@35iter/spider-core/dist/check.js

使用 puppetter-cluster 的爬虫工具。

"use strict";
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
    return new (P || (P = Promise))(function (resolve, reject) {
        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
        step((generator = generator.apply(thisArg, _arguments || [])).next());
    });
};
Object.defineProperty(exports, "__esModule", { value: true });
exports.runCheck = exports.sleep = void 0;
function checkByElement(page, selector) {
    return __awaiter(this, void 0, void 0, function* () {
        return !!(yield page.$(selector));
    });
}
// 计时结束后的标志
const sleepStr = "awake";
const sleep = (s) => {
    return new Promise((res) => {
        setTimeout(() => {
            res(sleepStr);
        }, s);
    });
};
exports.sleep = sleep;
/**
 *
 * @param check 检查方法，可以返回 promise 或者 boolean
 * @param timeout 检查超时时间，默认 10 秒钟，
 * @returns
 */
function runCheck(check, timeout = 10 * 1000) {
    return __awaiter(this, void 0, void 0, function* () {
        let _resolve;
        let _reject;
        const maxTime = +new Date() + timeout;
        const returnPromise = new Promise((resolve, reject) => {
            _resolve = resolve;
            _reject = reject;
        });
        (function runrun() {
            return __awaiter(this, void 0, void 0, function* () {
                // 剩余时间
                const delta = maxTime - +new Date();
                if (delta < 0) {
                    _reject("检查失败[超时]");
                }
                let checkResult = false;
                try {
                    // 每次执行 check，都与剩余时间进行比较，避免超时
                    checkResult = yield Promise.race([check(), (0, exports.sleep)(delta)]);
                }
                catch (error) {
                    _reject("检查失败[check方法执行出错]");
                }
                if (checkResult === sleepStr) {
                    // sleep 函数先结束，表示已经超时了
                    _reject("检查失败[超时]");
                }
                else if (checkResult) {
                    _resolve();
                }
                else if (!checkResult) {
                    // check 执行返回 false，表示还没得到正确的结果，继续执行 check
                    setTimeout(() => __awaiter(this, void 0, void 0, function* () {
                        runrun();
                    }), 100);
                }
            });
        })();
        return returnPromise;
    });
}
exports.runCheck = runCheck;