Default Wait-Time Improvements (#162)

- netIdleWait better defaults: if not set, set to 15 seconds for page/page-spa scope, otherwise to 2 seconds
- default behaviors: include autoscroll in default behavior as well
- restart: if crawl already done, don't attempt to crawl further. if 'waitOnDone' set, wait for signal before exiting.
- bump to puppeteer-core 17.1.2
- bump to 0.7.0-beta.4

crawler.js

@@ -492,6 +492,20 @@ class Crawler {
       initState = await this.crawlState.getStatus();
     }
 
+    // if already done, don't crawl anymore
+    if (initState === "done") {
+      this.done = true;
+
+      if (this.params.waitOnDone) {
+        this.statusLog("Already done, waiting for signal to exit...");
+
+        // wait forever until signal
+        await new Promise(() => {});
+      }
+
+      return;
+    }
+
     if (this.params.generateWACZ) {
       this.storage = initStorage();
     }

package.json

@@ -1,6 +1,6 @@
 {
   "name": "browsertrix-crawler",
-  "version": "0.7.0-beta.3",
+  "version": "0.7.0-beta.4",
   "main": "browsertrix-crawler",
   "repository": "https://github.com/webrecorder/browsertrix-crawler",
   "author": "Ilya Kreymer <ikreymer@gmail.com>, Webrecorder Software",
@@ -17,7 +17,7 @@
     "minio": "7.0.26",
     "node-fetch": "^2.6.1",
     "puppeteer-cluster": "github:ikreymer/puppeteer-cluster#async-job-queue",
-    "puppeteer-core": "^16.1.1",
+    "puppeteer-core": "^17.1.2",
     "request": "^2.88.2",
     "sitemapper": "^3.1.2",
     "uuid": "8.3.2",

util/argParser.js

@@ -201,7 +201,7 @@ class ArgParser {
 
       "behaviors": {
         describe: "Which background behaviors to enable on each page",
-        default: "autoplay,autofetch,siteSpecific",
+        default: "autoplay,autofetch,autoscroll,siteSpecific",
         type: "string",
       },
 
@@ -289,9 +289,9 @@ class ArgParser {
       },
 
       "netIdleWait": {
-        describe: "if set, wait for network idle after page load and after behaviors are done (in seconds)",
+        describe: "if set, wait for network idle after page load and after behaviors are done (in seconds). if -1 (default), determine based on scope",
         type: "number",
-        default: 10
+        default: -1
       }
     };
   }
@@ -416,6 +416,15 @@ class ArgParser {
       }
     }
 
+    if (argv.netIdleWait === -1) {
+      if (argv.scopeType === "page" || argv.scopeType === "page-spa") {
+        argv.netIdleWait = 15;
+      } else {
+        argv.netIdleWait = 2;
+      }
+      console.log(`Set netIdleWait to ${argv.netIdleWait} seconds`);
+    }
+
     if (argv.include) {
       if (argv.scopeType && argv.scopeType !== "custom") {
         console.warn("You've specified a --scopeType and a --scopeIncludeRx / --include regex. The custom scope regex will take precedence, overriding the scopeType");

yarn.lock

@@ -1661,10 +1661,10 @@ detect-newline@^3.0.0:
   resolved "https://registry.yarnpkg.com/detect-newline/-/detect-newline-3.1.0.tgz#576f5dfc63ae1a192ff192d8ad3af6308991b651"
   integrity sha512-TLz+x/vEXm/Y7P7wn1EJFNLxYpUD4TgMosxY6fAVJUnJMbupHBOncxyWUG9OpTaH9EBD7uFI5LfEgmMOc54DsA==
 
-devtools-protocol@0.0.1019158:
+devtools-protocol@0.0.1036444:
-  version "0.0.1019158"
+  version "0.0.1036444"
-  resolved "https://registry.yarnpkg.com/devtools-protocol/-/devtools-protocol-0.0.1019158.tgz#4b08d06108a784a2134313149626ba55f030a86f"
+  resolved "https://registry.yarnpkg.com/devtools-protocol/-/devtools-protocol-0.0.1036444.tgz#a570d3cdde61527c82f9b03919847b8ac7b1c2b9"
-  integrity sha512-wvq+KscQ7/6spEV7czhnZc9RM/woz1AY+/Vpd8/h2HFMwJSdTliu7f/yr1A6vDdJfKICZsShqsYpEQbdhg8AFQ==
+  integrity sha512-0y4f/T8H9lsESV9kKP1HDUXgHxCdniFeJh6Erq+FbdOEvp/Ydp9t8kcAAM5gOd17pMrTDlFWntoHtzzeTUWKNw==
 
 diff-sequences@^26.6.2:
   version "26.6.2"
@@ -4151,7 +4151,7 @@ pirates@^4.0.1:
   dependencies:
     node-modules-regexp "^1.0.0"
 
-pkg-dir@4.2.0, pkg-dir@^4.2.0:
+pkg-dir@^4.2.0:
   version "4.2.0"
   resolved "https://registry.yarnpkg.com/pkg-dir/-/pkg-dir-4.2.0.tgz#f099133df7ede422e81d1d8448270eeb3e4261f3"
   integrity sha512-HRDzbaKjC+AOWVXxAU/x54COGeIv9eb+6CkDSQoNTt4XyWoIJvuPsXizxu/Fr23EiekbtZwmh1IcIG/l/a10GQ==
@@ -4246,17 +4246,16 @@ punycode@^2.1.0, punycode@^2.1.1:
   dependencies:
     debug "^4.1.1"
 
-puppeteer-core@^16.1.1:
+puppeteer-core@^17.1.2:
-  version "16.1.1"
+  version "17.1.2"
-  resolved "https://registry.yarnpkg.com/puppeteer-core/-/puppeteer-core-16.1.1.tgz#2c26c560934a1c524a767c9ec0818520b7adb22a"
+  resolved "https://registry.yarnpkg.com/puppeteer-core/-/puppeteer-core-17.1.2.tgz#fdf109fa2d805fdb007b5abfc83728c545ac9ac0"
-  integrity sha512-ls+A6t+cbeNtsNIEyWkGoVJRHseEvBhS3NlI2DBFaJNBUG6kUfmAVyColu1ubgy4VuWLKpGUcwrPTVIvNd1Dew==
+  integrity sha512-mUndfkp581aFC9Tj0NQzoQ4kBEiYszvubkAovAfA72cO2VgiAnk4RTeQhgPekdL50+7bvU1JZp+10y2xOBOy0g==
   dependencies:
     cross-fetch "3.1.5"
     debug "4.3.4"
-    devtools-protocol "0.0.1019158"
+    devtools-protocol "0.0.1036444"
     extract-zip "2.0.1"
     https-proxy-agent "5.0.1"
-    pkg-dir "4.2.0"
     progress "2.0.3"
     proxy-from-env "1.1.0"
     rimraf "3.0.2"