主页请求
1、无需验证码
2、需要验证码
第二次请求
我们可以看到,captcha第一发送请求时,响应show_captcha为False时,则不需要验证码;如果为Ture则需要验证码登陆,
而且captcha会立马发送第二次请求,响应后能得到img_base64,即加密后的图片。
3、
应该就是我们需要的数据
看到我们需要的数据例,signature也是加密的,所以我们需要看看signature是个什么鬼
可以通过js加密部分一起抓取过来
附上源码
import base64 import hmac import time from ctypes import * from hashlib import sha1 from urllib.parse import urlencode import execjs from requests_html import HTMLSession from http.cookiejar import LWPCookieJar import requests # session = HTMLSession() # requests.session() # session.cookies = LWPCookieJar() # session.cookies.save('1.txt') # session.cookies.load('1.txt') # session.request() # 云打码平台开发者文档调用的接口 YDMApi = windll.LoadLibrary(r'D:my way个人代码spider知乎yundamaAPI-x64.dll') appId = 9250 # 软件ID,开发者分成必要参数。登录开发者后台【我的软件】获得! appKey = b'11cd5fea5bcddb99b5a2886ae480f7a2' # username = b'yxp_ynx' password = b'yxp_ynx' codetype = 1004 # 分配30个字节存放识别结果 result = c_char_p(b" ") # 识别超时时间 单位:秒 timeout = 60 # 验证码文件路径 filename = b'captcha.png' class Spider(): def __init__(self): self.session = HTMLSession() # 验证码访问请求 self.captacha_api = 'https://www.zhihu.com/api/v3/oauth/captcha?lang=en' self.home_page = 'https://www.zhihu.com/signin?next=%2F' self.sign_in_api = 'https://www.zhihu.com/api/v3/oauth/sign_in' self.header = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36' } self.captcha = '' self.signature = '' # 获取cookies def get_first_cookie(self): self.session.get(url=self.home_page,headers=self.header) def deal_captcha(self): while True: r = self.session.get(url=self.captacha_api, headers=self.header).json() # 能获得show_captcha则为图片验证码登陆 if r.get('show_captcha'): r = self.session.put(self.captacha_api, headers= self.header).json() # 获得加密图片 img_base64 = r.get('img_base64') # 获取图片验证按数据 img_content = base64.b64decode(img_base64) # 图片写入文件 with open ('captcha.png','wb') as f: f.write(img_content) # 调用大码品平台接口,解读验证码 YDMApi.YDM_EasyDecodeByPath(username, password, appId, appKey, filename, codetype, timeout, result) self.captcha = result.value.decode('utf-8') # 拿到验证码,发送post请求 r = self.session.post(url=self.captacha_api, headers=self.header, data={'input_text':self.captcha}).json() if r.get('success'): print('验证码输入成功') break else: print('失败重试') # signature请求数据 def get_signature(self): obj = hmac.new(b'd1b964811afb40118a12068ff74a12f4',digestmod=sha1) obj.update(b'password') obj.update(b'c3cef7c66a1843f8b3a9e6a1e3160e20') obj.update(b'com.zhihu.web') obj.update(str(int(time.time() * 1000)).encode('utf-8')) self.signature = obj.hexdigest() # 登陆发送数据 def sign_in(self): data = { 'client_id': 'c3cef7c66a1843f8b3a9e6a1e3160e20', 'grant_type': 'password', 'timestamp': int(time.time() * 1000), 'source': 'com.zhihu.web', 'signature': self.signature, 'username': '用户名', 'password': '密码', 'captcha': self.captcha, 'lang': 'en', 'utm_source': '', 'ref_source': 'other_https://www.zhihu.com/signin?next=%2F', } # 带上js加密算法 with open('知乎加密.js', 'rt',encoding='utf-8') as f: js_code = f.read() js_obj = execjs.compile(js_code, cwd='node_modules') # 必须要转成字典类型 res = js_obj.call('b', urlencode(data)) # cnpm install jsdom 用于js的一个包 # 带上请求头 header = { 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.79 Safari/537.36', 'x-zse-83': '3_2.0', 'content-type': 'application/x-www-form-urlencoded', } self.session.post(url=self.sign_in_api, headers=header, data=res) r = self.session.get(url=r'https://www.zhihu.com/', headers=self.header) print(r.text) def run(self): self.get_first_cookie() self.deal_captcha() self.get_signature() self.sign_in() if __name__ == '__main__': zhihu = Spider() zhihu.run() ''' 在加密js文件必须加上 const jsdom = require("jsdom"); const { JSDOM } = jsdom; const dom = new JSDOM(`<!DOCTYPE html><p>Hello world</p>`); window = dom.window; document = window.document; XMLHttpRequest = window.XMLHttpRequest; '''
const jsdom = require("jsdom"); const { JSDOM } = jsdom; const dom = new JSDOM(`<!DOCTYPE html><p>Hello world</p>`); window = dom.window; document = window.document; XMLHttpRequest = window.XMLHttpRequest; "use strict"; function t(e) { return (t = "function" == typeof Symbol && "symbol" == typeof Symbol.A ? function(e) { return typeof e } : function(e) { return e && "function" == typeof Symbol && e.constructor === Symbol && e !== Symbol.prototype ? "symbol" : typeof e } )(e) } Object.defineProperty(exports, "__esModule", { value: !0 }); var A = "2.0" , __g = {}; function s() {} function i(e) { this.t = (2048 & e) >> 11, this.s = (1536 & e) >> 9, this.i = 511 & e, this.h = 511 & e } function h(e) { this.s = (3072 & e) >> 10, this.h = 1023 & e } function a(e) { this.a = (3072 & e) >> 10, this.c = (768 & e) >> 8, this.n = (192 & e) >> 6, this.t = 63 & e } function c(e) { this.s = e >> 10 & 3, this.i = 1023 & e } function n() {} function e(e) { this.a = (3072 & e) >> 10, this.c = (768 & e) >> 8, this.n = (192 & e) >> 6, this.t = 63 & e } function o(e) { this.h = (4095 & e) >> 2, this.t = 3 & e } function r(e) { this.s = e >> 10 & 3, this.i = e >> 2 & 255, this.t = 3 & e } s.prototype.e = function(e) { e.o = !1 } , i.prototype.e = function(e) { switch (this.t) { case 0: e.r[this.s] = this.i; break; case 1: e.r[this.s] = e.k[this.h] } } , h.prototype.e = function(e) { e.k[this.h] = e.r[this.s] } , a.prototype.e = function(e) { switch (this.t) { case 0: e.r[this.a] = e.r[this.c] + e.r[this.n]; break; case 1: e.r[this.a] = e.r[this.c] - e.r[this.n]; break; case 2: e.r[this.a] = e.r[this.c] * e.r[this.n]; break; case 3: e.r[this.a] = e.r[this.c] / e.r[this.n]; break; case 4: e.r[this.a] = e.r[this.c] % e.r[this.n]; break; case 5: e.r[this.a] = e.r[this.c] == e.r[this.n]; break; case 6: e.r[this.a] = e.r[this.c] >= e.r[this.n]; break; case 7: e.r[this.a] = e.r[this.c] || e.r[this.n]; break; case 8: e.r[this.a] = e.r[this.c] && e.r[this.n]; break; case 9: e.r[this.a] = e.r[this.c] !== e.r[this.n]; break; case 10: e.r[this.a] = t(e.r[this.c]); break; case 11: e.r[this.a] = e.r[this.c]in e.r[this.n]; break; case 12: e.r[this.a] = e.r[this.c] > e.r[this.n]; break; case 13: e.r[this.a] = -e.r[this.c]; break; case 14: e.r[this.a] = e.r[this.c] < e.r[this.n]; break; case 15: e.r[this.a] = e.r[this.c] & e.r[this.n]; break; case 16: e.r[this.a] = e.r[this.c] ^ e.r[this.n]; break; case 17: e.r[this.a] = e.r[this.c] << e.r[this.n]; break; case 18: e.r[this.a] = e.r[this.c] >>> e.r[this.n]; break; case 19: e.r[this.a] = e.r[this.c] | e.r[this.n]; break; case 20: e.r[this.a] = !e.r[this.c] } } , c.prototype.e = function(e) { e.Q.push(e.C), e.B.push(e.k), e.C = e.r[this.s], e.k = []; for (var t = 0; t < this.i; t++) e.k.unshift(e.f.pop()); e.g.push(e.f), e.f = [] } , n.prototype.e = function(e) { e.C = e.Q.pop(), e.k = e.B.pop(), e.f = e.g.pop() } , e.prototype.e = function(e) { switch (this.t) { case 0: e.u = e.r[this.a] >= e.r[this.c]; break; case 1: e.u = e.r[this.a] <= e.r[this.c]; break; case 2: e.u = e.r[this.a] > e.r[this.c]; break; case 3: e.u = e.r[this.a] < e.r[this.c]; break; case 4: e.u = e.r[this.a] == e.r[this.c]; break; case 5: e.u = e.r[this.a] != e.r[this.c]; break; case 6: e.u = e.r[this.a]; break; case 7: e.u = !e.r[this.a] } } , o.prototype.e = function(e) { switch (this.t) { case 0: e.C = this.h; break; case 1: e.u && (e.C = this.h); break; case 2: e.u || (e.C = this.h); break; case 3: e.C = this.h, e.w = null } e.u = !1 } , r.prototype.e = function(e) { switch (this.t) { case 0: for (var t = [], n = 0; n < this.i; n++) t.unshift(e.f.pop()); e.r[3] = e.r[this.s](t[0], t[1]); break; case 1: for (var r = e.f.pop(), i = [], o = 0; o < this.i; o++) i.unshift(e.f.pop()); e.r[3] = e.r[this.s][r](i[0], i[1]); break; case 2: for (var a = [], s = 0; s < this.i; s++) a.unshift(e.f.pop()); e.r[3] = new e.r[this.s](a[0],a[1]) } } ; var k = function(e) { for (var t = 66, n = [], r = 0; r < e.length; r++) { var i = 24 ^ e.charCodeAt(r) ^ t; n.push(String.fromCharCode(i)), t = i } return n.join("") }; function Q(e) { this.t = (4095 & e) >> 10, this.s = (1023 & e) >> 8, this.i = 1023 & e, this.h = 63 & e } function C(e) { this.t = (4095 & e) >> 10, this.a = (1023 & e) >> 8, this.c = (255 & e) >> 6 } function B(e) { this.s = (3072 & e) >> 10, this.h = 1023 & e } function f(e) { this.h = 4095 & e } function g(e) { this.s = (3072 & e) >> 10 } function u(e) { this.h = 4095 & e } function w(e) { this.t = (3840 & e) >> 8, this.s = (192 & e) >> 6, this.i = 63 & e } function G() { this.r = [0, 0, 0, 0], this.C = 0, this.Q = [], this.k = [], this.B = [], this.f = [], this.g = [], this.u = !1, this.G = [], this.b = [], this.o = !1, this.w = null, this.U = null, this.F = [], this.R = 0, this.J = { 0: s, 1: i, 2: h, 3: a, 4: c, 5: n, 6: e, 7: o, 8: r, 9: Q, 10: C, 11: B, 12: f, 13: g, 14: u, 15: w } } Q.prototype.e = function(e) { switch (this.t) { case 0: e.f.push(e.r[this.s]); break; case 1: e.f.push(this.i); break; case 2: e.f.push(e.k[this.h]); break; case 3: e.f.push(k(e.b[this.h])) } } , C.prototype.e = function(A) { switch (this.t) { case 0: var t = A.f.pop(); A.r[this.a] = A.r[this.c][t]; break; case 1: var s = A.f.pop() , i = A.f.pop(); A.r[this.c][s] = i; break; case 2: var h = A.f.pop(); A.r[this.a] = eval(h) } } , B.prototype.e = function(e) { e.r[this.s] = k(e.b[this.h]) } , f.prototype.e = function(e) { e.w = this.h } , g.prototype.e = function(e) { throw e.r[this.s] } , u.prototype.e = function(e) { var t = this , n = [0]; e.k.forEach(function(e) { n.push(e) }); var r = function(r) { var i = new G; return i.k = n, i.k[0] = r, i.v(e.G, t.h, e.b, e.F), i.r[3] }; r.toString = function() { return "() { [native code] }" } , e.r[3] = r } , w.prototype.e = function(e) { switch (this.t) { case 0: for (var t = {}, n = 0; n < this.i; n++) { var r = e.f.pop(); t[e.f.pop()] = r } e.r[this.s] = t; break; case 1: for (var i = [], o = 0; o < this.i; o++) i.unshift(e.f.pop()); e.r[this.s] = i } } , G.prototype.D = function(e) { for (var t = window.atob(e), n = t.charCodeAt(0) << 8 | t.charCodeAt(1), r = [], i = 2; i < n + 2; i += 2) r.push(t.charCodeAt(i) << 8 | t.charCodeAt(i + 1)); this.G = r; for (var o = [], a = n + 2; a < t.length; ) { var s = t.charCodeAt(a) << 8 | t.charCodeAt(a + 1) , c = t.slice(a + 2, a + 2 + s); o.push(c), a += s + 2 } this.b = o } , G.prototype.v = function(e, t, n) { for (t = t || 0, n = n || [], this.C = t, "string" == typeof e ? this.D(e) : (this.G = e, this.b = n), this.o = !0, this.R = Date.now(); this.o; ) { var r = this.G[this.C++]; if ("number" != typeof r) break; var i = Date.now(); if (500 < i - this.R) return; this.R = i; try { this.e(r) } catch (e) { this.U = e, this.w && (this.C = this.w) } } } , G.prototype.e = function(e) { var t = (61440 & e) >> 12; new this.J[t](e).e(this) } , "undefined" != typeof window && (new G).v("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"); var b = function(e) { return __g._encrypt(encodeURIComponent(e)) } exports.ENCRYPT_VERSION = A, exports.default = b