Question

使用Selenium WebDriver.chromedriver获取json结果数据时出现问题，服务器将响应http状态码429太多请求。但是当我直接使用chrome来获取此网址“ https://shop.coles.com.au/search/resources/store/20501/productview/2364711P”时，它将可以正常工作。我认为服务器端有一些验证逻辑，但是如何交叉，请多多帮助〜

我明白了为什么要被服务器阻止下面的这段js代码检测到我使用了webdriver然后阻止了我，然后就不创建cookie了。

"use strict";
!function() {
    function e(e) {
        var r = (void 0 !== e.stack ? e.stack : "").replace(/"/g, '"')
          , t = {
            stack: r,
            message: e.message,
            name: e.name
        };
        (new Image).src = l + "/error?e=" + encodeURIComponent(JSON.stringify(t)),
        console.log("Error", "\n  name: " + t.name, "\n  message: " + t.message, "\n  stack: " + t.stack)
    }
    function r(e) {
        return "true" === e
    }
    function t(e) {
        return void 0 !== e && e.indexOf("canvas") > -1
    }
    function n(e) {
        return void 0 !== e.ActiveXObject && null !== e.ActiveXObject
    }
    function a(e) {
        return void 0 !== e.Fingerprint2 && null !== e.Fingerprint2
    }
    function i(e) {
        return null !== ("" + e.userAgent).match(/PhantomJS/)
    }
    function o(e) {
        return void 0 !== e.webdriver
    }
    function c(e) {
        try {
            return e.appName = "Chrome macIntel IE",
            "Chrome macIntel IE" === e.appName
        } catch (e) {
            return !1
        }
    }
    function s(e) {
        var r = o(e.navigator) && !1 !== e.navigator.webdriver
          , t = "webdriver"in e
          , n = "true" === document.getElementsByTagName("html")[0].getAttribute("webdriver");
        return r || t || n
    }
    function u(e) {
        try {
            return (0,
            (0,
            e.constructor.constructor)("return process")().mainModule.require)("fs"),
            !0
        } catch (e) {
            return !1
        }
    }
    function tEibEnv() {
        var e = ["stack", "stackTrace", "description"];
        try {
            []()[[+[]] + []]
        } catch (r) {
            return void 0 !== r[e[0]] ? r[e[0]] : void 0 !== r[e[1]] ? r[e[1]] : void 0 !== r[e[2]] ? r[e[2]] : ""
        }
    }
    function I() {
        if ("undefined" == typeof XMLHttpRequest)
            try {
                return new ActiveXObject("Msxml2.XMLHTTP.6.0")
            } catch (e) {
                try {
                    return new ActiveXObject("Msxml2.XMLHTTP.3.0")
                } catch (e) {
                    try {
                        return new ActiveXObject("Microsoft.XMLHTTP")
                    } catch (e) {
                        throw new Error("AJAX requests appear to be unsupported by this browser")
                    }
                }
            }
        return new XMLHttpRequest
    }
    function E(e, r) {
        for (var t in r)
            if (Object.prototype.hasOwnProperty.call(r, t)) {
                var n = r[t];
                void 0 !== n && e.setRequestHeader(t, n)
            }
        return e
    }
    function d(e, r, t, n, a) {
        try {
            var i = I();
            i.open(r, e, !0),
            void 0 !== t.headers && E(i, t.headers),
            i.onreadystatechange = function() {
                if (4 === i.readyState) {
                    var e = "" + i.status;
                    if ("4" === e.charAt(0) || "5" === e.charAt(0))
                        return void n(new Error("Error issuing AJAX request (status code: " + e + ")"));
                    a(i.responseText)
                }
            }
            ,
            i.send(t.body)
        } catch (e) {
            n(e)
        }
    }
    function N(e, r, t, n) {
        var a = n;
        try {
            d(l, "POST", {
                headers: {
                    "Content-Type": "application/json; charset=utf-8"
                },
                body: JSON.stringify({
                    t: e,
                    d: r
                })
            }, t, function(e) {
                try {
                    a(JSON.parse(e))
                } catch (e) {
                    t(e)
                }
            })
        } catch (e) {
            t(e)
        }
    }
    function _(e, r, t, a, o, I, E, d, _, v, l) {
        var f = window
          , R = window.navigator
          , L = {
            a719076e644f9e643a85b5c16b391623abd18d1b37c4b5629c4de8f2f01b4704f: e,
            ab78473b1c731bfc01032f3ee7df063b3fd085b3ba6c9eb186df3ed4f92442b1a: r,
            a6c7ed91d806b6bb3b5a3bdcc4091c4f8dc081db7ffc0831f955e2bcb3aab7355: t,
            a061a12d2fd8497ae57a06624b04b9c7faa35b77b803402a0da22f03b78e99a62: a,
            a2159e86126934a65811ace05974f8a36ae2b6d5de0bbf5824d3605e5d7077ab4: o,
            af5ea0bb3bdbaa142a206ed65324c1eb45469bf2cabbecdc7a180d27a49332bac: I,
            ab47f0a3cf8da04ff7dd6196f6ae6a06b906bc4a0b30cfc71c2730bb70efd2940: E,
            ab9cec510ce9fb76e79882a7f612275b083c607c17fe9dd44438da49625c08cfc: void 0 !== d ? d : [],
            a89ee5f18b07459773463dfd370524376e8b4d997c13436c62b763cc649f548ea: void 0 !== _ ? _ : [],
            a083c50eb73edc35f752e1b1d3925114d5a53f93352752e88d87e13f9432b05ce: tEibEnv(),
            ac54ffdaf47ba30b6e1c02994c2a77cd822c023cf55c8679fcd2b1e722a33fd88: u(f),
            a14559ea59a0352ae64faa9bbc92eec821130e9b560f420bb16d8542699952a87: s(f),
            a8d2114495f1bc2c3adeb4a7f0e99553e252ad79a39ad72c0be1f1ebdf3cf1cdb: void 0 !== R && i(R),
            a701bb64a76ab3877ebf146a5dd709778eb2fc99de0005972eda2dae28dc12fb7: void 0 !== R && c(R),
            ac57c5637ca15e2901d75b3953d35d492e6c700a554e58cf00f302d8ab82d0ac4: n(f)
        };
        N(T, L, v, l)
    }
    function v(n) {
        (new (0,
        n.Fingerprint2)).get(function(n, a) {
            for (var i = {}, o = 0; o < a.length; o++) {
                var c = a[o];
                i[c.key] = c.value
            }
            _(n, i.user_agent, r(i.has_lied_browser), r(i.has_lied_os), r(i.adblock), t(i.canvas), i.available_resolution, i.regular_plugins, i.ie_plugins, e, function(e) {
                e.redirect && window.location.reload(!0)
            })
        })
    }
    var l = "/149e9513-01fa-4fb0-aad4-566afd725d1b/2d206a39-8ed7-437e-a3be-862e0f06eea3/fingerprint"
      , T = "94dbc0cc-d783-c10b-3612-c657311fecb9";
    if (a(window))
        try {
            v(window)
        } catch (r) {
            e(r)
        }
    else
        !function(e, r, t, n) {
            var i = e
              , o = setInterval(function() {
                return i <= 0 ? (clearInterval(o),
                t(new Error("Library is not defined"))) : a(window) ? (clearInterval(o),
                n(window)) : void (i -= 1)
            }, r)
        }(100, 100, function(r) {
            e(r)
        }, function(r) {
            try {
                v(r)
            } catch (r) {
                e(r)
            }
        })
}();
//# sourceMappingURL=fingerprint.js.map

Answer 1

查找解决方案将此添加到您的.py，然后使用网络驱动程序

options = webdriver.ChromeOptions()
options.add_experimental_option('excludeSwitches', ['enable-automation']) 
wdriver = webdriver.Chrome(options=options)

然后它起作用了！

chromedriver请求时导致状态码429

1 个答案: