-
npm
npm i puppeteer @hoplin/puppeteer-pool
-
yarn
yarn add puppeteer @hoplin/puppeteer-pool
-
pnpm
pnpm install puppeteer @hoplin/puppeteer-pool
-
PuppeteerPool.start
required parameter as config typetype PuppeteerPoolStartOptions = { /** * Number of concurrency, * Default is 3 */ concurrencyLevel: number; /** * Context mode * Default is ContextMode.SHARED */ contextMode: ContextMode; /** * Puppeteer launch options * Default is {} */ options?: puppeteer.LaunchOptions; /** * Custom config path */ customConfigPath?: string; /** * Enable log * Default is true */ enableLog?: boolean; /** * Log level * Default is LogLevel.DEBUG */ logLevel?: LogLevel; };
-
Remove pino logger dependency and implement custom logger
- You can config
log level
andenable log
inPuppeteerPool.start
function
- You can config
-
Enhanced Concurrency Control
- Detailed Metrics Monitoring
- Monitor metrics by context
- Support to use Playwright instead of Puppeteer
The internal implementation is event-based, which significantly improves the stability. In addition, instead of relying on generic-pools to manage the pool, we have solved the problem of third-party dependency and features that were incompatible with generic-pools through our own pooling. However, there are many API changes and some features are currently disabled. If you update to 2.0.0, please be aware of the migration progress and disabled features for the changes. Also cluster mode client will be provided in near future.
From version 2.0.0, client API will return dispatcher instance after initialization. After that you can use dispatcher to control pool manager.
[ Client API ]
-
PuppeteePool
PuppeteerPool
is singleton class. You can usePuppeteerPool.start
to initialize pool manager.
-
PuppeteerPool.start
-
Static Method
-
Description: Initialize pool manager. You need to call this function to start puppeteer pool. Even if you invoke this function multiple times with differenct arguments, it will return the first initialized instance.
-
Args:
PuppeteerPoolStartOptions
type PuppeteerPoolStartOptions = { /** * Number of concurrency, * Default is 3 */ concurrencyLevel: number; /** * Context mode * Default is ContextMode.SHARED */ contextMode: ContextMode; /** * Puppeteer launch options * Default is {} */ options?: puppeteer.LaunchOptions; /** * Custom config path */ customConfigPath?: string; /** * Enable log * Default is true */ enableLog?: boolean; /** * Log level * Default is LogLevel.DEBUG */ logLevel?: LogLevel; };
-
Return
Promise<PuppeteerPool>
- Returns PuppeteerPool Instance.
-
-
Instance.stop
- Description: Stop pool manager. It will close all sessions and terminate pool manager.
- Return
Promise<void>
-
Instance.runTask
- Description: Run task in pool manager. It will return result of task.
- Args
- task
- Required
- Function
- task
- Return
Promise<any>
- Returns result of task(Same return type with task callback return type)
-
Instance.getPoolMetrics
- Description: Get pool metrics. It will return metrics of pool manager.
- Return
{ memoryUsageValue: (Memory Usage in MegaBytes), memoryUsagePercentage: (Memory Usage with percentage), cpuUsage: (CPU Usage with percentage) }
import { ContextMode, PuppeteerPool } from '@hoplin/puppeteer-pool';
async function main() {
const poolInstance = await PuppeteerPool.start({
concurrencyLevel: 2,
contextMode: ContextMode.ISOLATED,
});
const urls = [
'https://www.google.com',
'https://www.bing.com',
'https://github.com',
];
console.log(await poolInstance.getPoolMetrics());
const promises = urls.map((url) =>
poolInstance.runTask(async (page) => {
await page.goto(url);
return await page.title();
}),
);
const titles = await Promise.all(promises);
titles.forEach((title) => console.log(title));
}
main();
- Pool Managing
- Config
- Support config customize
- Threshold Watcher
- CPU
- Memory
- Support safe pool instance reset in runtime
- Metrics
- Support Metric by pool
- CPU usage of pool
- Memory usage of pool
- Managing session count in runtime
- Support Metric by pool
Default config should be puppeteer-pool-config.json
in root directory path.
If config file are not given or invalid path, manager will use default defined configurations. Or if you want to pass
config path, you can pass path to start()
function as parameter.
{
"session_pool": {
"width": 1080,
"height": 1024
},
"context": {
"timeout": 10
},
"threshold": {
"activate": true,
"interval": 5,
"cpu": 80,
"memory": 2048
}
}
width
: Width of session poolheight
: Height of session pool- Inteager Validation
width
should be larger or equal than 50height
should be larger or equal than 50width
should be integerheight
should be integer
- Inteager Validation
timeout
: Timeout of context.- Inteager Validation
timeout
should be at least 1timeout
should be integer
- Inteager Validation
activate
: Activate threshold watcherinterval
: Interval of threshold watchercpu
: CPU threshold valuememory
: Memory threshold value- Inteager Validation
interval
should be at least 1interval
should be integercpu
should be at least 1cpu
should be integermemory
should be at least 1memory
should be integer
- Inteager Validation