feat: 增强华能电商平台爬虫的反检测能力和数据结构
- 在 BidItem 实体中添加 priority 和 unit 字段,扩展数据结构 - 将爬虫浏览器模式改为非无头模式(headless: false)便于调试 - 为 ChngCrawler 添加人类行为模拟功能: * 模拟鼠标随机移动,增加移动步数和停顿时间 * 模拟人类滚动行为,包括随机滚动距离和停顿 * 添加 navigator 属性伪装,包括语言、插件等 - 在关键节点添加截图功能(bing.png, newPage.png, huaneng.png)用于调试 - 优化反检测策略,降低被目标网站识别为机器人的风险
This commit is contained in:
@@ -20,6 +20,12 @@ export class BidItem {
|
|||||||
@Column({ default: false })
|
@Column({ default: false })
|
||||||
isRead: boolean;
|
isRead: boolean;
|
||||||
|
|
||||||
|
@Column({ default: 0 })
|
||||||
|
priority: number;
|
||||||
|
|
||||||
|
@Column({ nullable: true })
|
||||||
|
unit: string;
|
||||||
|
|
||||||
@CreateDateColumn()
|
@CreateDateColumn()
|
||||||
createdAt: Date;
|
createdAt: Date;
|
||||||
|
|
||||||
|
|||||||
@@ -43,7 +43,7 @@ export class BidCrawlerService {
|
|||||||
}
|
}
|
||||||
|
|
||||||
const browser = await puppeteer.launch({
|
const browser = await puppeteer.launch({
|
||||||
headless: true,
|
headless: false,
|
||||||
args,
|
args,
|
||||||
});
|
});
|
||||||
|
|
||||||
|
|||||||
@@ -2,6 +2,51 @@ import * as puppeteer from 'puppeteer';
|
|||||||
import { Logger } from '@nestjs/common';
|
import { Logger } from '@nestjs/common';
|
||||||
import { ChdtpResult } from './chdtp_target';
|
import { ChdtpResult } from './chdtp_target';
|
||||||
|
|
||||||
|
// 模拟人类鼠标移动
|
||||||
|
async function simulateHumanMouseMovement(page: puppeteer.Page) {
|
||||||
|
const viewport = page.viewport();
|
||||||
|
if (!viewport) return;
|
||||||
|
|
||||||
|
const movements = 5 + Math.floor(Math.random() * 5); // 5-10次随机移动
|
||||||
|
|
||||||
|
for (let i = 0; i < movements; i++) {
|
||||||
|
const x = Math.floor(Math.random() * viewport.width);
|
||||||
|
const y = Math.floor(Math.random() * viewport.height);
|
||||||
|
|
||||||
|
await page.mouse.move(x, y, {
|
||||||
|
steps: 10 + Math.floor(Math.random() * 20) // 10-30步,使移动更平滑
|
||||||
|
});
|
||||||
|
|
||||||
|
// 随机停顿 100-500ms
|
||||||
|
await new Promise(r => setTimeout(r, 100 + Math.random() * 400));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// 模拟人类滚动
|
||||||
|
async function simulateHumanScrolling(page: puppeteer.Page) {
|
||||||
|
const scrollCount = 3 + Math.floor(Math.random() * 5); // 3-7次滚动
|
||||||
|
|
||||||
|
for (let i = 0; i < scrollCount; i++) {
|
||||||
|
const scrollDistance = 100 + Math.floor(Math.random() * 400); // 100-500px
|
||||||
|
|
||||||
|
await page.evaluate((distance) => {
|
||||||
|
window.scrollBy({
|
||||||
|
top: distance,
|
||||||
|
behavior: 'smooth'
|
||||||
|
});
|
||||||
|
}, scrollDistance);
|
||||||
|
|
||||||
|
// 随机停顿 500-1500ms
|
||||||
|
await new Promise(r => setTimeout(r, 500 + Math.random() * 1000));
|
||||||
|
}
|
||||||
|
|
||||||
|
// 滚动回顶部
|
||||||
|
await page.evaluate(() => {
|
||||||
|
window.scrollTo({ top: 0, behavior: 'smooth' });
|
||||||
|
});
|
||||||
|
await new Promise(r => setTimeout(r, 1000));
|
||||||
|
}
|
||||||
|
|
||||||
export const ChngCrawler = {
|
export const ChngCrawler = {
|
||||||
name: '华能集团电子商务平台',
|
name: '华能集团电子商务平台',
|
||||||
url: 'https://ec.chng.com.cn/ecmall/index.html#/purchase/home?top=0',
|
url: 'https://ec.chng.com.cn/ecmall/index.html#/purchase/home?top=0',
|
||||||
@@ -10,7 +55,8 @@ export const ChngCrawler = {
|
|||||||
async crawl(browser: puppeteer.Browser): Promise<ChdtpResult[]> {
|
async crawl(browser: puppeteer.Browser): Promise<ChdtpResult[]> {
|
||||||
const logger = new Logger('ChngCrawler');
|
const logger = new Logger('ChngCrawler');
|
||||||
let page = await browser.newPage();
|
let page = await browser.newPage();
|
||||||
|
// await page.setViewport({ width: 1920, height: 1080, deviceScaleFactor: 1 });
|
||||||
|
// await page.setViewport({ deviceScaleFactor: 1 });
|
||||||
const username = process.env.PROXY_USERNAME;
|
const username = process.env.PROXY_USERNAME;
|
||||||
const password = process.env.PROXY_PASSWORD;
|
const password = process.env.PROXY_PASSWORD;
|
||||||
if (username && password) {
|
if (username && password) {
|
||||||
@@ -19,6 +65,8 @@ export const ChngCrawler = {
|
|||||||
|
|
||||||
await page.evaluateOnNewDocument(() => {
|
await page.evaluateOnNewDocument(() => {
|
||||||
Object.defineProperty(navigator, 'webdriver', { get: () => false });
|
Object.defineProperty(navigator, 'webdriver', { get: () => false });
|
||||||
|
Object.defineProperty(navigator, 'language', { get: () => "zh-CN"});
|
||||||
|
Object.defineProperty(navigator, 'plugins', { get: () => [1,2,3,4,5]});
|
||||||
});
|
});
|
||||||
|
|
||||||
await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36');
|
await page.setUserAgent('Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/143.0.0.0 Safari/537.36');
|
||||||
@@ -40,6 +88,7 @@ export const ChngCrawler = {
|
|||||||
await page.waitForNavigation({ waitUntil: 'networkidle2' });
|
await page.waitForNavigation({ waitUntil: 'networkidle2' });
|
||||||
|
|
||||||
logger.log('Clicking search result...');
|
logger.log('Clicking search result...');
|
||||||
|
await page.screenshot({ path: 'bing.png' });
|
||||||
const firstResultSelector = '#b_results .b_algo h2 a';
|
const firstResultSelector = '#b_results .b_algo h2 a';
|
||||||
await page.waitForSelector(firstResultSelector);
|
await page.waitForSelector(firstResultSelector);
|
||||||
|
|
||||||
@@ -50,18 +99,33 @@ export const ChngCrawler = {
|
|||||||
const newPage = await newTarget.page();
|
const newPage = await newTarget.page();
|
||||||
|
|
||||||
if (newPage) {
|
if (newPage) {
|
||||||
|
await newPage.screenshot({ path: 'newPage.png' });
|
||||||
await page.close();
|
await page.close();
|
||||||
page = newPage;
|
page = newPage;
|
||||||
if (username && password) {
|
if (username && password) {
|
||||||
await page.authenticate({ username, password });
|
await page.authenticate({ username, password });
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
// 模拟人类行为
|
||||||
|
logger.log('Simulating human mouse movements...');
|
||||||
|
await simulateHumanMouseMovement(page);
|
||||||
|
|
||||||
|
logger.log('Simulating human scrolling...');
|
||||||
|
await simulateHumanScrolling(page);
|
||||||
|
|
||||||
await page.waitForNavigation({ waitUntil: 'domcontentloaded' }).catch(() => {});
|
await page.waitForNavigation({ waitUntil: 'domcontentloaded' }).catch(() => {});
|
||||||
|
// 模拟人类行为
|
||||||
|
logger.log('Simulating human mouse movements...');
|
||||||
|
await simulateHumanMouseMovement(page);
|
||||||
|
|
||||||
|
logger.log('Simulating human scrolling...');
|
||||||
|
await simulateHumanScrolling(page);
|
||||||
|
|
||||||
|
|
||||||
// PAUSE 15 SECONDS as requested
|
// PAUSE 15 SECONDS as requested
|
||||||
logger.log('Pausing 15 seconds before looking for "采购专栏"...');
|
logger.log('Pausing 15 seconds before looking for "采购专栏"...');
|
||||||
await new Promise(r => setTimeout(r, 15000));
|
await new Promise(r => setTimeout(r, 15000));
|
||||||
|
await page.screenshot({ path: 'huaneng.png' });
|
||||||
|
|
||||||
logger.log('Looking for "采购专栏" link...');
|
logger.log('Looking for "采购专栏" link...');
|
||||||
await page.waitForFunction(() => {
|
await page.waitForFunction(() => {
|
||||||
@@ -92,6 +156,13 @@ export const ChngCrawler = {
|
|||||||
|
|
||||||
logger.log(`Active URL: ${page.url()}`);
|
logger.log(`Active URL: ${page.url()}`);
|
||||||
|
|
||||||
|
// 模拟人类行为
|
||||||
|
logger.log('Simulating human mouse movements...');
|
||||||
|
await simulateHumanMouseMovement(page);
|
||||||
|
|
||||||
|
logger.log('Simulating human scrolling...');
|
||||||
|
await simulateHumanScrolling(page);
|
||||||
|
|
||||||
while (currentPage <= maxPages) {
|
while (currentPage <= maxPages) {
|
||||||
logger.log(`Processing page ${currentPage}...`);
|
logger.log(`Processing page ${currentPage}...`);
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user