复制代码 代码如下:
#-*- coding: UTF-8 -*-
'''
Created on 2013-12-5
@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');
python,京东商城手机
更新日志
- 小骆驼-《草原狼2(蓝光CD)》[原抓WAV+CUE]
- 群星《欢迎来到我身边 电影原声专辑》[320K/MP3][105.02MB]
- 群星《欢迎来到我身边 电影原声专辑》[FLAC/分轨][480.9MB]
- 雷婷《梦里蓝天HQⅡ》 2023头版限量编号低速原抓[WAV+CUE][463M]
- 群星《2024好听新歌42》AI调整音效【WAV分轨】
- 王思雨-《思念陪着鸿雁飞》WAV
- 王思雨《喜马拉雅HQ》头版限量编号[WAV+CUE]
- 李健《无时无刻》[WAV+CUE][590M]
- 陈奕迅《酝酿》[WAV分轨][502M]
- 卓依婷《化蝶》2CD[WAV+CUE][1.1G]
- 群星《吉他王(黑胶CD)》[WAV+CUE]
- 齐秦《穿乐(穿越)》[WAV+CUE]
- 发烧珍品《数位CD音响测试-动向效果(九)》【WAV+CUE】
- 邝美云《邝美云精装歌集》[DSF][1.6G]
- 吕方《爱一回伤一回》[WAV+CUE][454M]