html-snapshots 5.11.0 → 6.0.0

package/lib/phantom/modules/selectorDetect.js

@@ -1,108 +0,0 @@
-/*
- * selectorDetect.js
- *
- * Produce a single snapshot for a web page when a given selector is detected.
- *
- * This is a module for a phantomJS script that runs in phantomjs.
- *
- * Copyright (c) 2013 - 2025 Alex Grant, LocalNerve, contributors
- * Licensed under the MIT license.
- */
-
-// Get the start time immediately since we're already in a PhantomJS process instance
-// The spawner is already counting down (with allowances)...
-var start = new Date().getTime();
-
-/**
- * Dependencies, phantomjs
- */
-var page = require("webpage").create();
-var fs = require("fs");
-var globals = require("./globals");
-var verbose = require("./verbose");
-
-/**
- * waitFor
- *
- * Heavily borrowed from phantomJS 'waitFor' example
- */
-function waitFor (testFx, onReady, onTimeout, timeout, checkInterval) {
-  var condition = false,
-  interval = setInterval(function () {
-    if ( (new Date().getTime() - start < timeout) && !condition ) {
-      // If not timeout yet and condition not yet fulfilled
-      condition = testFx();
-    } else {
-      clearInterval(interval); // Stop this interval
-      if ( !condition ) {
-        // If condition still not fulfilled (timeout but condition is 'false')
-        onTimeout();
-      } else {
-        // Condition fulfilled (timeout and/or condition is 'true')
-        onReady((new Date().getTime() - start));
-      }
-    }
-  }, checkInterval);
-}
-
-/**
- * snapshot
- *
- * Opens the page and waits for the selector to become visible. Then takes the html snapshot.
- * Applies an optional output filter to the html content.
- *
- */
-function snapshot (options, detector, filter) {
-  filter = filter || function(content) { return content; };
-
-  console.log("Creating snapshot for "+options.url+"...");
-
-  // https://github.com/ariya/phantomjs/issues/10930
-  page.customHeaders = {
-    "Accept-Encoding": "identity"
-  };
-
-  // add optional verbose output
-  if (options.verbose) {
-    verbose(page);
-  }
-
-  // create the snapshot
-  page.open(options.url, {
-    resourceTimeout: options.timeout - 300 // a little space to report problems.
-  }, function (status) {
-    if (status !== "success") {
-      // if phantomJS could not load the page, so end right now
-      globals.exit(2, "Unable to load page " + options.url);
-    } else {
-      // phantomJS loaded the page, so wait for it to be ready
-      waitFor(
-
-        // The test to determine readiness
-        function () {
-          return page.evaluate(detector, {
-            selector: options.selector,
-            url: options.url
-          });
-        },
-
-        // The onReady callback
-        function (time) {
-          fs.write(options.outputFile, filter(page.content), "w");
-          globals.exit(0, "snapshot for "+options.url+" finished in "+time+" ms\n  written to "+options.outputFile);
-        },
-
-        // The onTimeout callback
-        function () {
-          globals.exit(1, "timed out waiting for "+options.selector+" to become visible for "+options.url);
-        },
-
-        options.timeout,
-        options.checkInterval
-
-      );
-    }
-  });
-}
-
-module.exports = snapshot;

package/lib/phantom/modules/verbose.js

@@ -1,71 +0,0 @@
-/*
- * verbose.js
- *
- * Adds handlers to WebPage module to produce additional output for debugging.
- *
- * This is a module for a phantomJS script that runs in phantomjs.
- *
- * Copyright (c) 2013 - 2025 Alex Grant, LocalNerve, contributors
- * Licensed under the MIT license.
- */
-/* global window */
-var system = require("system");
-
-/**
- * Decorate the given WebPage with handlers to produce verbose output.
- * Source:
- * https://newspaint.wordpress.com/2013/04/25/getting-to-the-bottom-of-why-a-phantomjs-page-load-fails/
- */
-function verbose (page) {
-
-  page.onResourceError = function(resourceError) {
-      system.stderr.writeLine('= onResourceError()');
-      system.stderr.writeLine('  - unable to load url: "' + resourceError.url + '"');
-      system.stderr.writeLine('  - error code: ' + resourceError.errorCode + ', description: ' + resourceError.errorString );
-  };
-
-  page.onError = function(msg, trace) {
-      system.stderr.writeLine('= onError()');
-      var msgStack = ['  ERROR: ' + msg];
-      if (trace) {
-          msgStack.push('  TRACE:');
-          trace.forEach(function(t) {
-              msgStack.push('    -> ' + t.file + ': ' + t.line + (t.function ? ' (in function "' + t.function + '")' : ''));
-          });
-      }
-      system.stderr.writeLine(msgStack.join('\n'));
-  };
-
-  page.onResourceRequested = function (request) {
-      system.stderr.writeLine('= onResourceRequested()');
-      system.stderr.writeLine('  request: ' + JSON.stringify(request, undefined, 4));
-  };
-
-  page.onResourceReceived = function(response) {
-      system.stderr.writeLine('= onResourceReceived()' );
-      system.stderr.writeLine('  id: ' + response.id + ', stage: "' + response.stage + '", response: ' + JSON.stringify(response));
-  };
-
-  page.onLoadStarted = function() {
-      system.stderr.writeLine('= onLoadStarted()');
-      var currentUrl = page.evaluate(function() {
-          return window.location.href;
-      });
-      system.stderr.writeLine('  leaving url: ' + currentUrl);
-  };
-
-  page.onNavigationRequested = function(url, type, willNavigate, main) {
-      system.stderr.writeLine('= onNavigationRequested');
-      system.stderr.writeLine('  destination_url: ' + url);
-      system.stderr.writeLine('  type (cause): ' + type);
-      system.stderr.writeLine('  will navigate: ' + willNavigate);
-      system.stderr.writeLine('  from page\'s main frame: ' + main);
-  };
-
-  page.onLoadFinished = function(status) {
-      system.stderr.writeLine('= onLoadFinished()');
-      system.stderr.writeLine('  status: ' + status);
-  };
-}
-
-module.exports = verbose;

package/lib/phantom/removeScripts.js

@@ -1,30 +0,0 @@
-/*
- * removeScripts.js
- *
- * Produce a single snapshot for a web page.
- * Snapshot taken when selector is(:visible).
- * Applies a single filter to remove any script tags.
- *
- * This is a phantomJS script that runs in phantomjs.
- *
- * Copyright (c) 2013 - 2025 Alex Grant, LocalNerve, contributors
- * Licensed under the MIT license.
- */
-var selectorDetect = require("./modules/selectorDetect");
-var cli = require("./modules/cli");
-var detectors = require("./modules/detectors");
-
-/**
- * Remove all script tags from content
- */
-function removeScriptTags(content) {
-  return content.replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, "");
-}
-
-var options = cli.selector();
-
-selectorDetect(
-  options,
-  options.useJQuery ? detectors.jquerySelector : detectors.querySelector,
-  removeScriptTags
-);