├── youku_comments_filter
├── readme.md
└── pyld.py
├── XPath提取工具-代替Xpath checker-包含Windows下exe打包
├── readme.md
└── xpathld.py
├── 优酷评论抓取
├── readme.md
└── pyld.py
├── 抓取电商类网站全商品信息代码存档
├── 易迅-1 抓取全部类目URL.py
├── 1-国美抓取所有catid.py
├── 当当-1抓取所有catid.py
├── 淘宝-根据类目ID抓取所有商品ID.py
├── 易迅-3根据ID抓取商品信息.py
├── 2-国美根据catid获取所有页的商品ID.py
├── 易迅2 根据类目抓取ID.py
├── 当当-2根据列表URL抓取ID.py
├── 淘宝-实际应用中根据全部类目ID抓取商品ID并存入文件夹aa.py
└── 亚马逊1根据列表页抓取ID.py
├── README.md
├── 京东评论抓取-含Windows打包后exe
├── readme.md
└── jd_comments.py
└── get_jd.py
/youku_comments_filter/readme.md:
--------------------------------------------------------------------------------
1 | [Windows已编译可执行文件]( http://pan.baidu.com/s/1bn0jLmf )
2 |
--------------------------------------------------------------------------------
/XPath提取工具-代替Xpath checker-包含Windows下exe打包/readme.md:
--------------------------------------------------------------------------------
1 |
2 |
3 | # exe下载地址:http://share.weiyun.com/e9c01a28ca81fedb36d4c6f06a2c5880
4 | #密码:pyld
--------------------------------------------------------------------------------
/优酷评论抓取/readme.md:
--------------------------------------------------------------------------------
1 | # 源代码:pyld.py
2 |
3 | ##用法:双击,然后输入优酷视频网址,导出为csv格式的评论集合,行数为页码
4 |
5 |
6 | ## Windows下exe打包文件:http://pan.baidu.com/s/1yMBXs
7 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/易迅-1 抓取全部类目URL.py:
--------------------------------------------------------------------------------
1 | #! python2
2 | # coding:utf-8
3 | import requests
4 | from lxml.html import fromstring
5 |
6 | r = requests.get('http://searchex.yixun.com/')
7 | r.encoding = 'gbk'
8 | ss = r.text
9 | aa = fromstring(ss).xpath('//dd/a/@href')
10 | aa = '\n'.join(aa)
11 | with open('all_cat.txt', 'w') as f:
12 | f.write(aa)
13 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/1-国美抓取所有catid.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 |
3 | import requests
4 | from lxml.html import fromstring
5 | # import uniout
6 | import re
7 | r = requests.get('http://www.gome.com.cn/allcategory/')
8 |
9 | aa = fromstring(r.text).xpath('//div[@class="in"]/a/@href')
10 | aa = ''.join(aa)
11 | aa = re.findall('(cat\d+)\.', aa)
12 | with open('allcategory.txt', 'w') as f:
13 | f.write('\n'.join(aa))
14 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | Unofficial-API_for_Crawling
2 | ===========================
3 | #声明:
4 | 该源码仅为学习交流使用,不用于商业用途,如有侵权问题
5 |
6 | 请在[Issues](https://github.com/ClericPy/EC-Spider/issues)里留言
7 |
8 | ##介绍:
9 |
10 | 文件名:get_jd.py
11 |
12 | 用途:非官方-京东商品爬虫API(包括价格、评论等),评分在评价的返回页面里有,销量暂时无法抓取。
13 |
14 | 抓取所有评论页耗费时间:
15 |
16 | Python2 :3.19 s
17 |
18 | Python3 :4.21 s
19 |
20 | ## 函数说明:
21 | get_jd_rate:根据商品ID与页码获得评论页面的源代码,后续解析工作暂时不做了,就是解析Json
22 |
23 | get_jd_rate_totalpagenum:根据商品ID得到评论页码范围,返回值是整型数字,最大页码-1,因为从0开始
24 |
25 | get_jd_rate_all:根据商品ID抓取所有评论,返回结果是按顺序存放页面源码的列表
26 |
27 | get_jd_price:根据商品ID抓取价格,这个速度最快,而且从来不会封IP
28 |
29 | ######modifie:2014-11-09 11:23:36
30 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/当当-1抓取所有catid.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | try:
3 | from gevent import monkey
4 | monkey.patch_all()
5 | from gevent.pool import Pool
6 | except:
7 | from multiprocessing.dummy import Pool
8 | import requests
9 | import re
10 | from lxml.html import fromstring
11 |
12 | # 先抓下所有三级类目的href
13 | # 123654
14 | r = requests.get('http://category.dangdang.com/')
15 | aa = fromstring(r.text).xpath('//div[@class="cfied-list"]/div/a/@href')
16 |
17 | # 删除电子书部分
18 | aa = [re.sub('#.*', '', i) for i in aa if 'e.dangdang' not in i]
19 | # 将所有网址尾巴改成第一页带页码的
20 | aa = [i.replace('.html', '') for i in aa]
21 | aa = [i + '-pg1.html' for i in aa]
22 | aa = [i for i in aa if 'http' in i]
23 | aa = '\n'.join(aa)
24 | # 将图书的网址改成重定向以后的第一页
25 | aa = re.sub('all/\?category_path=', 'cp', aa)
26 |
27 | with open('all_cat.txt', 'w') as f:
28 | f.write(aa)
29 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/淘宝-根据类目ID抓取所有商品ID.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | try:
3 | from gevent import monkey
4 | monkey.patch_all()
5 | from gevent.pool import Pool
6 | except:
7 | from multiprocessing.dummy import Pool
8 | import re
9 | import requests
10 | '''Python2和3通用,注意下载好支持库,因为淘宝最大显示页数100页,为了使结果更有价值,按销量排序抓取,而且选中了合并同款商品'''
11 |
12 |
13 | def get_taobao_ids(catid, pagenum):
14 | if pagenum == 1:
15 | pagenum = 1
16 | else:
17 | pagenum = (pagenum - 1) * 96
18 | # print pagenum
19 | url = 'http://list.taobao.com/itemlist/default.htm?_input_charset=utf-8&json=on&cat={0}&sort=biz30day&msp=1&as=1&viewIndex=1&atype=b&style=list&same_info=1&tid=0&isnew=2&pSize=96&data-key=s&data-value={1}&data-action&module=page&s=0'.format(
20 | catid, pagenum)
21 | r = requests.get(url)
22 | ss = r.text
23 | ids = '\n'.join(re.findall('itemId":"(.*?)"', ss))
24 | return ids
25 |
26 |
27 | def get_ids_by_cat(catid):
28 | url = 'http://list.taobao.com/itemlist/default.htm?_input_charset=utf-8&json=on&cat={0}&sort=biz30day&msp=1&as=1&viewIndex=1&atype=b&style=list&same_info=1&tid=0&isnew=2&pSize=96&data-key=s&data-value=1&data-action&module=page&s=0'.format(
29 | catid)
30 | r = requests.get(url)
31 | ss = r.text
32 | totalPage = int(re.findall('totalPage":"(\d+)"', ss)[0])
33 | pagenums = range(1, totalPage + 1)
34 | pp = Pool(5)
35 | ss = pp.map(lambda x: get_taobao_ids(catid, x), pagenums)
36 | try:
37 | pp.close()
38 | pp.join()
39 | except:
40 | pass
41 | return '\n'.join(ss)
42 | if __name__ == '__main__':
43 | print(get_ids_by_cat(50052124).count('\n'))
44 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/易迅-3根据ID抓取商品信息.py:
--------------------------------------------------------------------------------
1 |
2 | # coding:utf-8
3 | try:
4 | from gevent import monkey
5 | monkey.patch_all()
6 | from gevent.pool import Pool
7 | except:
8 | from multiprocessing.dummy import Pool
9 | import requests
10 | from lxml.html import fromstring
11 | headers = {'Cookie': 'wsid=1001'}
12 |
13 |
14 | def getid(pid):
15 | while 1:
16 | try:
17 | pid = str(pid)
18 | url = 'http://item.yixun.com/item-{}.html'.format(pid)
19 | r = requests.get(url)
20 | xpath = fromstring(r.text).xpath
21 | title = xpath('/html/head/title/text()')[0]
22 | desc = xpath(
23 | '/html/head/meta[@name="description"]/@content|/html/head/meta[@name="Description"]/@content')[0]
24 | try:
25 | kw = xpath(
26 | '/html/head/meta[@name="Keywords"]/@content|/html/head/meta[@name="keywords"]/@content')[0]
27 | except:
28 | kw = 'Null'
29 | cat = '-'.join(xpath('//div[@class="mod_crumb"]/a/text()'))
30 | result = '\t'.join((pid, title, url, kw, desc, cat)) + '\n'
31 | # print result
32 | # return result
33 | with open('jieguo.txt', 'a') as f:
34 | f.write(result.encode('utf-8'))
35 | global jishu
36 | jishu += 1
37 | print('=' * 20, jishu, '/', zongshu, '=' * 20)
38 | return
39 | except:
40 | pass
41 | # print pid, 'retry'
42 | with open('all_id.txt') as f:
43 | all_id = set([i.strip() for i in f.readlines()])
44 |
45 | zongshu = len(all_id)
46 | jishu = 0
47 | pp = Pool(200)
48 | pp.map(getid, all_id)
49 | try:
50 | pp.close()
51 | pp.join()
52 | except:
53 | pass
54 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/2-国美根据catid获取所有页的商品ID.py:
--------------------------------------------------------------------------------
1 |
2 | # coding:utf-8
3 | try:
4 | from gevent import monkey
5 | monkey.patch_all()
6 | from gevent.pool import Pool
7 | except:
8 | from multiprocessing.dummy import Pool
9 | import sys
10 | import requests
11 | # 在windows的终端CMD下会有进度显示,总过程耗费时间看网速
12 |
13 |
14 | def getgome(cat):
15 | for i in range(3):
16 | try:
17 | url = ''.join(('http://www.gome.com.cn/p/json?module=async_search¶mJson={%22pageNumber%22%3A', '1', '%2C%22envReq%22%3A{%22catId%22%3A%22', str(
18 | cat), '%22%2C%22regionId%22%3A%2231010100%22%2C%22et%22%3A%22%22%2C%22XSearch%22%3Afalse%2C%22pageNumber%22%3A1%2C%22pageSize%22%3A48}}'))
19 | r = requests.get(url)
20 | totalpage = int(r.json()['num']['totalPage'])
21 | urls = [''.join(('http://www.gome.com.cn/p/json?module=async_search¶mJson={%22pageNumber%22%3A', str(i), '%2C%22envReq%22%3A{%22catId%22%3A%22', str(
22 | cat), '%22%2C%22regionId%22%3A%2231010100%22%2C%22et%22%3A%22%22%2C%22XSearch%22%3Afalse%2C%22pageNumber%22%3A1%2C%22pageSize%22%3A48}}')) for i in xrange(1, totalpage + 1)]
23 |
24 | def ff(url):
25 | while 1:
26 | try:
27 | r = requests.get(url, timeout=3)
28 | return '\n'.join([i['pId'] for i in r.json()['products']])
29 | except:
30 | continue
31 | pp = Pool(30)
32 | ss = pp.map(ff, urls)
33 | try:
34 | pp.close()
35 | pp.join()
36 | except:
37 | pass
38 | global jishu
39 | jishu += 1
40 | sys.stderr.write(str(jishu) + ' / ' + zongshu + '\r')
41 | return '\n'.join(ss) + '\n'
42 | except:
43 | continue
44 |
45 | with open('allcategory.txt') as f:
46 | allcategory = [i.strip() for i in f.readlines()]
47 | zongshu = str(len(allcategory))
48 | jishu = 0
49 | with open('allids.txt', 'w') as f:
50 | # 这里又开了Pool,但一开始我是用for单线程做的,因为每个类目已经开了多线程,结果用了很久
51 | p1 = Pool(50)
52 | ss = p1.map(getgome, allcategory)
53 | f.writelines(ss)
54 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/易迅2 根据类目抓取ID.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | try:
3 | from gevent import monkey
4 | monkey.patch_all()
5 | from gevent.pool import Pool
6 | except:
7 | from multiprocessing.dummy import Pool
8 |
9 | import requests
10 | import re
11 | from lxml.html import fromstring
12 |
13 | headers = {'Cookie': 'wsid=1001'}
14 | jishu = 0
15 |
16 |
17 | def getbypn(url1, pn):
18 | while 1:
19 | try:
20 | url = url1 + 'all/----1--{}---------.html'.format(pn)
21 | r = requests.get(url, headers=headers).text
22 | print('.')
23 | return '\n'.join(re.findall('commid="(\d+)"', r))
24 | except:
25 | pass
26 |
27 |
28 | def getid(url1):
29 | while 1:
30 | try:
31 | url = url1 + 'all/----1--1---------.html'
32 | r = requests.get(url, headers=headers).text
33 | ss = re.findall('commid="(\d+)"', r)
34 | if not ss:
35 | global jishu
36 | jishu += 1
37 | print('=' * 20, jishu, '/', zongshu, '=' * 20)
38 | return
39 | pn = fromstring(r).xpath(
40 | '//div[@class="sort_page_num"]/span/text()')[0].replace('/', '')
41 | if pn == '1':
42 | result = '\n'.join(ss) + '\n'
43 | else:
44 | pns = range(2, int(pn) + 1)
45 | pp = Pool(30)
46 | dd = pp.map(lambda x: getbypn(url1, x), pns)
47 | try:
48 | pp.close()
49 | pp.join()
50 | except:
51 | pass
52 | ss += dd
53 | result = '\n'.join(ss) + '\n'
54 | with open('all_id.txt', 'a') as f:
55 | f.write(result)
56 | global jishu
57 | jishu += 1
58 | print('=' * 20, jishu, '/', zongshu, '=' * 20)
59 | return
60 | except:
61 | pass
62 | with open('all_cat.txt') as f:
63 | all_cat = [i.strip() for i in f.readlines()]
64 |
65 |
66 | zongshu = len(all_cat)
67 | pp = Pool(55)
68 | pp.map(getid, all_cat)
69 | try:
70 | pp.close()
71 | pp.join()
72 | except:
73 | pass
74 |
--------------------------------------------------------------------------------
/优酷评论抓取/pyld.py:
--------------------------------------------------------------------------------
1 | # coding=utf-8
2 | print('正在初始化...')
3 | import requests
4 | import re
5 | from lxml.html import fromstring
6 | from multiprocessing.dummy import Pool
7 | from lxml import _elementpath
8 |
9 |
10 | class Youku_comment:
11 |
12 | """docstring for Youku_comment"""
13 |
14 | def __init__(self, raw_url):
15 |
16 | self.pid = re.findall('/id_(.*?)\.html', raw_url)[0]
17 | r1 = requests.get(raw_url)
18 | title = re.findall('
(.*?)', r1.text)[0]
19 | title = re.sub('\W', '', title).replace('在线播放优酷网视频高清在线观看', '')
20 | totalpn = self.get_totalpn(self.pid)
21 | print('视频ID:%s' % self.pid, '\n视频标题:%s' %
22 | title, '\n总页码数:%s\n正在抓取...' % totalpn)
23 |
24 | pp = Pool(30)
25 | pagenums = range(1, totalpn + 1)
26 | result = pp.map(self.get_comment, pagenums)
27 | pp.close()
28 | pp.join()
29 | result = [i for i in result if i]
30 | jieguo = '\n'.join(result).replace(
31 | ',//', '').replace('//', '').replace(',#', '')
32 | with open('%s.csv' % title, 'w', encoding='gbk') as f:
33 | f.write(jieguo.encode('gbk', 'ignore').decode('gbk'))
34 |
35 | def get_totalpn(self, pid):
36 | r = requests.get(
37 | 'http://comments.youku.com/comments/~ajax/vpcommentContent.html?__ap={"videoid":"%s","page":1}' % pid)
38 | totalpn = (int(r.json()['totalSize'].replace(',', '')) // 30) + 1
39 | return totalpn
40 |
41 | def get_comment(self, pagenum):
42 | for _ in range(5):
43 | try:
44 | r = requests.get(
45 | 'http://comments.youku.com/comments/~ajax/vpcommentContent.html?__ap={"videoid":"%s","page":%s}' % (self.pid, pagenum), timeout=3)
46 | sjson = r.json()
47 | scode = sjson['con']
48 | nxpath = fromstring(scode).xpath
49 | ss = nxpath('//p[@id]')
50 | ss = [i.text for i in ss if i.text]
51 | if ss:
52 | return ','.join(ss)
53 | except:
54 | pass
55 |
56 |
57 | print('注:试用版没有多次抓取、切换代理、GUI、回复包括原文、批量抓取、提取关键词等功能\n\n\n\n\n初始化结束,请输入优酷视频网址。')
58 | while 1:
59 | try:
60 | url = input('请输入网址:')
61 | Youku_comment(url)
62 | break
63 | except:
64 | print('错误,请重试')
65 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/当当-2根据列表URL抓取ID.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | try:
3 | from gevent import monkey
4 | monkey.patch_all()
5 | from gevent.pool import Pool
6 | except:
7 | from multiprocessing.dummy import Pool
8 | import requests
9 | import re
10 | from lxml.html import fromstring
11 | # //div[@class="inner"]/p[@class="name"]/a/@href
12 | jishu = 0
13 |
14 |
15 | def getbypn(url1, pn):
16 | while 1:
17 | try:
18 | url = re.sub('pg\d+', 'pg' + str(pn), url1)
19 | r = requests.get(url, timeout=5).text
20 | ss = fromstring(r).xpath(
21 | '//div[@class="inner"]/p[@class="name"]/a/@href')
22 | ss = re.findall('dangdang\.com/(\d+)\.html', ''.join(ss))
23 | print(pn)
24 | return '\n'.join(ss)
25 | except:
26 | pass
27 |
28 |
29 | def getid(url1):
30 | global jishu
31 | while 1:
32 | try:
33 | url = url1
34 | r = requests.get(url, timeout=5).text
35 | ss = fromstring(r).xpath(
36 | '//div[@class="inner"]/p[@class="name"]/a/@href')
37 | ss = re.findall('dangdang\.com/(\d+)\.html', ''.join(ss))
38 | if not ss:
39 | with open('finished.txt', 'a') as f:
40 | f.write(url1 + '\n')
41 | jishu += 1
42 | print('=' * 20, jishu, '/', zongshu, '=' * 20)
43 | return
44 | pn = fromstring(r).xpath(
45 | '//div[@name="Fy"]/span[3]/text()|//div[@class="page"]/span[3]/text()')[0].replace('/', '')
46 | if pn == '1':
47 | result = '\n'.join(ss) + '\n'
48 | else:
49 | pns = range(2, int(pn) + 1)
50 | pp = Pool(50)
51 | dd = pp.map(lambda x: getbypn(url1, x), pns)
52 | try:
53 | pp.close()
54 | pp.join()
55 | except:
56 | pass
57 | ss += dd
58 | result = '\n'.join(ss) + '\n'
59 | with open('all_id.txt', 'a') as f:
60 | f.write(result)
61 | with open('finished.txt', 'a') as f:
62 | f.write(url1 + '\n')
63 | jishu += 1
64 | print('=' * 20, jishu, '/', zongshu, '=' * 20)
65 | return
66 | except Exception as e:
67 | print(url1, e)
68 | pass
69 | with open('all_cat.txt') as f:
70 | all_cat = set([i.strip() for i in f.readlines()])
71 | try:
72 | with open('finished.txt') as f:
73 | finish = set([i.strip() for i in f.readlines()])
74 | except:
75 | finish = set()
76 | all_cat = all_cat - finish
77 | zongshu = len(all_cat)
78 | pp = Pool(200)
79 | pp.map(getid, all_cat)
80 | try:
81 | pp.close()
82 | pp.join()
83 | except:
84 | pass
85 |
--------------------------------------------------------------------------------
/京东评论抓取-含Windows打包后exe/readme.md:
--------------------------------------------------------------------------------
1 | #usage:
2 | double click...
3 | #用法:
4 | 双击啊……
5 | #为了避免拿来主义,试用版源代码和编译好直接在Windows下运行的程序都进行功能限定 :
6 |
7 | ####当前功能仅限单商品爬虫、分类页商品ID爬虫(不是搜索结果页)、根据商品ID列表(TXT)抓取评论
8 |
9 | ####未包含功能:切换代理、GUI、搜索结果页爬虫、结果合并、评论时间与图片抓取、评论用户信息抓取
10 |
11 | #####exe打包文件下载地址:http://share.weiyun.com/6d85ad2179b92e5fea4896755d3c64e3,解压缩密码pyld
12 |
13 | #demo:
14 | ================================================================================
15 |
16 | 功能列表:
17 |
18 | 1. 输入单个商品页地址或商品ID========>导出评论(pid.ini)
19 |
20 | 2. 输入商品列表页地址(比如某类目,事先最好按评论数排序)========>该类目下有评论的ID(类目标题.txt)
21 |
22 | 3. 输入文件名(类目标题.txt)========>得到该类目下所有商品评论(类目.ini)
23 |
24 | 4. 输入exit或quit退出程序
25 |
26 | 以上模式自动识别,请输入指令:
27 |
28 | http://list.jd.com/list.html?cat=6144%2C6167%2C6173&ev=705_7895%40exbrand_%E7%92%A7%E6%98%9F%40&page=1&sort=sort_commentcount_desc&JL=3_%E5%93%81%E7%89%8C_%E7%92%A7%E6%98%9F
29 | start the mission for product-list pages...
30 | get http://list.jd.com/list.html?cat=6144%2C6167%2C6173&ev=705_7895%40exbrand_%E7%92%A7%E6%98%9F%40&page=1&sort=sort_commentcount_desc&JL=3_%E5%93%81%E7%89%8C_%E7%92%A7%E6%98%9F
31 | 已经出现评价数量为0的商品,程序终止...
32 | 结果已存入璧星和田玉耳饰.txt
33 | ['1060917739', '1034221311', '1033921135', '1033919980', '1055982851', '1212390180', '1212395162', '1212402141', '1255630033', '1285571849', '1334591695', '1334612767']
34 |
35 | ================================================================================
36 |
37 | 功能列表:
38 | 1. 输入单个商品页地址或商品ID========>导出评论(pid.ini)
39 | 2. 输入商品列表页地址(比如某类目,事先最好按评论数排序)========>该类目下有评论的ID(类目标题.txt)
40 | 3. 输入文件名(类目标题.txt)========>得到该类目下所有商品评论(类目.ini)
41 | 4. 输入exit或quit退出程序
42 | 以上模式自动识别,请输入指令:
43 | 璧星和田玉耳饰.txt
44 | ['1060917739', '1034221311', '1033921135', '1033919980', '1055982851', '1212390180', '1212395162', '1212402141', '1255630033', '1285571849', '1334591695', '1334612767']
45 | . . 1060917739已完成-1/12
46 | 所有结果已存入璧星和田玉耳饰.ini
47 | . . 1034221311已完成-2/12
48 | 所有结果已存入璧星和田玉耳饰.ini
49 | 1033921135已完成-3/12
50 | 所有结果已存入璧星和田玉耳饰.ini
51 | 1033919980已完成-4/12
52 | 所有结果已存入璧星和田玉耳饰.ini
53 | 1055982851已完成-5/12
54 | 所有结果已存入璧星和田玉耳饰.ini
55 | 1212390180已完成-6/12
56 | 所有结果已存入璧星和田玉耳饰.ini
57 | 1212395162已完成-7/12
58 | 所有结果已存入璧星和田玉耳饰.ini
59 | 1212402141已完成-8/12
60 | 所有结果已存入璧星和田玉耳饰.ini
61 | 1255630033已完成-9/12
62 | 所有结果已存入璧星和田玉耳饰.ini
63 | 1285571849已完成-10/12
64 | 所有结果已存入璧星和田玉耳饰.ini
65 | 1334591695已完成-11/12
66 | 所有结果已存入璧星和田玉耳饰.ini
67 | 1334612767已完成-12/12
68 | 所有结果已存入璧星和田玉耳饰.ini
69 |
70 | ================================================================================
71 |
72 | 功能列表:
73 | 1. 输入单个商品页地址或商品ID========>导出评论(pid.ini)
74 | 2. 输入商品列表页地址(比如某类目,事先最好按评论数排序)========>该类目下有评论的ID(类目标题.txt)
75 | 3. 输入文件名(类目标题.txt)========>得到该类目下所有商品评论(类目.ini)
76 | 4. 输入exit或quit退出程序
77 | 以上模式自动识别,请输入指令:
78 | 1060917739
79 | 1060917739
80 | . . 1060917739已完成,结果已存入1060917739.txt
81 |
82 | ================================================================================
83 |
84 | 功能列表:
85 | 1. 输入单个商品页地址或商品ID========>导出评论(pid.ini)
86 | 2. 输入商品列表页地址(比如某类目,事先最好按评论数排序)========>该类目下有评论的ID(类目标题.txt)
87 | 3. 输入文件名(类目标题.txt)========>得到该类目下所有商品评论(类目.ini)
88 | 4. 输入exit或quit退出程序
89 | 以上模式自动识别,请输入指令:
90 | http://item.jd.com/1021919082.html
91 | 1021919082
92 | 1021919082已完成,结果已存入1021919082.txt
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/淘宝-实际应用中根据全部类目ID抓取商品ID并存入文件夹aa.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | try:
3 | from gevent import monkey
4 | monkey.patch_all()
5 | from gevent.pool import Pool
6 | except:
7 | from multiprocessing.dummy import Pool
8 | import re
9 | import requests
10 | import glob
11 | '''
12 | 淘宝并行开太多会需要验证码,只要浏览器打完验证码,把cookies里的那句sec的放入header就可以跳过去了,目前测试Pool大小设定在5比较持久……但还是会要验证码,10以上都会要打验证码
13 | '''
14 |
15 | proxies = {}
16 |
17 | headers = {'Host': 'list.taobao.com', 'User-Agent':
18 | 'Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0', 'Cookie': 'sec=5462c34d67e290446e405972f4d684630f8b4046'}
19 |
20 |
21 | def get_taobao_ids(catid, pagenum):
22 | if pagenum == 1:
23 | pagenum = 1
24 | else:
25 | pagenum = (pagenum - 1) * 96
26 | while 1:
27 | try:
28 | # print pagenum
29 | url = 'http://list.taobao.com/itemlist/default.htm?_input_charset=utf-8&json=on&cat={0}&sort=biz30day&msp=1&as=1&viewIndex=1&atype=b&style=list&same_info=1&tid=0&isnew=2&pSize=96&data-key=s&data-value={1}&data-action&module=page&s=0'.format(
30 | catid, pagenum)
31 | r = requests.get(url, headers=headers, proxies=proxies, timeout=5)
32 | ss = r.text
33 | ids = '\n'.join(re.findall('itemId":"(.*?)"', ss))
34 | print pagenum / 96, 'get'
35 | return ids
36 | except Exception as e:
37 | print('retry fen')
38 | continue
39 |
40 |
41 | def get_ids_by_cat(catid):
42 | while 1:
43 | try:
44 | url = 'http://list.taobao.com/itemlist/default.htm?_input_charset=utf-8&json=on&cat={0}&sort=biz30day&msp=1&as=1&viewIndex=1&atype=b&style=list&same_info=1&tid=0&isnew=2&pSize=96&data-key=s&data-value=1&data-action&module=page&s=0'.format(
45 | catid)
46 | r = requests.get(url, headers=headers, proxies=proxies, timeout=5)
47 | ss = r.text
48 | # print ss
49 | if '"itemList":null' in ss:
50 | return
51 | totalPage = int(re.findall('totalPage":"(\d+)"', ss)[0])
52 | print 'start', catid, '=' * 50, '\ntotalPage', totalPage
53 | pagenums = range(1, totalPage + 1)
54 | pp = Pool(5)
55 | ss = pp.map(lambda x: get_taobao_ids(catid, x), pagenums)
56 | try:
57 | pp.close()
58 | pp.join()
59 | except:
60 | pass
61 | ss = '\n'.join(ss) + '\n'
62 | with open('./aa/' + str(catid) + '.txt', 'w') as f:
63 | f.write(ss)
64 | jishu = len(glob.glob('./aa/*.*'))
65 | print jishu, '/', zongshu, 'completed'
66 | return
67 | except Exception as e:
68 | print('retry zong', catid, e)
69 | continue
70 | with open('all_catid.txt') as f:
71 | cats = [i.strip() for i in f.readlines()]
72 | zongshu = len(cats)
73 |
74 | cats = set(cats) - set([re.search('aa.*?(\d+)\.txt', i).group(1)
75 | for i in glob.glob('./aa/*')])
76 |
77 | for i in cats:
78 | # print i
79 | get_ids_by_cat(i)
80 |
--------------------------------------------------------------------------------
/youku_comments_filter/pyld.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | print('正在初始化...')
3 | import requests
4 | import re
5 | from lxml.html import fromstring
6 | import pyautogui
7 | import sys
8 | import os
9 | from multiprocessing.dummy import Pool
10 | from lxml import _elementpath
11 |
12 |
13 | class Youku_comment:
14 |
15 | """docstring for Youku_comment"""
16 |
17 | def __init__(self, raw_url):
18 |
19 | self.pid = re.findall('/id_(.*?)\.html', raw_url)[0]
20 | r1 = requests.get(raw_url)
21 | title = re.findall('(.*?)', r1.text)[0]
22 | title = re.sub('\W', '', title).replace('在线播放优酷网视频高清在线观看', '')
23 | totalpn = self.get_totalpn(self.pid)
24 | print('视频ID:%s' % self.pid, '\n视频标题:%s' %
25 | title, '\n总页码数:%s\n正在抓取...' % totalpn)
26 |
27 | pp = Pool(30)
28 | pagenums = range(1, totalpn + 1)
29 | result = pp.map(self.get_comment, pagenums)
30 | pp.close()
31 | pp.join()
32 | result = [i for i in result if i]
33 | self.aa = sum(result, [])
34 | # print(jieguo)
35 | # with open('%s.csv' % title, 'w', encoding='gbk') as f:
36 | # f.write(jieguo.encode('gbk', 'ignore').decode('gbk'))
37 |
38 | def get_totalpn(self, pid):
39 | r = requests.get(
40 | 'http://comments.youku.com/comments/~ajax/vpcommentContent.html?__ap={"videoid":"%s","page":1}' % pid)
41 | totalpn = (int(r.json()['totalSize'].replace(',', '')) // 30) + 1
42 | return totalpn
43 |
44 | def get_comment(self, pagenum):
45 | for _ in range(5):
46 | try:
47 | r = requests.get(
48 | 'http://comments.youku.com/comments/~ajax/vpcommentContent.html?__ap={"videoid":"%s","page":%s}' % (self.pid, pagenum), timeout=3)
49 | sjson = r.json()
50 | scode = sjson['con']
51 | ss = re.findall('.*?
', scode, flags=re.S)
52 | ss = [re.sub('<.*?>', '', i) for i in ss]
53 | if ss:
54 | return ss
55 | except:
56 | pass
57 |
58 |
59 | def filt1(str1, kws):
60 | kws = kws.split(' ') if kws else 'OST 背景 音乐 旋律 歌曲 调子 music 耳熟 BGM 谁唱的 来自 出自 原声'.split(
61 | ' ')
62 | for i in kws:
63 | if i in str1:
64 | return str1
65 |
66 |
67 | def quchong(ll):
68 | ss = ''
69 | for i in ll:
70 | if i in ss:
71 | continue
72 | else:
73 | ss = ss + '\n' + i
74 | return ss
75 |
76 | while 1:
77 | try:
78 | url = pyautogui.prompt('请输入网址:')
79 | if not url:
80 | break
81 | tt = Youku_comment(url)
82 | pinglun = tt.aa
83 | while 1:
84 | kws = pyautogui.prompt('请输入关键词,多个请用空格隔开(直接回车则代表找背景音乐):')
85 | kws = kws if kws else 0
86 | ss = [filt1(i, kws) for i in pinglun]
87 | ss = [i for i in ss if i]
88 | ss = quchong(ss)
89 | print('检索结果:\n')
90 | print(ss)
91 | jixu = pyautogui.confirm(
92 | text='是否要继续检索', title='请确认', buttons=['是', '否'])
93 | if jixu == '否':
94 | break
95 |
96 | except Exception as e:
97 | print(e)
98 | print('错误,请重试')
99 | os.system('pause')
100 |
--------------------------------------------------------------------------------
/get_jd.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | # Compatible with Python2.x & 3.x
3 | # Email:lidongone@qq.com
4 | try:
5 | from gevent import monkey # 有gevent就用它比较快,没有就用内置多线程,同时也为py3兼容
6 | monkey.patch_all()
7 | from gevent.pool import Pool
8 | except:
9 | from multiprocessing.dummy import Pool # py2和3通用的多线程
10 | import requests
11 | import json
12 | import re
13 | # import uniout。这个库可以让python2像3一样print中文列表
14 |
15 |
16 | '''
17 | #声明:
18 | 该源码仅为学习交流使用,不用于商业用途,如有侵权问题
19 |
20 | 请及时联系lidongone@qq.com撤销全部代码
21 |
22 | ##介绍:
23 |
24 | 文件名:get_jd.py
25 | 用途:非官方-京东商品爬虫API(包括价格、评论等),评分在评价的返回页面里有,销量暂时无法抓取。
26 |
27 | 抓取所有评论页耗费时间:
28 |
29 | Python2 :3.19 s
30 |
31 | Python3 :4.21 s
32 |
33 | ## 函数说明:
34 | get_jd_rate:根据商品ID与页码获得评论页面的源代码,后续解析工作暂时不做了,就是解析Json
35 |
36 | get_jd_rate_totalpagenum:根据商品ID得到评论页码范围,返回值是整型数字,最大页码-1,因为从0开始
37 |
38 | get_jd_rate_all:根据商品ID抓取所有评论,返回结果是按顺序存放页面源码的列表
39 |
40 | get_jd_price:根据商品ID抓取价格,这个速度最快,而且从来不会封IP
41 |
42 | ######modifie:2014-11-09 11:23:36
43 | '''
44 | # 没这header就抓不到
45 | headers = {'Host': 'club.jd.com',
46 | 'Referer': 'http://item.jd.com/0.html'}
47 |
48 |
49 | def get_jd_title(pid):
50 | aa = get_jd_rate(pid, 0)
51 | try:
52 | title = json.loads(aa)["comments"][0]['referenceName']
53 | except:
54 | title = 'Null'
55 | return title
56 |
57 |
58 | def get_jd_rate(pid, pagenum):
59 | '''页码从0开始,在网页上显示的第一页'''
60 | for i in range(20):
61 | # 因为经常抓到空数据,所以重试20次(本来是while 1)
62 | try:
63 | r = requests.get(
64 | 'http://club.jd.com/productpage/p-{}-s-0-t-3-p-{}.html'.format(pid, pagenum), timeout=1, headers=headers)
65 | if 'content-length' in r.headers:
66 | # 一般它的值要么是0说明没抓到数据(包括页码超出),要么不存在
67 | # print('retry')
68 | continue
69 | else:
70 | # print(pid, pagenum, 'get it')
71 | return r.text
72 | # continue
73 | break
74 | except Exception as e:
75 | # print e
76 | continue
77 | # print(pid, pagenum, 'failed')
78 |
79 |
80 | def get_jd_rate_totalpagenum(pid):
81 | # 得到的是pagenum的最大数字,页面上显示的页码,还要+1
82 | try:
83 | totalpn = json.loads(get_jd_rate(pid, 0))[
84 | 'productCommentSummary']['commentCount']
85 | return totalpn // 10
86 | except:
87 | # print('failed')
88 | return -1
89 |
90 |
91 | def get_jd_rate_all(pid):
92 | maxpn = get_jd_rate_totalpagenum(pid)
93 | if maxpn == -1:
94 | # print('null')
95 | return
96 | pp = Pool(100)
97 | result = pp.map(
98 | lambda x: get_jd_rate(x[0], x[1]), list(zip([pid] * (maxpn + 1), range(maxpn + 1))))
99 | try:
100 | pp.close()
101 | pp.join()
102 | except:
103 | pass
104 | return result
105 |
106 |
107 | def get_jd_price(*pid):
108 | # 可以是多个PID
109 | pids = ','.join(['J_{}'.format(i) for i in pid])
110 | url = 'http://p.3.cn/prices/mgets?skuids=' + pids
111 | r = requests.get(url)
112 | return r.content
113 |
114 |
115 | def getjd(pid):
116 | aa = get_jd_rate_all(pid)
117 | # print aa[0]
118 |
119 | aa = [json.loads(i)['comments'] for i in aa if i]
120 | aa = sum(aa, [])
121 | aa = [i['content'].strip() for i in aa]
122 |
123 | return '\n'.join(aa)
124 | if __name__ == '__main__':
125 | import time
126 | aa = time.time()
127 | print(getjd(919979))
128 | print(get_jd_title(919979))
129 | print(time.time() - aa)
130 |
--------------------------------------------------------------------------------
/XPath提取工具-代替Xpath checker-包含Windows下exe打包/xpathld.py:
--------------------------------------------------------------------------------
1 | from tkinter import *
2 | import requests
3 | from lxml.html import fromstring
4 |
5 |
6 | def getit(url1, xpath1, np1):
7 | cout = []
8 | if '----' in np1:
9 | np, domain = np1.split('----')
10 | else:
11 | np = np1
12 | domain = ''
13 | if '----' in url1:
14 | url, host = url1.split('----')
15 | else:
16 | url = url1
17 | host = ''
18 | while 1:
19 | zhuangtai.set(url)
20 | headers = {'Referer': url, 'User-Agent':
21 | 'Mozilla/5.0 (Windows NT 6.3; WOW64; rv:35.0) Gecko/20100101 Firefox/35.0'}
22 | try:
23 | r = requests.get(url, headers=headers)
24 | except:
25 | zhuangtai.set('网址错误')
26 | return
27 | scode = r.content
28 | try:
29 | ss = scode.decode('utf-8')
30 | except:
31 | try:
32 | ss = scode.decode('gb18030')
33 | except:
34 | return '该网页编码不是utf-8或gb18030'
35 | xpath = fromstring(ss).xpath
36 | result = []
37 | for x in xpath1.strip().split('\n'):
38 | tt = xpath(x)
39 | if x.endswith('@href') and host:
40 | tt = [host + i for i in tt]
41 | result.append(tt)
42 | result = ['\t'.join(i) for i in list(zip(*result))]
43 | cout += result
44 | if np.strip() == '':
45 | break
46 | nextpage = xpath(np)
47 | if not nextpage:
48 | break
49 | if nextpage and domain:
50 | url = domain + nextpage[0]
51 | else:
52 | url = nextpage[0]
53 |
54 | return '\n'.join(cout)
55 |
56 |
57 | def settext(ss=None):
58 | text1.delete(0.0, END)
59 | text1.insert(0.0, getit(wangzhi.get(), xpath1.get(0.0, END), nppath.get()))
60 |
61 |
62 | def getabout(ss=None):
63 | text1.delete(0.0, END)
64 | text1.insert(
65 | 0.0, '简介\n\n\n结果:\n\t多行Xpath的返回结果按顺序用Tab分隔,可以直接复制到Excel\n\n输入URL:\n\n\t如果@href属性是相对地址,可在末尾用四个-隔开带上缺失域名,如:http://em.scnu.edu.cn/article/xueyuantongzhi/yanban/----http://em.scnu.edu.cn\n\n<下一页>Xpath:\n\n\t如果下一页URL是相对地址,请在末尾用四个-隔开带上缺失路径,如://li/a[text()="下一页"]/@href----http://em.scnu.edu.cn/article/xueyuantongzhi/yanban/\n\n\n\n注:该程序仅做交流使用,如有问题联系lidongone@qq.com,当前版本0.1处于alpha测试阶段,功能仅限于自动查找下一页的单线程爬虫(可以只抓单页)。待完成功能:切换代理、动态页面、多线程加速等')
66 |
67 |
68 | root = Tk()
69 | # root.update() # update window ,must do
70 | # curWidth = 800 # root.winfo_reqwidth() # get current width
71 | # curHeight = 600 # root.winfo_height() # get current height
72 | scnWidth, scnHeight = root.maxsize() # get screen width and height
73 | # now generate configuration information
74 | # tmpcnf = '%dx%d+%d+%d' % (curWidth, curHeight,
75 | # (scnWidth - curWidth) / 2, (scnHeight - curHeight) / 2)
76 | root.geometry('800x600+%d+%d' % (scnWidth / 5, scnHeight / 6))
77 | # root.resizable(width=0, height=0)
78 |
79 |
80 | root.columnconfigure(0, weight=1)
81 | root.rowconfigure(0, weight=1)
82 |
83 |
84 | root.title("Xpath版网页提取工具(手工爬虫) 0.10v - Alpha")
85 |
86 | #########
87 | jieguolab = LabelFrame(root, text='结果:')
88 | jieguolab.rowconfigure(0, weight=1)
89 | # jieguolab.columnconfigure(0, weight=1)
90 | jieguolab.grid(row=0, columnspan=2, column=0, sticky=W + E + S + N)
91 | ss = StringVar()
92 | text1 = Text(jieguolab)
93 | text1.pack(expand=1, side=LEFT, fill=BOTH)
94 | ###
95 | xpathframe = LabelFrame(
96 | jieguolab, width=300, text="输入Xpath:")
97 | xpathframe.pack(side=RIGHT, fill=BOTH)
98 |
99 |
100 | xpath1 = Text(xpathframe)
101 | xpath1.bind('', settext)
102 |
103 | xpath1.pack(expand=1, fill=BOTH)
104 | #######
105 | urlframe = LabelFrame(
106 | root, text="输入URL:")
107 | urlframe.grid(row=1, column=0, sticky=W + E)
108 | wangzhi = StringVar()
109 | urlentry = Entry(urlframe, textvariable=wangzhi)
110 | urlentry.bind('', settext)
111 | urlentry.pack(expand=1, fill=BOTH)
112 | #######
113 | pagenumframe = LabelFrame(
114 | root, text='输入<下一页>Xpath:')
115 | pagenumframe.grid(row=2, column=0, sticky=W + E)
116 | nppath = StringVar()
117 | nextpagexpath = Entry(pagenumframe, textvariable=nppath)
118 | nextpagexpath.bind('', settext)
119 | nextpagexpath.pack(expand=1, fill=BOTH)
120 |
121 | ###
122 | start_button = Button(root, text='开始', height=3, command=settext)
123 | start_button.grid(column=0, columnspan=2, sticky=W + E)
124 | guanyu = Button(root, text='关于', height=3, command=getabout)
125 | root.bind('', getabout)
126 | guanyu.grid(column=0, columnspan=2, sticky=W + E)
127 | zhuangtai = StringVar()
128 | dangqianurl = Label(root, textvariable=zhuangtai, wraplength=600)
129 | zhuangtai.set('当前网址:')
130 | dangqianurl.grid(column=0, columnspan=2, sticky=W)
131 | getabout()
132 | root.mainloop()
133 |
--------------------------------------------------------------------------------
/京东评论抓取-含Windows打包后exe/jd_comments.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | from multiprocessing.dummy import Pool
3 | import requests
4 | import json
5 | import re
6 | from lxml.html import fromstring
7 | from lxml import _elementpath
8 |
9 | # 没这header就抓不到
10 | headers = {'Host': 'club.jd.com',
11 | 'Referer': 'http://item.jd.com/0.html'}
12 |
13 |
14 | def get_jd_rate(pid, pagenum):
15 | '''!页码从0开始,在网页上显示的第一页'''
16 | for i in range(20):
17 | # 因为经常抓到空数据,所以重试20次(本来是while 1)
18 | try:
19 | r = requests.get(
20 | 'http://club.jd.com/productpage/p-{}-s-0-t-3-p-{}.html'.format(pid, pagenum), timeout=1, headers=headers)
21 | if 'content-length' in r.headers:
22 | # 一般它的值要么是0说明没抓到数据(包括页码超出),要么不存在
23 | # print('retry')
24 | continue
25 | else:
26 | print('.', end=' ')
27 | return r.text
28 | # continue
29 | break
30 | except Exception as e:
31 | # print e
32 | continue
33 | return ''
34 | # print(pid, pagenum, 'failed')
35 |
36 |
37 | def get_jd_rate_totalpagenum(pid):
38 | # !得到的是pagenum的最大数字,页面上显示的页码,还要+1
39 | try:
40 | totalpn = json.loads(get_jd_rate(pid, 0))[
41 | 'productCommentSummary']['commentCount']
42 | return totalpn // 10
43 | except:
44 | # print('failed')
45 | return -1
46 |
47 |
48 | def get_jd_rate_all(pid):
49 | maxpn = get_jd_rate_totalpagenum(pid)
50 | if maxpn == -1:
51 | # print('null')
52 | return ''
53 | pp = Pool(100)
54 | result = pp.map(
55 | lambda x: get_jd_rate(x[0], x[1]), list(zip([pid] * (maxpn + 1), range(maxpn + 1))))
56 | pp.close()
57 | pp.join()
58 | result = '\n'.join(re.findall(r'content":"(.*?)"', str(result)))
59 | result = re.sub('<.*?>', '', result)
60 | return result
61 |
62 |
63 | def get_list_ids(url):
64 | r = requests.get(url, headers={'Host': 'list.jd.com',
65 | 'Referer': 'http://channel.jd.com/jewellery.html'})
66 | try:
67 | scode = r.content.decode('utf-8')
68 | except:
69 | scode = r.content.decode('gbk')
70 | xpath = fromstring(scode).xpath
71 | ids = xpath('//a/@wareid|//i/@name|//a/@data-tag')
72 | nextpage = xpath('//a[@class="pn-next"]/@href|//a[@class="next"]/@href')
73 | nextpage = nextpage[0] if nextpage else False
74 | stopmsg = '已有0人评价' in scode or '0个评论' in scode
75 | return (ids, nextpage, stopmsg)
76 |
77 |
78 | def get_list(url):
79 | r = requests.get(url, headers={'Host': 'list.jd.com',
80 | 'Referer': 'http://channel.jd.com/jewellery.html'})
81 | try:
82 | scode = r.content.decode('utf-8')
83 | except:
84 | scode = r.content.decode('gbk')
85 | xpath = fromstring(scode).xpath
86 | title = xpath('/html/head/title/text()')[0]
87 | title = re.sub('\s.*', '', title)
88 | result = []
89 | while 1:
90 | ids, nextpage, stopmsg = get_list_ids(url)
91 | print('get %s' % url)
92 | result += ids
93 | if stopmsg:
94 | print('已经出现评价数量为0的商品,程序终止...')
95 | break
96 | if not nextpage:
97 | print('已达最大页码数,程序终止...')
98 | break
99 |
100 | url = nextpage if nextpage.startswith(
101 | 'http') else 'http://list.jd.com' + nextpage
102 | with open('./files/%s.txt' % title, 'w', encoding='utf-8') as f:
103 | f.write('\n'.join(result))
104 | print('结果已存入%s.txt' % title)
105 | print(result)
106 | return result
107 | import os
108 | if not os.path.exists("files"):
109 | os.makedirs('files')
110 |
111 |
112 | def main(url):
113 | pid = re.findall('jd\.com/(\d+)\.htm', url)
114 | if pid:
115 | print(pid[0])
116 | with open('./files/%s.txt' % pid[0], 'w', encoding='utf-8') as f:
117 | f.write(get_jd_rate_all(pid[0]))
118 | print('%s已完成,结果已存入%s.txt' % (pid[0], pid[0]))
119 |
120 | else:
121 | print('start the mission for product-list pages...')
122 | get_list(url)
123 |
124 |
125 | # print(main('http://list.jd.com/list.html?cat=6144,6167,6173'))
126 | while 1:
127 | print('\n' + '=' * 80 + '\n')
128 | try:
129 | command = input(
130 | '为了避免拿来主义,本程序功能仅限以下内容:\n1. 输入单个商品页地址或商品ID========>导出评论(pid.ini)\n2. 输入商品列表页地址(比如某类目,不是搜索结果页,事先最好按评论数排序)========>该类目下有评论的ID(类目标题.txt)\n3. 输入文件名(类目标题.txt)========>得到该类目下所有商品评论(类目.ini)\n4. 输入exit或quit退出程序\n注:所有非程序文件读写都在files目录下\n以上模式自动识别,请输入指令:\n')
131 | if command == 'exit' or command == 'quit':
132 | print('程序结束...')
133 | break
134 | if command.isalnum():
135 | print(command)
136 | with open('./files/%s.txt' % command, 'w', encoding='utf-8') as f:
137 | f.write(get_jd_rate_all(command))
138 | print('%s已完成,结果已存入%s.txt' % (command, command))
139 | continue
140 | if '.txt' in command:
141 | with open('./files/' + command) as ff:
142 | ids = ff.read().split()
143 | fname = command.replace('.txt', '.ini')
144 | print(ids)
145 | zongshu = len(ids)
146 | jishu = 0
147 | with open('./files/' + fname, 'w', encoding='utf-8') as f:
148 | for i in ids:
149 | f.write(get_jd_rate_all(i) + '\n')
150 | jishu += 1
151 | print('%s已完成-%s/%s' % (i, jishu, zongshu))
152 | print('所有结果已存入%s' % fname)
153 | continue
154 |
155 | main(command)
156 | except Exception as e:
157 | print(e)
158 | print('错误..')
159 |
--------------------------------------------------------------------------------
/抓取电商类网站全商品信息代码存档/亚马逊1根据列表页抓取ID.py:
--------------------------------------------------------------------------------
1 | # coding:utf-8
2 | try:
3 | from gevent import monkey
4 | monkey.patch_all()
5 | from gevent.pool import Pool
6 | except:
7 | from multiprocessing.dummy import Pool
8 | from lxml.html import fromstring
9 | import requests
10 | # 有关根据ID抓取详情,用的scrapy,就懒得放上来了,ID详情页URL规则是'http://www.amazon.cn/sdsss/dp/{}'.format(pid.strip())
11 | starturls = ['http://www.amazon.cn/s/ref=sd_allcat_digita_l3_siphone?ie=UTF8&page=1&rh=n%3A665002051%2Cp_89%3AApple%2Cn%3A664978051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_ssamsung?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3ASAMSUNG%20%E4%B8%89%E6%98%9F', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_snokia?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3ANOKIA%20%E8%AF%BA%E5%9F%BA%E4%BA%9A', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_shuawei?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3AHUAWEI%20%E5%8D%8E%E4%B8%BA', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_sxiaomi?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3A%E5%B0%8F%E7%B1%B3%2Cn%3A664978051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_sassociation?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3ALenovo%20%E8%81%94%E6%83%B3', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_ssony?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3ASony%20%E7%B4%A2%E5%B0%BC', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_sznet?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3AZTE%20%E4%B8%AD%E5%85%B4%2Cn%3A664978051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_shtc?ie=UTF8&page=1&rh=n%3A665002051%2Cp_4%3AHTC', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_smeizu?ie=UTF8&page=1&rh=n%3A665002051%2Cp_89%3A%E9%AD%85%E6%97%8F%2Cn%3A664978051%2Cn%3A!2016117051%2Cn%3A2016116051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_scoolpad?ie=UTF8&page=1&rh=n%3A665002051%2Cp_89%3ACoolpad%20%E9%85%B7%E6%B4%BE%2Cn%3A664978051%2Cn%3A!2016117051%2Cn%3A2016116051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_sall_phone?ie=UTF8&page=1&rh=n%3A665002051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b244630071?ie=UTF8&node=244630071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b244629071?ie=UTF8&node=244629071', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_sset_remote_ch?ie=UTF8&page=1&rh=n%3A244671071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b2127529051?ie=UTF8&node=2127529051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b665020051?ie=UTF8&node=665020051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b665194051?ie=UTF8&node=665194051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b665196051?ie=UTF8&node=665196051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b407627071?ie=UTF8&node=407627071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b2110347051?ie=UTF8&node=2110347051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b2110348051?ie=UTF8&node=2110348051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b117198071?ie=UTF8&node=117198071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b152323071?ie=UTF8&node=152323071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b755657051?ie=UTF8&node=755657051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b120678071?ie=UTF8&node=120678071', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_smonitor?ie=UTF8&page=1&rh=n%3A121949071', 'http://www.amazon.cn/b/ref=sd_allcat_camera_l3_b49404071?ie=UTF8&node=49404071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b755670051?ie=UTF8&node=755670051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b755668051?ie=UTF8&node=755668051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b755673051?ie=UTF8&node=755673051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b755675051?ie=UTF8&node=755675051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_scamera_batter?ie=UTF8&page=1&rh=n%3A755669051', 'http://www.amazon.cn/gp/feature.html/ref=sd_allcat_digita_l3_f164038?ie=UTF8&docId=164038', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b760236051?ie=UTF8&node=760236051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b760240051?ie=UTF8&node=760240051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b760239051?ie=UTF8&node=760239051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b1995000051?ie=UTF8&node=1995000051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b760237051?ie=UTF8&node=760237051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b128478071?ie=UTF8&node=128478071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b1995002051?ie=UTF8&node=1995002051', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b1994998051?ie=UTF8&node=1994998051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_srecorder?ie=UTF8&page=1&rh=n%3A124912071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b1404899071?ie=UTF8&node=1404899071', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_ssmart_wear_devices?ie=UTF8&page=1&rh=n%3A1323500071', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_ssmart_watch?ie=UTF8&page=1&rh=n%3A1323501071', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_ssmart_furniture?ie=UTF8&page=1&rh=n%3A1323978071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b1323980071?ie=UTF8&node=1323980071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b1323981071?ie=UTF8&node=1323981071', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_spiano_keyboar?ie=UTF8&page=1&rh=n%3A2018658051', 'http://www.amazon.cn/s/ref=sd_allcat_digita_l3_sguitar_bass?ie=UTF8&page=1&rh=n%3A148315071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b100140071?ie=UTF8&node=100140071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b275499071?ie=UTF8&node=275499071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b275138071?ie=UTF8&node=275138071', 'http://www.amazon.cn/b/ref=sd_allcat_digita_l3_b276779071?ie=UTF8&node=276779071', 'http://www.amazon.cn/%E7%AC%94%E8%AE%B0%E6%9C%AC%E7%94%B5%E8%84%91/b/ref=sd_allcat_office_l3_b106200071?ie=UTF8&node=106200071', 'http://www.amazon.cn/%E8%B6%85%E6%9E%81%E6%9C%AC/b/ref=sd_allcat_office_l3_b148770071?ie=UTF8&node=148770071', 'http://www.amazon.cn/%E5%8F%B0%E5%BC%8F%E7%94%B5%E8%84%91%E5%8F%8A%E4%B8%80%E4%BD%93%E6%9C%BA/b/ref=sd_allcat_office_l3_b2054678051?ie=UTF8&node=2054678051', 'http://www.amazon.cn/%E4%B8%80%E4%BD%93%E6%9C%BA%E7%94%B5%E8%84%91/b/ref=sd_allcat_office_l3_b106201071?ie=UTF8&node=106201071', 'http://www.amazon.cn/%E5%B9%B3%E6%9D%BF%E7%94%B5%E8%84%91/b/ref=sd_allcat_office_l3_b51878071?ie=UTF8&node=51878071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2126204051?ie=UTF8&node=2126204051', 'http://www.amazon.cn/s/ref=sd_allcat_pc_l3_sapple?ie=UTF8&page=1&rh=n%3A42689071%2Cp_89%3AApple%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/b/ref=sd_allcat_pc_l3_b1416845071?ie=UTF8&node=1416845071', 'http://www.amazon.cn/gp/feature.html/ref=sd_allcat_jewelr_l3_1495988?ie=UTF8&docId=1495988', 'http://www.amazon.cn/gp/feature.html/ref=sd_allcat_pc__l3_f247988?ie=UTF8&docId=247988', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b158151071?ie=UTF8&node=158151071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888585051?ie=UTF8&node=888585051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_sheadphone_and?ie=UTF8&page=1&rh=n%3A888537051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_sspeaker?ie=UTF8&page=1&rh=n%3A888534051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_stablet_cover?ie=UTF8&page=1&rh=n%3A106578071', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_scamera_headse?ie=UTF8&page=1&rh=n%3A106223071', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_shard_disc?ie=UTF8&page=1&rh=n%3A888650051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_sportable_disc?ie=UTF8&page=1&rh=n%3A888502051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_su_disk?ie=UTF8&page=1&rh=n%3A888501051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_smemory_card?ie=UTF8&page=1&rh=n%3A755664051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888494051?ie=UTF8&node=888494051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b81819071?ie=UTF8&node=81819071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888488051?ie=UTF8&node=888488051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888490051?ie=UTF8&node=888490051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888491051?ie=UTF8&node=888491051', 'http://www.amazon.cn/%E6%98%BE%E7%A4%BA%E5%99%A8/b/ref=sd_allcat_office_l3_b888468051?ie=UTF8&node=888468051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888489051?ie=UTF8&node=888489051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888493051?ie=UTF8&node=888493051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888496051?ie=UTF8&node=888496051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888498051?ie=UTF8&node=888498051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2028187051?ie=UTF8&node=2028187051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888497051?ie=UTF8&node=888497051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b1978463051?ie=UTF8&node=1978463051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b106234071?ie=UTF8&node=106234071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b106231071?ie=UTF8&node=106231071', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_swl_camera?ie=UTF8&page=1&rh=n%3A333872071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2028202051?ie=UTF8&node=2028202051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2028342051?ie=UTF8&node=2028342051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b114799071?ie=UTF8&node=114799071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142127051?ie=UTF8&node=2142127051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b114793071?ie=UTF8&node=114793071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2028204051?ie=UTF8&node=2028204051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b114798071?ie=UTF8&node=114798071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142117051?ie=UTF8&node=2142117051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142124051?ie=UTF8&node=2142124051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2028206051?ie=UTF8&node=2028206051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b103849071?ie=UTF8&node=103849071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142212051?ie=UTF8&node=2142212051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142196051?ie=UTF8&node=2142196051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142135051?ie=UTF8&node=2142135051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142152051?ie=UTF8&node=2142152051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b103885071?ie=UTF8&node=103885071', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142236051?ie=UTF8&node=2142236051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b888471051?ie=UTF8&node=888471051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142255051?ie=UTF8&node=2142255051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142186051?ie=UTF8&node=2142186051', 'http://www.amazon.cn/b/ref=sd_allcat_office_l3_b2142166051?ie=UTF8&node=2142166051', 'http://www.amazon.cn/s/ref=sd_allcat_office_l3_scalculator?ie=UTF8&page=1&rh=n%3A2147366051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b874269051?ie=UTF8&node=874269051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b874267051?ie=UTF8&node=874267051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b874373051?ie=UTF8&node=874373051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b874268051?ie=UTF8&node=874268051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b874274051?ie=UTF8&node=874274051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b874272051?ie=UTF8&node=874272051', 'http://www.amazon.cn/s/ref=sd_allcat_applia_l3_swashing_machi?ie=UTF8&page=1&rh=n%3A2121147051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b150624071?ie=UTF8&node=150624071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b2132895051?ie=UTF8&node=2132895051', 'http://www.amazon.cn/s/ref=sd_allcat_applia_l3_shood_and_gas?ie=UTF8&page=1&rh=n%3A80207071%2Ck%3A%E7%83%9F%E7%81%B6%E5%A5%97%E9%A4%90', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b2132892051?ie=UTF8&node=2132892051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b2132893051?ie=UTF8&node=2132893051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b81948071?ie=UTF8&node=81948071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b81949071?ie=UTF8&node=81949071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b81951071?ie=UTF8&node=81951071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b2121145051?ie=UTF8&node=2121145051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b2132894051?ie=UTF8&node=2132894051', 'http://www.amazon.cn/s/ref=sd_allcat_applia_l3_sdishwasher?ie=UTF8&page=1&rh=n%3A2121151051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814683051?ie=UTF8&node=814683051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814685051?ie=UTF8&node=814685051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814688051?ie=UTF8&node=814688051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814717051?ie=UTF8&node=814717051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814684051?ie=UTF8&node=814684051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814252051?ie=UTF8&node=814252051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814718051?ie=UTF8&node=814718051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b98516071?ie=UTF8&node=98516071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b98518071?ie=UTF8&node=98518071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814716051?ie=UTF8&node=814716051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b98519071?ie=UTF8&node=98519071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814696051?ie=UTF8&node=814696051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814713051?ie=UTF8&node=814713051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814719051?ie=UTF8&node=814719051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b155895071?ie=UTF8&node=155895071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814700051?ie=UTF8&node=814700051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814275051?ie=UTF8&node=814275051', 'http://www.amazon.cn/%E7%94%B5%E9%A3%8E%E6%89%87/b/ref=sd_allcat_applia_l3_b814270051?ie=UTF8&node=814270051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814269051?ie=UTF8&node=814269051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814350051?ie=UTF8&node=814350051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814282051?ie=UTF8&node=814282051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814267051?ie=UTF8&node=814267051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b2112270051?ie=UTF8&node=2112270051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814272051?ie=UTF8&node=814272051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814274051?ie=UTF8&node=814274051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814259051?ie=UTF8&node=814259051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814257051?ie=UTF8&node=814257051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814264051?ie=UTF8&node=814264051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814266051?ie=UTF8&node=814266051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814262051?ie=UTF8&node=814262051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b148287071?ie=UTF8&node=148287071', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814331051?ie=UTF8&node=814331051', 'http://www.amazon.cn/b/ref=sd_allcat_applia_l3_b814258051?ie=UTF8&node=814258051', 'http://www.amazon.cn/s/ref=sd_allcat_applia_l3_spretty?ie=UTF8&page=1&rh=n%3A814265051%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A814228051%2Cn%3A814224051', 'http://www.amazon.cn/s/ref=sd_allcat_applia_l3_smessage_machine?ie=UTF8&page=1&rh=n%3A814329051%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A814228051%2Cn%3A814224051', 'http://www.amazon.cn/s/ref=sd_allcat_applia_l3_sfoot_massage?ie=UTF8&page=1&rh=n%3A814261051%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A814228051%2Cn%3A814224051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813109051?ie=UTF8&node=813109051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813212051?ie=UTF8&node=813212051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813116051?ie=UTF8&node=813116051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813110051?ie=UTF8&node=813110051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813112051?ie=UTF8&node=813112051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b157568071?ie=UTF8&node=157568071', 'http://www.amazon.cn/%E6%9D%AF%E5%AD%90/b/ref=sd_allcat_kitche_l3_b813272051?ie=UTF8&node=813272051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813830051?ie=UTF8&node=813830051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813269051?ie=UTF8&node=813269051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813270051?ie=UTF8&node=813270051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813111051?ie=UTF8&node=813111051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813114051?ie=UTF8&node=813114051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b813271051?ie=UTF8&node=813271051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831963051?ie=UTF8&node=831963051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831965051?ie=UTF8&node=831965051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b832607051?ie=UTF8&node=832607051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831967051?ie=UTF8&node=831967051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92388071?ie=UTF8&node=92388071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831968051?ie=UTF8&node=831968051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831969051?ie=UTF8&node=831969051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92389071?ie=UTF8&node=92389071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831966051?ie=UTF8&node=831966051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92454071?ie=UTF8&node=92454071', 'http://www.amazon.cn/b/ref=sd_allcat_home_l3_b832627051?ie=UTF8&node=832627051', 'http://www.amazon.cn/b/ref=sd_allcat_home_l3_b832626051?ie=UTF8&node=832626051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b832066051?ie=UTF8&node=832066051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92472071?ie=UTF8&node=92472071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92420071?ie=UTF8&node=92420071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831983051?ie=UTF8&node=831983051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92401071?ie=UTF8&node=92401071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831973051?ie=UTF8&node=831973051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b2114395051?ie=UTF8&node=2114395051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_sbed?ie=UTF8&page=1&rh=n%3A1152518071%2Cn%3A831780051%2Cn%3A831785051%2Cn%3A92412071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831982051?ie=UTF8&node=831982051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_smattress?ie=UTF8&page=1&rh=n%3A831968051%2Cn%3A92407071%2Cn%3A831785051%2Cn%3A831780051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92422071?ie=UTF8&node=92422071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831975051?ie=UTF8&node=831975051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92415071?ie=UTF8&node=92415071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831974051?ie=UTF8&node=831974051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_sbed?ie=UTF8&page=1&rh=n%3A92411071%2Cp_36%3A40000-99999900%2Cn%3A92407071%2Cn%3A831785051%2Cn%3A831780051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_soutdoor_furniture?ie=UTF8&page=1&rh=n%3A219255071%2Cn%3A831785051%2Cn%3A831780051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_schildren_furniture?ie=UTF8&page=1&rh=n%3A2005483051%2Cn%3A831785051%2Cn%3A831780051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831786051?ie=UTF8&node=831786051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92431071?ie=UTF8&node=92431071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831791051?ie=UTF8&node=831791051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92390071?ie=UTF8&node=92390071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b831787051?ie=UTF8&node=831787051', 'http://www.amazon.cn/b/ref=sd_allcat_home_l3_b831795051?ie=UTF8&node=831795051', 'http://www.amazon.cn/b/ref=sd_allcat_home_l3_b92452071?ie=UTF8&node=92452071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92466071?ie=UTF8&node=92466071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b832065051?ie=UTF8&node=832065051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b832056051?ie=UTF8&node=832056051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b79952071?ie=UTF8&node=79952071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b150415071?ie=UTF8&node=150415071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b92487071?ie=UTF8&node=92487071', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_smasks?ie=UTF8&page=1&rh=n%3A1952920051%2Ck%3A%E5%8F%A3%E7%BD%A9', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952922051?ie=UTF8&node=1952922051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952924051?ie=UTF8&node=1952924051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952925051?ie=UTF8&node=1952925051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952935051?ie=UTF8&node=1952935051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952923051?ie=UTF8&node=1952923051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_ssprinkler?ie=UTF8&page=1&rh=n%3A1952994051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_sfaucet?ie=UTF8&page=1&rh=n%3A1952920051%2Ck%3A%E9%BE%99%E5%A4%B4', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952986051?ie=UTF8&node=1952986051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952996051?ie=UTF8&node=1952996051', 'http://www.amazon.cn/s/ref=sd_allcat_kitche_l3_stoilet_cleani?ie=UTF8&page=1&rh=n%3A1953127051%2Cn%3A1952996051%2Cn%3A1952929051%2Cn%3A!1952921051%2Cn%3A1952920051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b2152650051?ie=UTF8&node=2152650051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952926051?ie=UTF8&node=1952926051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b1952932051?ie=UTF8&node=1952932051', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b149410071?ie=UTF8&node=149410071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b149348071?ie=UTF8&node=149348071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b149540071?ie=UTF8&node=149540071', 'http://www.amazon.cn/b/ref=sd_allcat_kitche_l3_b124844071?ie=UTF8&node=124844071', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_smilk?ie=UTF8&page=1&rh=n%3A43247071%2Cp_n_feature_four_browse-bin%3A2140440051', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_scoffee?ie=UTF8&page=1&rh=n%3A2141095051%2Cp_n_feature_four_browse-bin%3A2140440051', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_scakes_biscuit?ie=UTF8&page=1&rh=n%3A2134644051%2Cp_n_feature_four_browse-bin%3A2140440051', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_ssnacks?ie=UTF8&page=1&rh=n%3A2134651051%2Cp_n_feature_four_browse-bin%3A2140440051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134679051?ie=UTF8&node=2134679051', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_sconvenience_f?ie=UTF8&page=1&rh=n%3A2134691051%2Cp_n_feature_four_browse-bin%3A2140440051', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_solive_oil?ie=UTF8&page=1&rh=n%3A2141134051%2Cp_n_feature_four_browse-bin%3A2140440051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b43235071?ie=UTF8&node=43235071', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b43237071?ie=UTF8&node=43237071', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b43238071?ie=UTF8&node=43238071', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_schampaign?ie=UTF8&page=1&rh=n%3A43243071', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b43241071?ie=UTF8&node=43241071', 'http://www.amazon.cn/s/ref=sd_allcat_food_l3_swestern_liquo?ie=UTF8&page=1&rh=n%3An%3A2127215051%2Cn%3A!2127216051%2Cn%3A43234071%2Cn%3A43240071', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2141094051?ie=UTF8&node=2141094051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2140457051?ie=UTF8&node=2140457051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134640051?ie=UTF8&node=2134640051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134642051?ie=UTF8&node=2134642051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134638051?ie=UTF8&node=2134638051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134636051?ie=UTF8&node=2134636051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134639051?ie=UTF8&node=2134639051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134641051?ie=UTF8&node=2134641051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134663051?ie=UTF8&node=2134663051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134660051?ie=UTF8&node=2134660051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134644051?ie=UTF8&node=2134644051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134652051?ie=UTF8&node=2134652051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2141111051?ie=UTF8&node=2141111051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134657051?ie=UTF8&node=2134657051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134669051?ie=UTF8&node=2134669051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134691051?ie=UTF8&node=2134691051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134701051?ie=UTF8&node=2134701051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134673051?ie=UTF8&node=2134673051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b2134680051?ie=UTF8&node=2134680051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b836683051?ie=UTF8&node=836683051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b836690051?ie=UTF8&node=836690051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b836687051?ie=UTF8&node=836687051', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b111006071?ie=UTF8&node=111006071', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b111005071?ie=UTF8&node=111005071', 'http://www.amazon.cn/b/ref=sd_allcat_food_l3_b111018071?ie=UTF8&node=111018071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747001051?ie=UTF8&node=747001051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747003051?ie=UTF8&node=747003051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747005051?ie=UTF8&node=747005051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b422481071?ie=UTF8&node=422481071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747006051?ie=UTF8&node=747006051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747007051?ie=UTF8&node=747007051', 'http://www.amazon.cn/b/ref=sd_allcat_beauty_l3_b747932051?ie=UTF8&node=747932051', 'http://www.amazon.cn/b/ref=sd_allcat_beauty_l3_b422483071?ie=UTF8&node=422483071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747011051?ie=UTF8&node=747011051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747010051?ie=UTF8&node=747010051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747012051?ie=UTF8&node=747012051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853728051?ie=UTF8&node=853728051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747066051?ie=UTF8&node=747066051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b747014051?ie=UTF8&node=747014051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853732051?ie=UTF8&node=853732051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853734051?ie=UTF8&node=853734051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b427964071?ie=UTF8&node=427964071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853736051?ie=UTF8&node=853736051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853735051?ie=UTF8&node=853735051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853739051?ie=UTF8&node=853739051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853209051?ie=UTF8&node=853209051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b1175201071?ie=UTF8&node=1175201071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853750051?ie=UTF8&node=853750051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853749051?ie=UTF8&node=853749051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853211051?ie=UTF8&node=853211051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853714051?ie=UTF8&node=853714051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853751051?ie=UTF8&node=853751051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b427925071?ie=UTF8&node=427925071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853779051?ie=UTF8&node=853779051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853214051?ie=UTF8&node=853214051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b427929071?ie=UTF8&node=427929071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b746996051?ie=UTF8&node=746996051',
12 | 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b746995051?ie=UTF8&node=746995051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b746996051?ie=UTF8&node=746996051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b1175198071?ie=UTF8&node=1175198071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b746997051?ie=UTF8&node=746997051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2133897051?ie=UTF8&node=2133897051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2133898051?ie=UTF8&node=2133898051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2133899051?ie=UTF8&node=2133899051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b111069071?ie=UTF8&node=111069071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2118945051?ie=UTF8&node=2118945051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b111061071?ie=UTF8&node=111061071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2150840051?ie=UTF8&node=2150840051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853213051?ie=UTF8&node=853213051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853796051?ie=UTF8&node=853796051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853216051?ie=UTF8&node=853216051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b853797051?ie=UTF8&node=853797051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2025136051?ie=UTF8&node=2025136051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b110980071?ie=UTF8&node=110980071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2007739051?ie=UTF8&node=2007739051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b836323051?ie=UTF8&node=836323051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b836745051?ie=UTF8&node=836745051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b836322051?ie=UTF8&node=836322051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b110973071?ie=UTF8&node=110973071', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b836719051?ie=UTF8&node=836719051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2133889051?ie=UTF8&node=2133889051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b836723051?ie=UTF8&node=836723051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b2045919051?ie=UTF8&node=2045919051', 'http://www.amazon.cn/b/ref=sd_allcat_bodyca_l3_b80706071?ie=UTF8&node=80706071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sinfant_toys?ie=UTF8&page=1&rh=n%3A1982054051%2Cp_n_age_range%3A2046142051%7C2046143051%7C2046144051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b1982065051?ie=UTF8&node=1982065051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b1982062051?ie=UTF8&node=1982062051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b2017770051?ie=UTF8&node=2017770051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b1982058051?ie=UTF8&node=1982058051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b1982059051?ie=UTF8&node=1982059051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b281527071?ie=UTF8&node=281527071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b1982064051?ie=UTF8&node=1982064051', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b1982061051?ie=UTF8&node=1982061051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_stoy0_12_months?ie=UTF8&page=1&rh=n%3A647070051%2Cp_n_age_range%3A2046142051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_stoy1_3_years?ie=UTF8&page=1&rh=n%3A647070051%2Cp_n_age_range%3A2046143051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_stoy4_6_years_ol?ie=UTF8&page=1&rh=n%3A647070051%2Cp_n_age_range%3A2046144051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_stoy7_12_years?ie=UTF8&page=1&rh=n%3A647070051%2Cp_n_age_range%3A2046145051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_stoy_more_than_1?ie=UTF8&page=1&rh=n%3A647070051%2Cp_n_age_range%3A2046146051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sdiaper_nbs?ie=UTF8&page=1&rh=n%3A79140071%2Cp_n_feature_three_browse-bin%3A2031560051%7C2031561051%2Cn%3A79139071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sdiaper_m?ie=UTF8&page=1&rh=n%3A79140071%2Cp_n_feature_three_browse-bin%3A2031562051%2Cn%3A79139071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sdiaper_l?ie=UTF8&page=1&rh=n%3A42692071%2Cn%3A!42693071%2Cn%3A79139071%2Cn%3A79140071%2Cp_n_feature_three_browse-bin%3A2031563051', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sdiaper_xl?ie=UTF8&page=1&rh=n%3A79140071%2Cp_n_feature_three_browse-bin%3A2031564051%2Cn%3A79139071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sdiaper_xxl?ie=UTF8&page=1&rh=n%3A79140071%2Cp_n_feature_three_browse-bin%3A51697071%2Cn%3A79139071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sgrow_pants?ie=UTF8&page=1&rh=n%3A273113071%2Cn%3A79140071%2Cn%3A79139071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sdiaper_pants?ie=UTF8&page=1&rh=n%3A79143071%2Cn%3A79139071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sstage1?ie=UTF8&page=1&rh=n%3A79496071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sstage_2?ie=UTF8&page=1&rh=n%3A79497071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sstage_3?ie=UTF8&page=1&rh=n%3A79498071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sstage_4?ie=UTF8&page=1&rh=n%3A79499071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smotherhood_milk?ie=UTF8&page=1&rh=n%3A79194071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sspecial_formula?ie=UTF8&page=1&rh=n%3A273192071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b80392071?ie=UTF8&node=80392071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sjuicy_smash?ie=UTF8&page=1&rh=n%3A80391071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b79197071?ie=UTF8&node=79197071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b79204071?ie=UTF8&node=79204071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_digestion?ie=UTF8&page=1&rh=n%3A79199071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b79205071?ie=UTF8&node=79205071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_meat_food?ie=UTF8&page=1&rh=n%3A80395071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smilk_bottle?ie=UTF8&page=1&rh=n%3A273337071%2Cn%3A79206071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_snaizui?ie=UTF8&page=1&rh=n%3A79272071%2Cn%3A79206071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_snaizui?ie=UTF8&page=1&rh=n%3A79225071%2Cn%3A79206071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b79147071?ie=UTF8&node=79147071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b79156071?ie=UTF8&node=79156071', 'http://www.amazon.cn/b/ref=sd_allcat_baby_l3_b79187071?ie=UTF8&node=79187071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smom_xinai?ie=UTF8&page=1&rh=n%3A42692071%2Cn%3A!42693071%2Cn%3A79206071%2Cn%3A79216071%2Cn%3A79218071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smom_bag?ie=UTF8&page=1&rh=n%3A42692071%2Cn%3A!42693071%2Cn%3A79206071%2Cn%3A79216071%2Cn%3A291440071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sstrollers?ie=UTF8&page=1&rh=n%3A2039922051%2Ck%3A%E6%8E%A8%E8%BD%A6%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbicycle?ie=UTF8&page=1&rh=n%3A49923071%2Cn%3A2039922051%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_scar_child_seat?ie=UTF8&page=1&rh=n%3A255410071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_spedicab?ie=UTF8&page=1&rh=n%3A1982499051%2Cn%3A2039922051%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sstorage_battery?ie=UTF8&page=1&rh=n%3A1982496051%2Cn%3A2039922051%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_swalker?ie=UTF8&page=1&rh=n%3A79271071%2Cn%3A2039922051%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_scots?ie=UTF8&page=1&rh=n%3A79300071%2Cn%3A79292071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_food_table?ie=UTF8&page=1&rh=n%3A79317071%2Cn%3A79292071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_sleep_bag?ie=UTF8&page=1&rh=n%3A79249071%2Cn%3A79242071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_hug_quilt?ie=UTF8&page=1&rh=n%3A273137071%2Cn%3A79242071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_cool_sleep?ie=UTF8&page=1&rh=n%3A273134071%2Cn%3A79242071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_mosquito?ie=UTF8&page=1&rh=n%3A273133071%2Cn%3A79242071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_pillow?ie=UTF8&page=1&rh=n%3A79246071%2Cn%3A79242071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbaby_towel_quil?ie=UTF8&page=1&rh=n%3A79250071%2Cn%3A79242071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sunderwear?ie=UTF8&page=1&rh=n%3A1335054071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_shatscarf?ie=UTF8&page=1&rh=n%3A1335053071%2Cn%3A1335057071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_scloth_package?ie=UTF8&page=1&rh=n%3A1335055071%2Cn%3A1335055071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbag_case?ie=UTF8&page=1&rh=n%3A1335056071%2Cn%3A1335056071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smaternity?ie=UTF8&page=1&rh=i%3Ababy%2Cn%3A42692071%2Cn%3A!79334071%2Cn%3A!79335071%2Cn%3A1342735071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbodyshape_after?ie=UTF8&page=1&rh=i%3Ababy%2Cn%3A42692071%2Cn%3A!79334071%2Cn%3A!79335071%2Cn%3A1341462071%2Cn%3A1341464071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smothers_underwe?ie=UTF8&page=1&rh=%3Di%3Ababy%2Cn%3A42692071%2Cn%3A!79334071%2Cn%3A!79335071%2Cn%3A1342739071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_sbeidai?ie=UTF8&page=1&rh=n%3A79263071%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A79259071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_smom_bag?ie=UTF8&page=1&rh=n%3A79266071%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A79259071%2Cn%3A!42693071%2Cn%3A42692071', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_swashing_skincare?ie=UTF8&page=1&rh=i%3Ababy%2Cn%3A42692071%2Cn%3A!79334071%2Cn%3A!79335071%2Cn%3A1341462071%2Cn%3A1341471071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/s/ref=sd_allcat_baby_l3_santi_ratiation_cloth?ie=UTF8&page=1&rh=i%3Ababy%2Cn%3A42692071%2Cn%3A!79334071%2Cn%3A!79335071%2Cn%3A1341462071%2Cn%3A1341466071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b399831071?ie=UTF8&node=399831071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b399827071?ie=UTF8&node=399827071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b399836071?ie=UTF8&node=399836071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b399832071?ie=UTF8&node=399832071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b399835071?ie=UTF8&node=399835071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b399838071?ie=UTF8&node=399838071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b836886051?ie=UTF8&node=836886051', 'http://www.amazon.cn/s/ref=sd_allcat_pc_l3_sapple?ie=UTF8&page=1&rh=n%3A49331071%2Cn%3A49319071%2Cn%3A!836313051%2Cn%3A836312051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49342071?ie=UTF8&node=49342071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49375071?ie=UTF8&node=49375071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b813114051?ie=UTF8&node=813114051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49404071?ie=UTF8&node=49404071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49382071?ie=UTF8&node=49382071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49320071?ie=UTF8&node=49320071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b220559071?ie=UTF8&node=220559071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b220563071?ie=UTF8&node=220563071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b220565071?ie=UTF8&node=220565071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b220562071?ie=UTF8&node=220562071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b220560071?ie=UTF8&node=220560071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b220564071?ie=UTF8&node=220564071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49823071?ie=UTF8&node=49823071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49825071?ie=UTF8&node=49825071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49820071?ie=UTF8&node=49820071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49874071?ie=UTF8&node=49874071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b2153972051?ie=UTF8&node=2153972051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49921071?ie=UTF8&node=49921071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49624071?ie=UTF8&node=49624071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b1370852071?ie=UTF8&node=1370852071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49601071?ie=UTF8&node=49601071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49620071?ie=UTF8&node=49620071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49603071?ie=UTF8&node=49603071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b49577071?ie=UTF8&node=49577071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l2_b229730071?ie=UTF8&node=229730071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l2_b229731071?ie=UTF8&node=229731071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l2_b229729071?ie=UTF8&node=229729071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l2_b229734071?ie=UTF8&node=229734071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l2_b1317870071?ie=UTF8&node=1317870071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b1317865071?ie=UTF8&node=1317865071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l2_b100428071?ie=UTF8&node=100428071', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b2128055051?ie=UTF8&node=2128055051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b2133453051?ie=UTF8&node=2133453051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b2134348051?ie=UTF8&node=2134348051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b2128053051?ie=UTF8&node=2128053051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b2128054051?ie=UTF8&node=2128054051', 'http://www.amazon.cn/s/ref=sd_allcat_sports_l3_sfootball?ie=UTF8&page=1&rh=n%3A836312051%2Cn%3A!836313051%2Cn%3A836332051', 'http://www.amazon.cn/s/ref=sd_allcat_sports_l3_sswimming?ie=UTF8&page=1&rh=n%3A836312051%2Cn%3A!836313051%2Cn%3A836338051', 'http://www.amazon.cn/s/ref=sd_allcat_sports_l3_sbadminton?ie=UTF8&page=1&rh=n%3A836312051%2Cn%3A!836313051%2Cn%3A836330051', 'http://www.amazon.cn/s/ref=sd_allcat_sports_l3_sbasketball?ie=UTF8&page=1&rh=n%3A836312051%2Cn%3A!836313051%2Cn%3A836331051', 'http://www.amazon.cn/s/ref=sd_allcat_sports_l3_stable_tennis?ie=UTF8&page=1&rh=n%3A836312051%2Cn%3A!836313051%2Cn%3A836334051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b836333051?ie=UTF8&node=836333051', 'http://www.amazon.cn/b/ref=sd_allcat_sports_l3_b836335051?ie=UTF8&node=836335051', 'http://www.amazon.cn/%E5%A5%B3%E8%A3%85/b/ref=sd_allcat_bags_l3_b2152154051?ie=UTF8&node=2152154051', 'http://www.amazon.cn/%E7%94%B7%E8%A3%85/b/ref=sd_allcat_bags_l3_b2152155051?ie=UTF8&node=2152155051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b79963071?ie=UTF8&node=79963071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b341388071?ie=UTF8&node=341388071', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_swomen_dress?ie=UTF8&page=1&rh=n%3A2154399051%2Cn%3A91622071%2Cn%3A2152154051%2Cn%3A!2016157051%2Cn%3A2016156051', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_swomen_coat?ie=UTF8&page=1&rh=n%3A2154373051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b97238071?ie=UTF8&node=97238071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b80421071?ie=UTF8&node=80421071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2154233051?ie=UTF8&node=2154233051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b51302071?ie=UTF8&node=51302071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b163469071?ie=UTF8&node=163469071', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_scasual_pants?ie=UTF8&page=1&rh=n%3A51303071', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_sshirt_shop?ie=UTF8&page=1&rh=n%3A51301071&sort=popularity-rank', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_sdenim_pant?ie=UTF8&page=1&rh=n%3A51305071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b51300071?ie=UTF8&node=51300071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b79961071?ie=UTF8&node=79961071', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_sskirt_half?ie=UTF8&page=1&rh=n%3A2154404051', 'http://www.amazon.cn/gp/gallery/ref=sd_allcat_bags_l3_dapeijie', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2112003051?ie=UTF8&node=2112003051', 'http://www.amazon.cn/%E7%94%B7%E9%9E%8B/b/ref=sd_allcat_bags_l3_b2112046051?ie=UTF8&node=2112046051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_334956071?ie=UTF8&node=334956071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b167097071?ie=UTF8&node=167097071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2118816051?ie=UTF8&node=2118816051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2134348051?ie=UTF8&node=2134348051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2127225051?ie=UTF8&node=2127225051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2128059051?ie=UTF8&node=2128059051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b220558071?ie=UTF8&node=220558071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b162116071?ie=UTF8&node=162116071', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_sflat_2?ie=UTF8&page=1&rh=n%3A2112004051%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A2112003051%2Cn%3A!2029190051%2Cn%3A2029189051&sort=popularity-rank', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b162115071?ie=UTF8&node=162115071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2112048051?ie=UTF8&node=2112048051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2112047051?ie=UTF8&node=2112047051', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_cn_boots?ie=UTF8&page=1&rh=n%3A2029189051%2Cn%3A!2112205051%2Cn%3A!2118806051%2Cn%3A!2118815051%2Cn%3A2127226051%2Cp_6%3AA1AJ19PSB66TGU&sort=popularity-rank', 'http://www.amazon.cn/b/ref=sd_allcat_topnav_storetab_shoe?ie=UTF8&node=220588071', 'http://www.amazon.cn/s/ref=sd_allcat_sr_nr_p_6_2?ie=UTF8&page=1&rh=n%3A2029189051%2Cn%3A!2112205051%2Cn%3A!2118806051%2Cn%3A!2118815051%2Cn%3A220589071%2Cp_6%3AA1AJ19PSB66TGU', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2128057051?ie=UTF8&node=2128057051', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_sfashion_handbag?ie=UTF8&page=1&rh=n%3A100279071%2Cn%3A!100279071%2Cn%3A100279071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b100277071?ie=UTF8&node=100277071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b865374051?ie=UTF8&node=865374051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b865366051?ie=UTF8&node=865366051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b100275071?ie=UTF8&node=100275071', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_smale_ladys_purs?ie=UTF8&page=1&rh=n%3A865362051%2Cn%3A100296071%2Cn%3A865184051%2Cn%3A!2016157051%2Cn%3A2016156051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b100306071?ie=UTF8&node=100306071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b100428071?ie=UTF8&node=100428071', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b2113646051?ie=UTF8&node=2113646051', 'http://www.amazon.cn/b/ref=sd_allcat_bags_l3_b865361051?ie=UTF8&node=865361051', 'http://www.amazon.cn/s/ref=sd_allcat_bags_l3_stravel_bags?ie=UTF8&page=1&rh=n%3A2113647051&sort=popularity-rank', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_sman_watch?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_n_target_audience_browse-bin%3A2131959051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_swomen_watches?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_n_target_audience_browse-bin%3A2131960051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_smechanical_wa?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_n_feature_browse-bin%3A2131965051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_scouple_watche?ie=UTF8&page=1&rh=n%3A2040033051%2Cp_n_target_audience_browse-bin%3A2131961051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_schildrens_wat?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_n_target_audience_browse-bin%3A2131962051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_squartz_watch?ie=UTF8&page=1&rh=n%3A2040033051%2Cp_n_feature_browse-bin%3A2131964051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816492051?ie=UTF8&node=816492051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_scasio?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ACasio%20%E5%8D%A1%E8%A5%BF%E6%AC%A7', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_stissot?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ATissot%20%E5%A4%A9%E6%A2%AD', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_slongines?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ALongines%20%E6%B5%AA%E7%90%B4', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_somega?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3AOmega%20%E6%AC%A7%E7%B1%B3%E8%8C%84', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_sswatch?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ASwatch%20%E6%96%AF%E6%B2%83%E7%90%AA', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_sseiko?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ASeiko%20%E7%B2%BE%E5%B7%A5', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_shamilton?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3AHAMILTON%20%E6%B1%89%E7%B1%B3%E5%B0%94%E9%A1%BF', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_smido?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3AMIDO%20%E7%BE%8E%E5%BA%A6', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_stianwang?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ATianwang%20%E5%A4%A9%E7%8E%8B', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_sseagull?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3ASEA-GULL%20%E6%B5%B7%E9%B8%A5', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_srossini?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3AROSSINI%20%E7%BD%97%E8%A5%BF%E5%B0%BC', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_sebohr?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_4%3AEBOHR%20%E4%BE%9D%E6%B3%A2', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_ssongtuo?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_6%3AA1AJ19PSB66TGU%2Cp_89%3ASUUNTO%20%E9%A2%82%E6%8B%93', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_slangkunsongtuo?ie=UTF8&page=1&rh=n%3A1953164051%2Cp_89%3ALACO%20%E6%9C%97%E5%9D%A4', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b329825071?ie=UTF8&node=329825071', 'http://www.amazon.cn/gp/feature.html/ref=sd_allcat_jewelr_l3_1506408?ie=UTF8&docId=1506408', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_sgold_jewelry?ie=UTF8&page=1&rh=n%3A77323071', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_ssilver_jewelr?ie=UTF8&page=1&rh=n%3A816482051%2Cp_n_feature_eight_browse-bin%3A2051118051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_splatinum_jewe?ie=UTF8&page=1&rh=n%3A816482051%2Cp_n_feature_eight_browse-bin%3A2051112051%2Cp_n_feature_eight_browse-bin%3A2051114051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b80407071?ie=UTF8&node=80407071', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816604051?ie=UTF8&node=816604051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816602051?ie=UTF8&node=816602051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816605051?ie=UTF8&node=816605051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816622051?ie=UTF8&node=816622051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816612051?ie=UTF8&node=816612051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_salloy_jewelry?ie=UTF8&page=1&rh=n%3A816482051%2Cp_n_feature_eight_browse-bin%3A2051122051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_snatural_cryst?ie=UTF8&page=1&rh=n%3A816482051%2Cp_n_material_browse%3A2051132051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_snatural_jade?ie=UTF8&page=1&rh=n%3A816482051%2Cp_n_material_browse%3A2051160051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_spearl_jewelry?ie=UTF8&page=1&rh=n%3A816482051%2Cp_n_material_browse%3A2051141051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816603051?ie=UTF8&node=816603051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b816610051?ie=UTF8&node=816610051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_ssilver_jewelr?ie=UTF8&page=1&rh=n%3A816482051%2Cp_6%3AA1AJ19PSB66TGU%2Cp_n_material_browse%3A2051144051%2Cp_n_material_browse%3A2051154051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_syuanmu?ie=UTF8&page=1&rh=n%3A816482051%2Cp_6%3AA1AJ19PSB66TGU%2Cp_n_material_browse%3A2051182051', 'http://www.amazon.cn/s/ref=sd_allcat_jewelr_l3_simport_access?ie=UTF8&page=1&rh=n%3A816482051%2Cp_89%3ADaisy%7CTuscany%20Silver%7CMissoma%7CHoxton%20London%7CLILY%20AND%20LOTTY%7CFrance%20Luxe%26bbn%3D816482051', 'http://www.amazon.cn/b/ref=sd_allcat_jewelr_l3_b2154072051?ie=UTF8&node=2154072051', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_sgps_navigator?ie=UTF8&page=1&rh=n%3A1947901051%2Cp_6%3AA1AJ19PSB66TGU%2Cn%3A2127789051%2Cn%3A!1947900051%2Cn%3A1947899051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b124947071?ie=UTF8&node=124947071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b2127790051?ie=UTF8&node=2127790051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b124944071?ie=UTF8&node=124944071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b124949071?ie=UTF8&node=124949071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1947991051?ie=UTF8&node=1947991051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1947923051?ie=UTF8&node=1947923051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b163692071?ie=UTF8&node=163692071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b77812071?ie=UTF8&node=77812071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1947953051?ie=UTF8&node=1947953051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1947935051?ie=UTF8&node=1947935051', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_strunk_mat?ie=UTF8&page=1&rh=n%3A255478071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b77999071?ie=UTF8&node=77999071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b2054679051?ie=UTF8&node=2054679051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b2126200051?ie=UTF8&node=2126200051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1948012051?ie=UTF8&node=1948012051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1948021051?ie=UTF8&node=1948021051', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_scar_wash_liquid?ie=UTF8&page=1&rh=n%3A1947967051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1948015051?ie=UTF8&node=1948015051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b2128149051?ie=UTF8&node=2128149051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b51498071?ie=UTF8&node=51498071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1948024051?ie=UTF8&node=1948024051', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b51519071?ie=UTF8&node=51519071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b2127383051?ie=UTF8&node=2127383051', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_swelcome_tap?ie=UTF8&page=1&rh=n%3A255622071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_savoid_crash?ie=UTF8&page=1&rh=n%3A255631071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_scar_top_shelf?ie=UTF8&page=1&rh=n%3A255462071', 'http://www.amazon.cn/b/ref=sd_allcat_auto_l3_b1947961051?ie=UTF8&node=1947961051', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_smud_protection?ie=UTF8&page=1&rh=n%3A77963071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_splate_frame?ie=UTF8&page=1&rh=n%3A1947947051', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_sback_mirror?ie=UTF8&page=1&rh=n%3A77959071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_smoto_helmet?ie=UTF8&page=1&rh=n%3A255803071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_sriding_protecti?ie=UTF8&page=1&rh=n%3A255814071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_seye_protection?ie=UTF8&page=1&rh=n%3A255802071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_ssafety_seat?ie=UTF8&page=1&rh=n%3A255410071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_srepair_tool?ie=UTF8&page=1&rh=n%3A255961071', 'http://www.amazon.cn/s/ref=sd_allcat_auto_l3_semergency_rescu?ie=UTF8&page=1&rh=n%3A1947903051']
13 | headers = {'User-Agent':
14 | 'Mozilla/5.0 (Windows NT 5.1; rv:33.0) Gecko/20100101 Firefox/33.0', 'Host': 'www.amazon.cn'}
15 | jishu = 0
16 | zongshu = len(starturls)
17 |
18 |
19 | def get_id(url):
20 | while 1:
21 | try:
22 | r = requests.get(url, headers=headers, timeout=5)
23 | xpath = fromstring(r.text).xpath
24 | pid = xpath('//li/@data-asin|//div/@name')
25 | nextpage = xpath('//a[@id="pagnNextLink"]/@href')
26 | if pid:
27 | with open('all_ids.txt', 'a') as f:
28 | f.write('\n'.join(pid) + '\n')
29 | try:
30 | print '.\r',
31 | except:
32 | print('.', end='')
33 | if not nextpage:
34 | return
35 | np = nextpage[0]
36 | if not np.startswith('http'):
37 | np = 'http://www.amazon.cn' + np
38 | # print np
39 | return np
40 | except:
41 | pass
42 | return
43 |
44 |
45 | def ss(url):
46 | aa = get_id(url)
47 | while aa:
48 | aa = get_id(aa)
49 | global jishu
50 | jishu += 1
51 | try:
52 | print '=' * 30, jishu, '/', zongshu, '=' * 30
53 | except:
54 | print('=' * 30, jishu, '/', zongshu, '=' * 30)
55 |
56 | pp = Pool(150)
57 |
58 | pp.map(ss, starturls)
59 | try:
60 | pp.close()
61 | pp.join()
62 | except:
63 | pass
64 | # import smtplib
65 | # from email.mime.text import MIMEText
66 | # from email.header import Header
67 |
68 | # mailfrom = 'xx@163.com'
69 | # mailto = 'xx@qq.com'
70 | # title = u'亚马逊ID抓完了'
71 | # cc = 'check english'
72 |
73 |
74 | # msg = MIMEText(cc)
75 | # msg['Subject'] = Header(title, 'utf-8')
76 | # smtp = smtplib.SMTP()
77 | # smtp.connect("smtp.163.com")
78 | # smtp.login('idxx', 'passwordxx')
79 | # smtp.sendmail(mailfrom, mailto, msg.as_string())
80 | # smtp.quit()
81 |
--------------------------------------------------------------------------------