2022-12-21 12:06:13 -05:00
|
|
|
#!/usr/bin/env -S node --experimental-global-webcrypto
|
2020-11-01 19:22:53 -08:00
|
|
|
|
2022-10-24 15:30:10 +02:00
|
|
|
import { Crawler } from "./crawler.js";
|
2022-12-15 12:38:41 -05:00
|
|
|
import { Logger } from "./util/logger.js";
|
|
|
|
|
|
|
|
const logger = new Logger();
|
2022-10-24 15:30:10 +02:00
|
|
|
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
var crawler = null;
|
|
|
|
|
|
|
|
var lastSigInt = 0;
|
|
|
|
let forceTerm = false;
|
|
|
|
|
|
|
|
|
2022-09-20 17:09:52 -07:00
|
|
|
async function handleTerminate(signame) {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.info(`${signame} received...`);
|
2022-02-20 22:22:19 -08:00
|
|
|
if (!crawler || !crawler.crawlState) {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.error("error: no crawler running, exiting");
|
2022-09-20 17:09:52 -07:00
|
|
|
process.exit(1);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (crawler.done) {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.info("success: crawler done, exiting");
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
process.exit(0);
|
|
|
|
}
|
|
|
|
|
|
|
|
try {
|
Dev 0.9.0 Beta 1 Work - Playwright Removal + Worker Refactor + Redis State (#253)
* Migrate from Puppeteer to Playwright!
- use playwright persistent browser context to support profiles
- move on-new-page setup actions to worker
- fix screencaster, init only one per page object, associate with worker-id
- fix device emulation: load on startup, also replace '-' with space for more friendly command-line usage
- port additional chromium setup options
- create / detach cdp per page for each new page, screencaster just uses existing cdp
- fix evaluateWithCLI to call CDP command directly
- workers directly during WorkerPool - await not necessary
* State / Worker Refactor (#252)
* refactoring state:
- use RedisCrawlState, defaulting to local redis, remove MemoryCrawlState and BaseState
- remove 'real' accessors / draining queue - no longer neede without puppeteer-cluster
- switch to sorted set for crawl queue, set depth + extraHops as score, (fixes #150)
- override console.error to avoid logging ioredis errors (fixes #244)
- add MAX_DEPTH as const for extraHops
- fix immediate exit on second interrupt
* worker/state refactor:
- remove job object from puppeteer-cluster
- rename shift() -> nextFromQueue()
- condense crawl mgmt logic to crawlPageInWorker: init page, mark pages as finished/failed, close page on failure, etc...
- screencaster: don't screencast about:blank pages
* more worker queue refactor:
- remove p-queue
- initialize PageWorkers which run in its own loop to process pages, until no pending pages, no queued pages
- add setupPage(), teardownPage() to crawler, called from worker
- await runWorkers() promise which runs all workers until completion
- remove: p-queue, node-fetch, update README (no longer using any puppeteer-cluster base code)
- bump to 0.9.0-beta.1
* use existing data object for per-page context, instead of adding things to page (will be more clear with typescript transition)
* more fixes for playwright:
- fix profile creation
- browser: add newWindowPageWithCDP() to create new page + cdp in new window, use with timeout
- crawler: various fixes, including for html check
- logging: addition logging for screencaster, new window, etc...
- remove unused packages
---------
Co-authored-by: Tessa Walsh <tessa@bitarchivist.net>
2023-03-17 12:50:32 -07:00
|
|
|
if (!crawler.interrupted) {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.info("SIGNAL: gracefully finishing current pages...");
|
2022-09-20 17:09:52 -07:00
|
|
|
crawler.gracefulFinish();
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
|
2022-09-20 17:09:52 -07:00
|
|
|
} else if (forceTerm || (Date.now() - lastSigInt) > 200) {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.info("SIGNAL: stopping crawl now...");
|
2022-09-20 17:09:52 -07:00
|
|
|
await crawler.serializeAndExit();
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
}
|
|
|
|
lastSigInt = Date.now();
|
|
|
|
} catch (e) {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.error("Error stopping crawl after receiving termination signal", e);
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2022-09-20 17:09:52 -07:00
|
|
|
process.on("SIGINT", () => handleTerminate("SIGINT"));
|
|
|
|
|
|
|
|
process.on("SIGTERM", () => handleTerminate("SIGTERM"));
|
|
|
|
|
|
|
|
process.on("SIGABRT", async () => {
|
2022-12-15 12:38:41 -05:00
|
|
|
logger.info("SIGABRT received, will force immediate exit on SIGTERM/SIGINT");
|
2022-09-20 17:09:52 -07:00
|
|
|
forceTerm = true;
|
2020-11-02 15:28:19 +00:00
|
|
|
});
|
|
|
|
|
0.6.0 Wait State + Screencasting Fixes (#141)
* new options:
- to support browsertrix-cloud, add a --waitOnDone option, which has browsertrix crawler wait when finished
- when running with redis shared state, set the `<crawl id>:status` field to `running`, `failing`, `failed` or `done` to let job controller know crawl is finished.
- set redis state to `failing` in case of exception, set to `failed` in case of >3 or more failed exits within 60 seconds (todo: make customizable)
- when receiving a SIGUSR1, assume final shutdown and finalize files (eg. save WACZ) before exiting.
- also write WACZ if exiting due to size limit exceed, but not do to other interruptions
- change sleep() to be in seconds
* misc fixes:
- crawlstate.finished() -> isFinished() - return if >0 pages and none left in queue
- don't fail crawl if isFinished() is true
- don't keep looping in pending wait for urls to finish if received abort request
* screencast improvements (fix related to webrecorder/browsertrix-cloud#233)
- more optimized screencasting, don't close and restart after every page.
- don't assume targets change after every page, they don't in window mode!
- only send 'close' message when target is actually closed
* bump to 0.6.0
2022-06-17 11:58:44 -07:00
|
|
|
process.on("SIGUSR1", () => {
|
|
|
|
if (crawler) {
|
2022-09-20 17:09:52 -07:00
|
|
|
crawler.prepareForExit(true);
|
0.6.0 Wait State + Screencasting Fixes (#141)
* new options:
- to support browsertrix-cloud, add a --waitOnDone option, which has browsertrix crawler wait when finished
- when running with redis shared state, set the `<crawl id>:status` field to `running`, `failing`, `failed` or `done` to let job controller know crawl is finished.
- set redis state to `failing` in case of exception, set to `failed` in case of >3 or more failed exits within 60 seconds (todo: make customizable)
- when receiving a SIGUSR1, assume final shutdown and finalize files (eg. save WACZ) before exiting.
- also write WACZ if exiting due to size limit exceed, but not do to other interruptions
- change sleep() to be in seconds
* misc fixes:
- crawlstate.finished() -> isFinished() - return if >0 pages and none left in queue
- don't fail crawl if isFinished() is true
- don't keep looping in pending wait for urls to finish if received abort request
* screencast improvements (fix related to webrecorder/browsertrix-cloud#233)
- more optimized screencasting, don't close and restart after every page.
- don't assume targets change after every page, they don't in window mode!
- only send 'close' message when target is actually closed
* bump to 0.6.0
2022-06-17 11:58:44 -07:00
|
|
|
}
|
|
|
|
});
|
|
|
|
|
2022-09-20 17:09:52 -07:00
|
|
|
process.on("SIGUSR2", () => {
|
|
|
|
if (crawler) {
|
|
|
|
crawler.prepareForExit(false);
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
}
|
2020-11-02 15:28:19 +00:00
|
|
|
});
|
|
|
|
|
State Save + Restore State from Config + Redis State + Scope Fix 0.5.0 (#78)
* save state work:
- support interrupting and saving crawl
- support loading crawl state (frontier queue, pending, done) from YAML
- support scope check when loading to apply new scoping rules when restarting crawl
- failed urls added to done as failed, can be retried if crawl is stopped and restarted
- save state to crawls/crawl-<ts>-<id>.yaml when interrupted
- --saveState option controls when crawl state is saved, default to partial/when interrupted, also always, never.
- support in-memory or redis based crawl state, using fork of puppeteer-cluster
- --redisStore used to enable redis-based state
* signals/crawl interruption:
- crawl state set to drain/not provide any more urls to crawl
- graceful stop of crawl in response to sigint/sigterm
- initial sigint/sigterm waits for graceful end of current pages, second terminates immediately
- initial sigabrt followed by sigterm terminates immediately
- puppeteer disable handleSIGTERM, handleSIGHUP, handleSIGINT
* redis state support:
- use lua scripts for atomic move from queue -> pending, and pending -> done
- pending key expiry set to page timeout
- add numPending() and numSeen() to support better puppeteer-cluster semantics for early termination
- drainMax returns the numPending() + numSeen() to work with cluster stats
* arg improvements:
- add --crawlId param, also settable via CRAWL_ID env var, defaulting to os.hostname() (used for redis key and crawl state file)
- support setting cmdline args via env var CRAWL_ARGS
- use 'choices' in args when possible
* build update:
- switch base browser image to new webrecorder/browsertrix-browser-base, simple image with .deb files only for amd64 and arm64 builds
- use setuptools<58.0
* misc crawl/scoping rule fixes:
- scoping rules fix when external is used with scopeType
state:
- limit: ensure no urls, including initial seeds, are added past the limit
- signals: fix immediate shutdown on second signal
- tests: add scope test for default scope + excludes
* py-wacz update
- add 'seed': true to pages that are seeds for optimized wacz creation, keeping non-seeds separate (supported via wacz 0.3.2)
- pywb: use latest pywb branch for improved twitter video capture
* update to latest browsertrix-behaviors
* fix setuptools dependency #88
* update README for 0.5.0 beta
2021-09-28 09:41:16 -07:00
|
|
|
crawler = new Crawler();
|
|
|
|
crawler.run();
|
|
|
|
|
2020-11-01 19:22:53 -08:00
|
|
|
|