Python3爬取淘宝网商品数据！
分析淘宝网
这次选择的是淘宝网热卖而不是淘宝网，二者虽然名字有不同，但是数据还是一样的，区别就在于前者把后者的所有店铺和商品的海量数据按照销售量、好评度、信誉度综合测评、重新计算、重新排序展现给买家的一个导购网站。
找到准确数据：
请求参数对比：
jsv: 2.4.0
appKey: 12574478
t: 1597626852590
sign: 457c09a81147eb493d1f58ad6ab64d52
api: mtop.alimama.union.sem.landing.pc.items
v: 1.0
AntiCreep: true
dataType: jsonp
type: jsonp
ecode: 0
callback: mtopjsonp1
data: {"keyword":"女装","ppath":"","loc":"","minPrice":"","maxPrice":"","ismall":"","ship":"","itemAssurance":"","exch
jsv: 2.4.0
appKey: 12574478
t: 1597626856031
sign: 4a87f4308903ded469a1328275ded458
api: mtop.alimama.union.sem.landing.pc.items
v: 1.0
AntiCreep: true
dataType: jsonp
type: jsonp
ecode: 0
callback: mtopjsonp1
data: {"keyword":"女装","ppath":"","loc":"","minPrice":"","maxPrice":"","ismall":"","ship":"","itemAssurance":"","exchange7":"","custAssurance":"","b":"","clk1":"91a160066daf9f8b69646bd610341da7","pvoff":"","pageSize":"100","page":"","elemtid":"1","refpid":"mm_26632258_3504122_32538762","pid":"430673_1006","featureNames":"spGoldMedal,dsrDescribe,dsrDescribeGap,dsrService,dsrServiceGap,dsrDeliver, dsrDeliverGap","ac":"5TGcF6nyjHkCAXt4MaK1QH5c","wangwangid":"","catId":""}
发现请求数据有所改变的地方只有t和sign以及data中的page和ac，其他均没有发生改变，t参数明眼就能猜出是时间戳，sign参数还得通过调试和阅读源码进行逆向分析。
解决t和sign参数
发现sign和t以及其他参数都在这里面构造的。
所以我们现在开始下断点调试这些参数，得出sign参数的构造过程。可以发现t就是当前时间戳，然后sign是由h(d.token + "&" + i + "&" + g + "&" + c.data)构成，d.token是this.options.token也就是cookie值中的_m_h5_tk参数的前部分，i是时间戳，g就是12574478，c.data就是this.params.data。
this.options.token = e4a0bbef377f5792e1852f92581f769c(参考值)
this.params.data = {"keyword":"女装","ppath":"","loc":"","minPrice":"","maxPrice":"","ismall":"","ship":"","itemAssurance":"","exchange7":"","custAssurance":"","b":"","clk1":"91a160066daf9f8b69646bd610341da7","pvoff":"","pageSize":"100","page":"","elemtid":"1","refpid":"mm_26632258_3504122_32538762","pid":"430673_1006","featureNames":"spGoldMedal,dsrDescribe,dsrDescribeGap,dsrService,dsrServiceGap,dsrDeliver, dsrDeliverGap","ac":"5TGcF6nyjHkCAXt4MaK1QH5c","wangwangid":"","catId":""}
h函数就是下图所示。
function h(a) {
function b(a, b) {
return a << b | a >>> 32 - b
}
function c(a, b) {
var c, d, e, f, g;
return e = 2147483648 & a,
f = 2147483648 & b,
c = 1073741824 & a,
d = 1073741824 & b,
g = (1073741823 & a) + (1073741823 & b),
c & d ? 2147483648 ^ g ^ e ^ f : c | d ? 1073741824 & g ? 3221225472 ^ g ^ e ^ f : 1073741824 ^ g ^ e ^ f : g ^ e ^ f
}
function d(a, b, c) {
return a & b | ~a & c
}
function e(a, b, c) {
return a & c | b & ~c
}
function f(a, b, c) {
return a ^ b ^ c
}
function g(a, b, c) {
return b ^ (a | ~c)
}
function h(a, e, f, g, h, i, j) {
return a = c(a, c(c(d(e, f, g), h), j)),
c(b(a, i), e)
}
function i(a, d, f, g, h, i, j) {
return a = c(a, c(c(e(d, f, g), h), j)),
c(b(a, i), d)
}
function j(a, d, e, g, h, i, j) {
return a = c(a, c(c(f(d, e, g), h), j)),
c(b(a, i), d)
}
function k(a, d, e, f, h, i, j) {
return a = c(a, c(c(g(d, e, f), h), j)),
c(b(a, i), d)
}
function l(a) {
for (var b, c = a.length, d = c + 8, e = (d - d % 64) / 64, f = 16 * (e + 1), g = new Array(f - 1), h = 0, i = 0; c > i; )
b = (i - i % 4) / 4,
h = i % 4 * 8,
g[b] = g[b] | a.charCodeAt(i) << h,
i++;
return b = (i - i % 4) / 4,
h = i % 4 * 8,
g[b] = g[b] | 128 << h,
g[f - 2] = c << 3,
g[f - 1] = c >>> 29,
g
}
function m(a) {
var b, c, d = "", e = "";
for (c = 0; 3 >= c; c++)
b = a >>> 8 * c & 255,
e = "0" + b.toString(16),
d += e.substr(e.length - 2, 2);
return d
}
function n(a) {
a = a.replace(/\r\n/g, "\n");
for (var b = "", c = 0; c < a.length; c++) {
var d = a.charCodeAt(c);
128 > d ? b += String.fromCharCode(d) : d > 127 && 2048 > d ? (b += String.fromCharCode(d >> 6 | 192),
b += String.fromCharCode(63 & d | 128)) : (b += String.fromCharCode(d >> 12 | 224),
b += String.fromCharCode(d >> 6 & 63 | 128),
b += String.fromCharCode(63 & d | 128))
}
return b
}
var o, p, q, r, s, t, u, v, w, x = [], y = 7, z = 12, A = 17, B = 22, C = 5, D = 9, E = 14, F = 20, G = 4, H = 11, I = 16, J = 23, K = 6, L = 10, M = 15, N = 21;
for (a = n(a),
x = l(a),
t = 1732584193,
u = 4023233417,
v = 2562383102,
w = 271733878,
o = 0; o < x.length; o += 16)
p = t,
q = u,
r = v,
s = w,
t = h(t, u, v, w, x[o + 0], y, 3614090360),
w = h(w, t, u, v, x[o + 1], z, 3905402710),
v = h(v, w, t, u, x[o + 2], A, 606105819),
u = h(u, v, w, t, x[o + 3], B, 3250441966),
t = h(t, u, v, w, x[o + 4], y, 4118548399),
w = h(w, t, u, v, x[o + 5], z, 1200080426),
v = h(v, w, t, u, x[o + 6], A, 2821735955),
u = h(u, v, w, t, x[o + 7], B, 4249261313),
t = h(t, u, v, w, x[o + 8], y, 1770035416),
w = h(w, t, u, v, x[o + 9], z, 2336552879),
v = h(v, w, t, u, x[o + 10], A, 4294925233),
u = h(u, v, w, t, x[o + 11], B, 2304563134),
t = h(t, u, v, w, x[o + 12], y, 1804603682),
w = h(w, t, u, v, x[o + 13], z, 4254626195),
v = h(v, w, t, u, x[o + 14], A, 2792965006),
u = h(u, v, w, t, x[o + 15], B, 1236535329),
t = i(t, u, v, w, x[o + 1], C, 4129170786),
w = i(w, t, u, v, x[o + 6], D, 3225465664),
v = i(v, w, t, u, x[o + 11], E, 643717713),
u = i(u, v, w, t, x[o + 0], F, 3921069994),
t = i(t, u, v, w, x[o + 5], C, 3593408605),
w = i(w, t, u, v, x[o + 10], D, 38016083),
v = i(v, w, t, u, x[o + 15], E, 3634488961),
u = i(u, v, w, t, x[o + 4], F, 3889429448),
t = i(t, u, v, w, x[o + 9], C, 568446438),
w = i(w, t, u, v, x[o + 14], D, 3275163606),
v = i(v, w, t, u, x[o + 3], E, 4107603335),
u = i(u, v, w, t, x[o + 8], F, 1163531501),
t = i(t, u, v, w, x[o + 13], C, 2850285829),
w = i(w, t, u, v, x[o + 2], D, 4243563512),
v = i(v, w, t, u, x[o + 7], E, 1735328473),
u = i(u, v, w, t, x[o + 12], F, 2368359562),
t = j(t, u, v, w, x[o + 5], G, 4294588738),
w = j(w, t, u, v, x[o + 8], H, 2272392833),
v = j(v, w, t, u, x[o + 11], I, 1839030562),
u = j(u, v, w, t, x[o + 14], J, 4259657740),
t = j(t, u, v, w, x[o + 1], G, 2763975236),
w = j(w, t, u, v, x[o + 4], H, 1272893353),
v = j(v, w, t, u, x[o + 7], I, 4139469664),
u = j(u, v, w, t, x[o + 10], J, 3200236656),
t = j(t, u, v, w, x[o + 13], G, 681279174),
w = j(w, t, u, v, x[o + 0], H, 3936430074),
v = j(v, w, t, u, x[o + 3], I, 3572445317),
u = j(u, v, w, t, x[o + 6], J, 76029189),
t = j(t, u, v, w, x[o + 9], G, 3654602809),
w = j(w, t, u, v, x[o + 12], H, 3873151461),
v = j(v, w, t, u, x[o + 15], I, 530742520),
u = j(u, v, w, t, x[o + 2], J, 3299628645),
t = k(t, u, v, w, x[o + 0], K, 4096336452),
w = k(w, t, u, v, x[o + 7], L, 1126891415),
v = k(v, w, t, u, x[o + 14], M, 2878612391),
u = k(u, v, w, t, x[o + 5], N, 4237533241),
t = k(t, u, v, w, x[o + 12], K, 1700485571),
w = k(w, t, u, v, x[o + 3], L, 2399980690),
v = k(v, w, t, u, x[o + 10], M, 4293915773),
u = k(u, v, w, t, x[o + 1], N, 2240044497),
t = k(t, u, v, w, x[o + 8], K, 1873313359),
w = k(w, t, u, v, x[o + 15], L, 4264355552),
v = k(v, w, t, u, x[o + 6], M, 2734768916),
u = k(u, v, w, t, x[o + 13], N, 1309151649),
t = k(t, u, v, w, x[o + 4], K, 4149444226),
w = k(w, t, u, v, x[o + 11], L, 3174756917),
v = k(v, w, t, u, x[o + 2], M, 718787259),
u = k(u, v, w, t, x[o + 9], N, 3951481745),
t = c(t, p),
u = c(u, q),
v = c(v, r),
w = c(w, s);
var O = m(t) + m(u) + m(v) + m(w);
return O.toLowerCase()
}
发现这个h函数就是个md5加密方式，这样的话也就太容易了。
解决page和ac参数
page参数一看就知道是页数了，第一页为空，第二页为2，如：访问第一页时，page:""，访问第二页时，page:"2"，后面以此类推。
ac参数就是我们cookie值中的cna参数值，cna参数值得访问网站获得https://log.mmstat.com/eg.js，获得
代码如下：
import requests
session = requests.Session()
headers = {
'authority': 'log.mmstat.com',
'method': 'GET',
'path': '/eg.js',
'scheme': 'https',
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'referer': "https://uland.taobao.com/sem/tbsearch?spm=a2e15.8261149.07626516003.1.7ab029b4ZS1aM4&refpid=mm_26632258_3504122_32538762&keyword=%E6%B7%98%E5%AE%9D&clk1=f1a5efd94339f0e6e7cba63ed79b8554&upsid=f1a5efd94339f0e6e7cba63ed79b8554&page=2&_input_charset=utf-8",
'sec-fetch-dest': 'script',
'sec-fetch-mode': 'no-cors',
'sec-fetch-site': 'cross-site',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
session.get('https://log.mmstat.com/eg.js', headers=headers)
print(session.cookies.get('cna'))
发现这个h函数就是个md5加密方式，这样的话也就太容易了。
在这里插入图片描述
在这里插入图片描述
解决page和ac参数
page参数一看就知道是页数了，第一页为空，第二页为2，如：访问第一页时，page:""，访问第二页时，page:"2"，后面以此类推。
ac参数就是我们cookie值中的cna参数值，cna参数值得访问网站获得https://log.mmstat.com/eg.js，获得
代码如下：
import requests
session = requests.Session()
headers = {
'authority': 'log.mmstat.com',
'method': 'GET',
'path': '/eg.js',
'scheme': 'https',
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'referer': "https://uland.taobao.com/sem/tbsearch?spm=a2e15.8261149.07626516003.1.7ab029b4ZS1aM4&refpid=mm_26632258_3504122_32538762&keyword=%E6%B7%98%E5%AE%9D&clk1=f1a5efd94339f0e6e7cba63ed79b8554&upsid=f1a5efd94339f0e6e7cba63ed79b8554&page=2&_input_charset=utf-8",
'sec-fetch-dest': 'script',
'sec-fetch-mode': 'no-cors',
'sec-fetch-site': 'cross-site',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
session.get('https://log.mmstat.com/eg.js', headers=headers)
print(session.cookies.get('cna'))
有人可能说我为什么会知道这些，因为我认真的分析了整个网站，这个部分的分析过程就不放出来了。
Python进行爬取
前面已经分析了整个网站了，废话不多说了，直接开始上开始上全代码了，复制过去就可以直接运行的代码，淘宝对每个结果最多只显示100页，所以这里也只有100页，如果你需要搜索的与我的不同自己直接修改即可。
import hashlib
import time
import requests
from urllib import parse
import json
class TaoBao():
def __init__(self,keyword):
self.keyword = keyword
self.session = requests.Session()
self.cookies = {}
self.data = {}
self.params = {}
self.headers = {}
for page in range(1,100+1):
if page == 1:
self.get_url()
self.get_m_h5_tk()
self.get_cna()
self.get_data(page)
else:
self.get_data(page)
def to_cookie(self):
cookie = ''
for key, value in self.cookies.items():
if '_m_h5' in key or 'cna' == key:
cookie += key + '=' + value + '; '
return cookie
def h(self,a):
md5 = hashlib.md5()
md5.update(a.encode())
return md5.hexdigest()
# 获取uland地址和clk1值
def get_url(self):
headers = {
"Host":"redirect.simba.taobao.com",
"Upgrade-Insecure-Requests":"1",
"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36",
"Accept":"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9",
"Accept-Encoding":"gzip, deflate",
"Accept-Language":"zh-CN,zh;q=0.9",
"Connection":"keep-alive"
}
url = 'http://redirect.simba.taobao.com/rd?c=un&w=unionsem&k=74175f13c74157df&p=mm_26632258_3504122_32538762&b=R9JQC0peugGMqgRlL5O&s={keyword}&f=https%3A%2F%2Fuland.taobao.com%2Fsem%2Ftbsearch%3Frefpid%3Dmm_26632258_3504122_32538762%26keyword{keywords}'.format(keyword=parse.quote(self.keyword),keywords=parse.quote(parse.quote('='+self.keyword)))
response = self.session.get(url,headers=headers,allow_redirects=False)
self.clk1 = response.headers.get('Location').split('&')[2]
self.uland_url = response.headers.get('Location')
# 获取_m_h5_tk和_m_h5_tk_enc
def get_m_h5_tk(self):
self.data = {
"keyword": self.keyword,
"ppath": "", "loc": "",
"minPrice": "",
"maxPrice": "",
"ismall": "",
"ship": "",
"itemAssurance": "",
"exchange7": "",
"custAssurance": "",
"b": "",
"clk1": self.clk1,
"pvoff": "",
"pageSize": "100",
"page": "",
"elemtid": "1",
"refpid": "mm_26632258_3504122_32538762",
"pid": "430673_1006",
"featureNames": "spGoldMedal,dsrDescribe,dsrDescribeGap,dsrService,dsrServiceGap,dsrDeliver, dsrDeliverGap",
"ac": "",
"wangwangid": "",
"catId": ""
}
self.timestamp = str(time.time()).replace('.', '')[:13]
self.params = {
'jsv': '2.4.0',
'appKey': '12574478',
't': self.timestamp,
'sign': self.h('undefined' + "&" + self.timestamp + "&" + '12574478' + "&" + json.dumps(self.data,ensure_ascii=False).replace(' ', '')),
'api': 'mtop.alimama.union.sem.landing.pc.items',
'v': '1.0',
'AntiCreep': 'true',
'dataType': 'jsonp',
'type': 'jsonp',
'ecode': '0',
'callback': 'mtopjsonp1',
'data': json.dumps(self.data, ensure_ascii=False).replace(' ', '')
}
self.headers = {
'host': 'h5api.m.taobao.com',
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-Hans-CN, zh-Hans; q=0.8, en-US; q=0.5, en; q=0.3',
'referer': self.uland_url,
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36',
}
self.session.get('https://h5api.m.taobao.com' + '/h5/mtop.alimama.union.sem.landing.pc.items/1.0/?' + parse.urlencode(self.params), headers=self.headers)
for key, value in self.session.cookies.items():
self.cookies[key] = value
self.token = self.cookies['_m_h5_tk'].split('_')[0]
# 获取cna
def get_cna(self):
headers = {
'authority': 'log.mmstat.com',
'method': 'GET',
'path': '/eg.js',
'scheme': 'https',
'accept': '*/*',
'accept-encoding': 'gzip, deflate, br',
'accept-language': 'zh-CN,zh;q=0.9',
'referer': self.uland_url,
'sec-fetch-dest': 'script',
'sec-fetch-mode': 'no-cors',
'sec-fetch-site': 'cross-site',
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.116 Safari/537.36'
}
self.session.get('https://log.mmstat.com/eg.js', headers=headers)
for key, value in self.session.cookies.items():
self.cookies[key] = value
# 获取数据
def get_data(self, page):
self.data['page'] = "" if page == 1 else page
self.data['ac'] = "" if page == 1 else self.cookies.get('cna')
self.timestamp = str(time.time()).replace('.', '')[:13]
self.params['t'] = self.timestamp
self.params['sign'] = self.h(self.token + "&" + self.timestamp + "&" + '12574478' + "&" + json.dumps(self.data,ensure_ascii=False).replace(' ',''))
self.params['data'] = json.dumps(self.data, ensure_ascii=False).replace(' ', '')
self.headers['cookie'] = self.to_cookie()
response = self.session.get('https://h5api.m.taobao.com' + '/h5/mtop.alimama.union.sem.landing.pc.items/1.0/?' + parse.urlencode(self.params), headers=self.headers)
json_data = json.loads(response.text.replace('mtopjsonp1(','').replace(')',''))
print(json_data)
if __name__ == '__main__':
TaoBao('男装') # 搜索关键词
