
return ''
def writeToFile(list,path):
f = open(path,'a')
for elem in list:
f.write(elem+'\n')
f.close()
if __name__ == '__main__':
list = analyzeList()
print '共抓取'+str(len(list))+'条\n'
writeToFile(list,u'E:\\jd_phone_list.dat');
总结
以上是编程之家为你收集整理的python抓取京东商城手机列表url实例代码全部内容，希望文章能够帮你解决python抓取京东商城手机列表url实例代码所遇到的程序开发问题。
如果您也喜欢它,动动您的小指点个赞吧
602392714
清零编程群