Compare commits
2 Commits
37e39d35b8
...
a62018a062
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
a62018a062 | ||
|
|
3d3b9b5dfa |
30
.vscode/launch.json
vendored
Normal file
30
.vscode/launch.json
vendored
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
// 使用 IntelliSense 了解相关属性。
|
||||
// 悬停以查看现有属性的描述。
|
||||
// 欲了解更多信息,请访问: https://go.microsoft.com/fwlink/?linkid=830387
|
||||
"version": "0.2.0",
|
||||
"configurations": [
|
||||
|
||||
{
|
||||
"type": "node",
|
||||
"request": "launch",
|
||||
"name": "同步数据库",
|
||||
"cwd": "${workspaceFolder}\\server",
|
||||
"skipFiles": [
|
||||
"<node_internals>/**"
|
||||
],
|
||||
"program": "${workspaceFolder}\\server\\scripts\\db_sync.js"
|
||||
},
|
||||
{
|
||||
"type": "node",
|
||||
"request": "launch",
|
||||
"name": "启动服务",
|
||||
"skipFiles": [
|
||||
"<node_internals>/**"
|
||||
],
|
||||
// 工作区根目录
|
||||
"cwd": "${workspaceFolder}\\server",
|
||||
"program": "${workspaceFolder}\\server\\app.js"
|
||||
}
|
||||
]
|
||||
}
|
||||
6
1.md
6
1.md
@@ -37,4 +37,8 @@
|
||||
3. 预期成果 (Outcome)
|
||||
- 可视化看板: 每天自动推送一份“户外品类异动日报”。
|
||||
- 爆款预警: 当监测到“防水包”类目下某新品 3 天内排名上升超过 50% 时,系统触发钉钉/邮件预警。
|
||||
- 决策支持: 提供该款产品的“避坑指南”(基于竞品售后差评分析)。
|
||||
- 决策支持: 提供该款产品的“避坑指南”(基于竞品售后差评分析)。
|
||||
|
||||
|
||||
|
||||
"C:\Program Files\Google\Chrome\Application\chrome.exe" --disable-features=ExtensionManifestV2Unsupported,ExtensionManifestV2Disabled
|
||||
@@ -1,15 +0,0 @@
|
||||
# MySQL
|
||||
MYSQL_HOST=127.0.0.1
|
||||
MYSQL_PORT=3306
|
||||
MYSQL_USER=root
|
||||
MYSQL_PASSWORD=
|
||||
MYSQL_DATABASE=ecom_crawl
|
||||
|
||||
# 扩展目录(未打包,含 manifest.json)
|
||||
CRX_SRC_PATH=d:/项目/电商抓取项目/mv2_simple_crx/src
|
||||
|
||||
SERVER_PORT=38080
|
||||
ACTION_TIMEOUT_MS=300000
|
||||
PUPPETEER_HEADLESS=false
|
||||
# 可选:指定浏览器路径(不填默认用 ../chrome-win/chrome.exe)
|
||||
CHROME_EXECUTABLE_PATH=
|
||||
@@ -1,4 +1,4 @@
|
||||
import dotenv from 'dotenv';
|
||||
import { get_app_config } from './config/app_config.js';
|
||||
import Koa from 'koa';
|
||||
import body_parser from 'koa-bodyparser';
|
||||
|
||||
@@ -6,8 +6,6 @@ import { sequelize } from './models/index.js';
|
||||
import { crawl_router } from './routes/crawl.js';
|
||||
import { start_all_cron_tasks } from './services/schedule_loader.js';
|
||||
|
||||
dotenv.config();
|
||||
|
||||
const app = new Koa();
|
||||
app.use(body_parser({ jsonLimit: '10mb' }));
|
||||
|
||||
@@ -18,10 +16,11 @@ app.use(async (ctx) => {
|
||||
ctx.body = { ok: false, error: 'not_found' };
|
||||
});
|
||||
|
||||
const port = Number(process.env.SERVER_PORT || 38080);
|
||||
const cfg = get_app_config();
|
||||
const port = cfg.server.port;
|
||||
|
||||
await sequelize.authenticate();
|
||||
await sequelize.sync();
|
||||
// await sequelize.sync();
|
||||
start_all_cron_tasks();
|
||||
|
||||
app.listen(port);
|
||||
|
||||
64
server/config/app_config.js
Normal file
64
server/config/app_config.js
Normal file
@@ -0,0 +1,64 @@
|
||||
import path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
import { get_env } from './env.js';
|
||||
|
||||
function must_get(key) {
|
||||
const v = get_env(key);
|
||||
if (v === undefined || v === null || v === '') {
|
||||
throw new Error(`缺少配置 ${key}`);
|
||||
}
|
||||
return v;
|
||||
}
|
||||
|
||||
function get_bool(key, default_value) {
|
||||
const v = get_env(key);
|
||||
if (v === undefined || v === null || v === '') {
|
||||
return default_value;
|
||||
}
|
||||
return String(v).toLowerCase() === 'true';
|
||||
}
|
||||
|
||||
function get_int(key, default_value) {
|
||||
const v = get_env(key);
|
||||
if (v === undefined || v === null || v === '') {
|
||||
return default_value;
|
||||
}
|
||||
const n = Number(v);
|
||||
if (Number.isNaN(n)) {
|
||||
throw new Error(`配置 ${key} 必须是数字`);
|
||||
}
|
||||
return n;
|
||||
}
|
||||
|
||||
let cached = null;
|
||||
|
||||
export function get_app_config() {
|
||||
if (cached) {
|
||||
return cached;
|
||||
}
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = path.dirname(__filename);
|
||||
|
||||
cached = {
|
||||
mysql: {
|
||||
host: must_get('MYSQL_HOST'),
|
||||
port: get_int('MYSQL_PORT', 3306),
|
||||
user: must_get('MYSQL_USER'),
|
||||
password: must_get('MYSQL_PASSWORD'),
|
||||
database: must_get('MYSQL_DATABASE')
|
||||
},
|
||||
server: {
|
||||
port: get_int('SERVER_PORT', 38080)
|
||||
},
|
||||
crawler: {
|
||||
crx_src_path: must_get('CRX_SRC_PATH'),
|
||||
action_timeout_ms: get_int('ACTION_TIMEOUT_MS', 300000),
|
||||
puppeteer_headless: get_bool('PUPPETEER_HEADLESS', false),
|
||||
chrome_executable_path: (get_env('CHROME_EXECUTABLE_PATH') || '').trim() || path.resolve(__dirname, '../../chrome-win/chrome.exe'),
|
||||
log_invoke_action: get_bool('LOG_INVOKE_ACTION', true)
|
||||
}
|
||||
};
|
||||
|
||||
return cached;
|
||||
}
|
||||
@@ -5,10 +5,10 @@
|
||||
|
||||
export const cron_task_list = [
|
||||
// 示例:每 6 小时跑一次列表抓取
|
||||
// {
|
||||
// name: 'amazon_search_list_every_6h',
|
||||
// cron_expression: '0 */6 * * *',
|
||||
// action_name: 'amazon_search_list',
|
||||
// action_payload: { keyword: '午餐包', limit: 100 }
|
||||
// }
|
||||
{
|
||||
name: 'amazon_search_list_every_6h',
|
||||
cron_expression: '0 */1 * * *',
|
||||
action_name: 'amazon_search_list',
|
||||
action_payload: { keyword: '野餐包', limit: 100 }
|
||||
}
|
||||
];
|
||||
|
||||
@@ -1,14 +1,15 @@
|
||||
import dotenv from 'dotenv';
|
||||
|
||||
dotenv.config();
|
||||
import { get_app_config } from './app_config.js';
|
||||
|
||||
export function get_sequelize_options() {
|
||||
const cfg = get_app_config();
|
||||
console.log( 'get_sequelize_options', cfg.mysql );
|
||||
|
||||
return {
|
||||
host: process.env.MYSQL_HOST || '127.0.0.1',
|
||||
port: Number(process.env.MYSQL_PORT || 3306),
|
||||
username: process.env.MYSQL_USER || 'root',
|
||||
password: process.env.MYSQL_PASSWORD || '',
|
||||
database: process.env.MYSQL_DATABASE || 'ecom_crawl',
|
||||
host: cfg.mysql.host,
|
||||
port: cfg.mysql.port,
|
||||
username: cfg.mysql.user,
|
||||
password: cfg.mysql.password,
|
||||
database: cfg.mysql.database,
|
||||
dialect: 'mysql',
|
||||
logging: false,
|
||||
define: {
|
||||
|
||||
74
server/config/env.js
Normal file
74
server/config/env.js
Normal file
@@ -0,0 +1,74 @@
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import { fileURLToPath } from 'node:url';
|
||||
|
||||
let loaded = false;
|
||||
let env_map = {};
|
||||
|
||||
function unquote(value) {
|
||||
const v = String(value);
|
||||
if ((v.startsWith('"') && v.endsWith('"')) || (v.startsWith("'") && v.endsWith("'"))) {
|
||||
return v.slice(1, -1);
|
||||
}
|
||||
return v;
|
||||
}
|
||||
|
||||
function parse_env_text(text) {
|
||||
const out = {};
|
||||
const lines = String(text).split(/\r?\n/);
|
||||
|
||||
for (const raw_line of lines) {
|
||||
const line = raw_line.trim();
|
||||
if (!line) continue;
|
||||
if (line.startsWith('#')) continue;
|
||||
|
||||
const idx = line.indexOf('=');
|
||||
if (idx <= 0) continue;
|
||||
|
||||
const key = line.slice(0, idx).trim();
|
||||
let value = line.slice(idx + 1).trim();
|
||||
|
||||
// 去掉行尾注释:仅在未被引号包裹时生效
|
||||
const quoted = (value.startsWith('"') && value.endsWith('"')) || (value.startsWith("'") && value.endsWith("'"));
|
||||
if (!quoted) {
|
||||
const sharp = value.indexOf('#');
|
||||
if (sharp >= 0) {
|
||||
value = value.slice(0, sharp).trim();
|
||||
}
|
||||
}
|
||||
|
||||
out[key] = unquote(value);
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
export function load_env() {
|
||||
if (loaded) {
|
||||
return;
|
||||
}
|
||||
|
||||
const __filename = fileURLToPath(import.meta.url);
|
||||
const __dirname = path.dirname(__filename);
|
||||
const env_path = path.resolve(__dirname, '../.env');
|
||||
|
||||
const text = fs.readFileSync(env_path, 'utf8');
|
||||
env_map = parse_env_text(text);
|
||||
loaded = true;
|
||||
}
|
||||
|
||||
export function get_env(key) {
|
||||
if (!loaded) {
|
||||
load_env();
|
||||
}
|
||||
return env_map[key];
|
||||
}
|
||||
|
||||
export function get_all_env() {
|
||||
if (!loaded) {
|
||||
load_env();
|
||||
}
|
||||
return { ...env_map };
|
||||
}
|
||||
|
||||
load_env();
|
||||
@@ -1 +0,0 @@
|
||||
// 已废弃:按需求改为写死定时任务(见 config/cron_tasks.js)
|
||||
13
server/package-lock.json
generated
13
server/package-lock.json
generated
@@ -9,7 +9,6 @@
|
||||
"version": "1.0.0",
|
||||
"dependencies": {
|
||||
"@koa/router": "^12.0.1",
|
||||
"dotenv": "^16.4.5",
|
||||
"koa": "^2.15.3",
|
||||
"koa-bodyparser": "^4.4.1",
|
||||
"mysql2": "^3.11.0",
|
||||
@@ -650,18 +649,6 @@
|
||||
"integrity": "sha512-XxtPuC3PGakY6PD7dG66/o8KwJ/LkH2/EKe19Dcw58w53dv4/vSQEkn/SzuyhHE2q4zPgCkxQBxus3VV4ql+Pg==",
|
||||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/dotenv": {
|
||||
"version": "16.6.1",
|
||||
"resolved": "https://registry.npmmirror.com/dotenv/-/dotenv-16.6.1.tgz",
|
||||
"integrity": "sha512-uBq4egWHTcTt33a72vpSG0z3HnPuIl6NqYcTrKEg2azoEyl2hpW0zqlxysq2pK9HlDIHyHyakeYaYnSAwd8bow==",
|
||||
"license": "BSD-2-Clause",
|
||||
"engines": {
|
||||
"node": ">=12"
|
||||
},
|
||||
"funding": {
|
||||
"url": "https://dotenvx.com"
|
||||
}
|
||||
},
|
||||
"node_modules/dottie": {
|
||||
"version": "2.0.7",
|
||||
"resolved": "https://registry.npmmirror.com/dottie/-/dottie-2.0.7.tgz",
|
||||
|
||||
@@ -9,7 +9,6 @@
|
||||
},
|
||||
"dependencies": {
|
||||
"@koa/router": "^12.0.1",
|
||||
"dotenv": "^16.4.5",
|
||||
"koa": "^2.15.3",
|
||||
"koa-bodyparser": "^4.4.1",
|
||||
"mysql2": "^3.11.0",
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
// 已废弃:按需求改为写死定时任务(见 config/cron_tasks.js)
|
||||
@@ -1 +0,0 @@
|
||||
// 已废弃:按需求改为写死定时任务(见 config/cron_tasks.js)
|
||||
@@ -1,22 +1,18 @@
|
||||
import dotenv from 'dotenv';
|
||||
import fs from 'node:fs';
|
||||
import path from 'node:path';
|
||||
import puppeteer from 'puppeteer';
|
||||
|
||||
dotenv.config();
|
||||
import { get_app_config } from '../config/app_config.js';
|
||||
|
||||
let browser_singleton = null;
|
||||
|
||||
function get_action_timeout_ms() {
|
||||
return Number(process.env.ACTION_TIMEOUT_MS || 300000);
|
||||
const cfg = get_app_config();
|
||||
return cfg.crawler.action_timeout_ms;
|
||||
}
|
||||
|
||||
function get_crx_src_path() {
|
||||
const crx_src_path = process.env.CRX_SRC_PATH;
|
||||
if (!crx_src_path) {
|
||||
throw new Error('缺少环境变量 CRX_SRC_PATH');
|
||||
}
|
||||
return crx_src_path;
|
||||
const cfg = get_app_config();
|
||||
return cfg.crawler.crx_src_path;
|
||||
}
|
||||
|
||||
function get_extension_id_from_targets(targets) {
|
||||
@@ -52,15 +48,8 @@ async function wait_for_extension_id(browser, timeout_ms) {
|
||||
}
|
||||
|
||||
function get_chrome_executable_path() {
|
||||
// 优先环境变量,方便你后续切换版本
|
||||
const from_env = process.env.CHROME_EXECUTABLE_PATH;
|
||||
if (from_env) {
|
||||
return path.resolve(from_env);
|
||||
}
|
||||
|
||||
// 默认使用项目根目录的 chrome-win/chrome.exe
|
||||
// 当前进程 cwd 通常是 server/,所以回到上一级
|
||||
return path.resolve(process.cwd(), '../chrome-win/chrome.exe');
|
||||
const cfg = get_app_config();
|
||||
return path.resolve(cfg.crawler.chrome_executable_path);
|
||||
}
|
||||
|
||||
export async function get_or_create_browser() {
|
||||
@@ -79,8 +68,9 @@ export async function get_or_create_browser() {
|
||||
throw new Error(`扩展 manifest.json 不存在: ${manifest_path}`);
|
||||
}
|
||||
|
||||
const cfg = get_app_config();
|
||||
const extension_path = raw_extension_path.replace(/\\/g, '/');
|
||||
const headless = String(process.env.PUPPETEER_HEADLESS || 'false') === 'true';
|
||||
const headless = cfg.crawler.puppeteer_headless;
|
||||
const user_data_dir = path.resolve(process.cwd(), 'puppeteer_profile');
|
||||
|
||||
browser_singleton = await puppeteer.launch({
|
||||
|
||||
@@ -4,9 +4,9 @@ import { execute_action_and_record } from './task_executor.js';
|
||||
|
||||
const cron_jobs = [];
|
||||
|
||||
export function start_all_cron_tasks() {
|
||||
export async function start_all_cron_tasks() {
|
||||
for (const task of cron_task_list) {
|
||||
const job = cron.schedule(task.cron_expression, async () => {
|
||||
// const job = cron.schedule(task.cron_expression, async () => {
|
||||
try {
|
||||
await execute_action_and_record({
|
||||
action_name: task.action_name,
|
||||
@@ -16,9 +16,9 @@ export function start_all_cron_tasks() {
|
||||
} catch (err) {
|
||||
// 失败会在 crawl_run_record 落库
|
||||
}
|
||||
});
|
||||
// });
|
||||
|
||||
cron_jobs.push(job);
|
||||
// cron_jobs.push(job);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -13,15 +13,18 @@ export async function execute_action_and_record(params) {
|
||||
let error_message = null;
|
||||
|
||||
try {
|
||||
const result = await invoke_extension_action(action_name, action_payload || {});
|
||||
|
||||
|
||||
console.log( 'invoke_extension_action-start', action_name, action_payload );
|
||||
const res_invoke = await invoke_extension_action(action_name, action_payload || {});
|
||||
console.log( 'invoke_extension_action-end', action_name, result );
|
||||
ok = true;
|
||||
result_payload = safe_json_stringify(result);
|
||||
result_payload = safe_json_stringify(res_invoke);
|
||||
|
||||
// 按 stage 自动入库(不影响原始 run_record 记录)
|
||||
await persist_amazon_result(result);
|
||||
await persist_amazon_result(res_invoke.result);
|
||||
|
||||
return result;
|
||||
return res_invoke;
|
||||
} catch (err) {
|
||||
ok = false;
|
||||
error_message = (err && err.message) || String(err);
|
||||
|
||||
Reference in New Issue
Block a user