.eslintrc.json

.idea
apify_storage
node_modules
.nyc_output
coverage
src/page_function.js
.DS_Store


.gitignore

FROM apify/actor-node-chrome-xvfb

COPY package.json package-lock.json ./

# Install default dependencies, print versions of everything
RUN npm --quiet set progress=false \
 && npm install --only=prod --no-optional \
 && echo "Installed NPM packages:" \
 && npm list || true \
 && echo "Node.js version:" \
 && node --version \
 && echo "NPM version:" \
 && npm --version

COPY . ./


Dockerfile

Use the following form to configure Web Scraper. The Start URLs and Page function are required and all other fields are optional. If you want to use Pseudo URLs, you also need to Use request queue. To learn more about the different options, click on their title or on the nearby question marks. For details about the Page function visit the actor's README in the ACTOR INFO tab. We also have a <a href="https://apify.com/docs/scraping/tutorial/introduction" target="_blank">step by step tutorial</a> to help you with the basics.

If you get stuck and it seems that you can no longer progress with the Web Scraper, try <a href="https://apify.com/docs/scraping/tutorial/puppeteer-scraper" target="_blank">Puppeteer Scraper</a>. It's a more powerful tool.

Console messages from the Browser will be included in the log. This may result in the log being flooded by error messages, warnings and other messages of little value, especially with high concurrency.

Browser log

Experimental implementation of Chrome debugger. In this mode the scraper will run with single browser on concurrency 1. You can place <code>debugger;</code> into your page function to set up a debugger breakpoint.

Chrome debugger [experimental]

This object will be available on pageFunction's context as customData.

Custom data

Debug messages will be included in the log. Use <code>context.log.debug('message')</code> to log your own debug messages.

Debug log

Scraper will download CSS stylesheets. Disabling this may speed up the scrape, but certain websites could stop working correctly.

Download CSS

Scraper will download media such as images, fonts, videos and sounds. Disabling this may speed up the scrape, but certain websites could stop working correctly.

Settings that help to disable downloading web page resources.

Download media

Scraper will ignore CSP (content security policy) and CORS (cross origin resource sharing) settings of visited pages and requested domains. This enables you to freely use XHR/Fetch to make HTTP requests from the scraper.

Ignore CORS and CSP

Scraper will ignore SSL certificate errors.

Various options that help you disable browser security features such as HTTPS certificates and CORS.

Ignore SSL errors

The provided cookies will be pre-set to all pages the scraper opens.

Initial cookies

The jQuery library will be injected into each page. If the page already uses jQuery, conflicts may arise.

Settings that help inject 3rd party libraries into scraper pageFunction.

jQuery

The Underscore.js library will be injected into each page. If the page already uses Underscore.js (or other libraries that attach to '_', such as Lodash), conflicts may arise.

Underscore

URL fragments (the parts of URL after a <code>#</code>) are not considered when the scraper determines whether a URL has already been visited. This means that when adding URLs such as <code>https://example.com/#foo</code> and <code>https://example.com/#bar</code>, only the first will be visited. Turn this option on to tell the scraper to visit both.

Keep URL fragments

CSS selector matching elements with 'href' attributes that should be enqueued. To enqueue urls from <code><div class="my-class" href=...></code> tags, you would enter <strong>div.my-class</strong>. Leave empty to ignore all links.

Link selector

Defines how many pages can be processed by the scraper in parallel. The scraper automatically increases and decreases concurrency based on available system resources. Use this option to set a hard limit.

Max concurrency

Defines how many links away from the StartURLs will the scraper descend. 0 means unlimited.

Max crawling depth

Maximum number of pages that the scraper will open. 0 means unlimited.

Max pages per run

Maximum number of times the request for the page will be retried in case of an error. Setting it to 0 means that the request will be attempted once and will not be retried if it fails.

Max request retries

Maximum number of results that will be saved to dataset. The scraper will terminate afterwards. 0 means unlimited.

Max result records

Page function

Maximum time the scraper will wait for the page function to execute in seconds.

Page function timeout

Maximum time the scraper will allow a web page to load in seconds.

Page load timeout

Choose to use no proxy, Apify Proxy, or provide custom proxy URLs.

Proxy configuration

Pseudo-URLs to match links in the page that you want to enqueue. Combine with Link selector to tell the scraper where to find links. Omitting the Pseudo-URLs will cause the scraper to enqueue all links matched by the Link selector.

Pseudo-URLs

Start URLs

The scraper will use a real Chrome browser instead of a Chromium masking as Chrome. Using this option may help with bypassing certain anti-scraping protections, but risks that the scraper will be unstable or not work at all.

Settings that help mask as a real user and prevent scraper detection, but increase the chances of the scraper not working at all with some websites.

Use Chrome

Request queue enables recursive crawling and the use of Pseudo-URLs, Link selector and <code>context.enqueueRequest()</code>.

Use request queue

The scraper will apply various browser emulation techniques to match a real user as closely as possible. This feature works best in conjunction with the Use Chrome option and also carries the risk of making the scraper unstable.

Use Stealth

The scraper will wait until the selected events are triggered in the page before executing the page function. Available events are <code>domcontentloaded</code>, <code>load</code>, <code>networkidle2</code> and <code>networkidle0</code>. <a href="https://pptr.dev/#?product=Puppeteer&show=api-pagegotourl-options" target="_blank">See Puppeteer docs</a>.

Navigation wait until

Web Scraper Input

INPUT_SCHEMA.json

                                 Apache License
                           Version 2.0, January 2004
                        http://www.apache.org/licenses/

   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION

   1. Definitions.

      "License" shall mean the terms and conditions for use, reproduction,
      and distribution as defined by Sections 1 through 9 of this document.

      "Licensor" shall mean the copyright owner or entity authorized by
      the copyright owner that is granting the License.

      "Legal Entity" shall mean the union of the acting entity and all
      other entities that control, are controlled by, or are under common
      control with that entity. For the purposes of this definition,
      "control" means (i) the power, direct or indirect, to cause the
      direction or management of such entity, whether by contract or
      otherwise, or (ii) ownership of fifty percent (50%) or more of the
      outstanding shares, or (iii) beneficial ownership of such entity.

      "You" (or "Your") shall mean an individual or Legal Entity
      exercising permissions granted by this License.

      "Source" form shall mean the preferred form for making modifications,
      including but not limited to software source code, documentation
      source, and configuration files.

      "Object" form shall mean any form resulting from mechanical
      transformation or translation of a Source form, including but
      not limited to compiled object code, generated documentation,
      and conversions to other media types.

      "Work" shall mean the work of authorship, whether in Source or
      Object form, made available under the License, as indicated by a
      copyright notice that is included in or attached to the work
      (an example is provided in the Appendix below).

      "Derivative Works" shall mean any work, whether in Source or Object
      form, that is based on (or derived from) the Work and for which the
      editorial revisions, annotations, elaborations, or other modifications
      represent, as a whole, an original work of authorship. For the purposes
      of this License, Derivative Works shall not include works that remain
      separable from, or merely link (or bind by name) to the interfaces of,
      the Work and Derivative Works thereof.

      "Contribution" shall mean any work of authorship, including
      the original version of the Work and any modifications or additions
      to that Work or Derivative Works thereof, that is intentionally
      submitted to Licensor for inclusion in the Work by the copyright owner
      or by an individual or Legal Entity authorized to submit on behalf of
      the copyright owner. For the purposes of this definition, "submitted"
      means any form of electronic, verbal, or written communication sent
      to the Licensor or its representatives, including but not limited to
      communication on electronic mailing lists, source code control systems,
      and issue tracking systems that are managed by, or on behalf of, the
      Licensor for the purpose of discussing and improving the Work, but
      excluding communication that is conspicuously marked or otherwise
      designated in writing by the copyright owner as "Not a Contribution."

      "Contributor" shall mean Licensor and any individual or Legal Entity
      on behalf of whom a Contribution has been received by Licensor and
      subsequently incorporated within the Work.

   2. Grant of Copyright License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      copyright license to reproduce, prepare Derivative Works of,
      publicly display, publicly perform, sublicense, and distribute the
      Work and such Derivative Works in Source or Object form.

   3. Grant of Patent License. Subject to the terms and conditions of
      this License, each Contributor hereby grants to You a perpetual,
      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
      (except as stated in this section) patent license to make, have made,
      use, offer to sell, sell, import, and otherwise transfer the Work,
      where such license applies only to those patent claims licensable
      by such Contributor that are necessarily infringed by their
      Contribution(s) alone or by combination of their Contribution(s)
      with the Work to which such Contribution(s) was submitted. If You
      institute patent litigation against any entity (including a
      cross-claim or counterclaim in a lawsuit) alleging that the Work
      or a Contribution incorporated within the Work constitutes direct
      or contributory patent infringement, then any patent licenses
      granted to You under this License for that Work shall terminate
      as of the date such litigation is filed.

   4. Redistribution. You may reproduce and distribute copies of the
      Work or Derivative Works thereof in any medium, with or without
      modifications, and in Source or Object form, provided that You
      meet the following conditions:

      (a) You must give any other recipients of the Work or
          Derivative Works a copy of this License; and

      (b) You must cause any modified files to carry prominent notices
          stating that You changed the files; and

      (c) You must retain, in the Source form of any Derivative Works
          that You distribute, all copyright, patent, trademark, and
          attribution notices from the Source form of the Work,
          excluding those notices that do not pertain to any part of
          the Derivative Works; and

      (d) If the Work includes a "NOTICE" text file as part of its
          distribution, then any Derivative Works that You distribute must
          include a readable copy of the attribution notices contained
          within such NOTICE file, excluding those notices that do not
          pertain to any part of the Derivative Works, in at least one
          of the following places: within a NOTICE text file distributed
          as part of the Derivative Works; within the Source form or
          documentation, if provided along with the Derivative Works; or,
          within a display generated by the Derivative Works, if and
          wherever such third-party notices normally appear. The contents
          of the NOTICE file are for informational purposes only and
          do not modify the License. You may add Your own attribution
          notices within Derivative Works that You distribute, alongside
          or as an addendum to the NOTICE text from the Work, provided
          that such additional attribution notices cannot be construed
          as modifying the License.

      You may add Your own copyright statement to Your modifications and
      may provide additional or different license terms and conditions
      for use, reproduction, or distribution of Your modifications, or
      for any such Derivative Works as a whole, provided Your use,
      reproduction, and distribution of the Work otherwise complies with
      the conditions stated in this License.

   5. Submission of Contributions. Unless You explicitly state otherwise,
      any Contribution intentionally submitted for inclusion in the Work
      by You to the Licensor shall be under the terms and conditions of
      this License, without any additional terms or conditions.
      Notwithstanding the above, nothing herein shall supersede or modify
      the terms of any separate license agreement you may have executed
      with Licensor regarding such Contributions.

   6. Trademarks. This License does not grant permission to use the trade
      names, trademarks, service marks, or product names of the Licensor,
      except as required for reasonable and customary use in describing the
      origin of the Work and reproducing the content of the NOTICE file.

   7. Disclaimer of Warranty. Unless required by applicable law or
      agreed to in writing, Licensor provides the Work (and each
      Contributor provides its Contributions) on an "AS IS" BASIS,
      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
      implied, including, without limitation, any warranties or conditions
      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
      PARTICULAR PURPOSE. You are solely responsible for determining the
      appropriateness of using or redistributing the Work and assume any
      risks associated with Your exercise of permissions under this License.

   8. Limitation of Liability. In no event and under no legal theory,
      whether in tort (including negligence), contract, or otherwise,
      unless required by applicable law (such as deliberate and grossly
      negligent acts) or agreed to in writing, shall any Contributor be
      liable to You for damages, including any direct, indirect, special,
      incidental, or consequential damages of any character arising as a
      result of this License or out of the use or inability to use the
      Work (including but not limited to damages for loss of goodwill,
      work stoppage, computer failure or malfunction, or any and all
      other commercial damages or losses), even if such Contributor
      has been advised of the possibility of such damages.

   9. Accepting Warranty or Additional Liability. While redistributing
      the Work or Derivative Works thereof, You may choose to offer,
      and charge a fee for, acceptance of support, warranty, indemnity,
      or other liability obligations and/or rights consistent with this
      License. However, in accepting such obligations, You may act only
      on Your own behalf and on Your sole responsibility, not on behalf
      of any other Contributor, and only if You agree to indemnify,
      defend, and hold each Contributor harmless for any liability
      incurred by, or claims asserted against, such Contributor by reason
      of your accepting any such warranty or additional liability.

   END OF TERMS AND CONDITIONS

   APPENDIX: How to apply the Apache License to your work.

      To apply the Apache License to your work, attach the following
      boilerplate notice, with the fields enclosed by brackets "[]"
      replaced with your own identifying information. (Don't include
      the brackets!)  The text should be enclosed in the appropriate
      comment syntax for the file format. We also recommend that a
      file or class name and description of purpose be included on the
      same "printed page" as the copyright notice for easier
      identification within third-party archives.

   Copyright [yyyy] [name of copyright owner]

   Licensed under the Apache License, Version 2.0 (the "License");
   you may not use this file except in compliance with the License.
   You may obtain a copy of the License at

       http://www.apache.org/licenses/LICENSE-2.0

   Unless required by applicable law or agreed to in writing, software
   distributed under the License is distributed on an "AS IS" BASIS,
   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
   See the License for the specific language governing permissions and
   limitations under the License.


LICENSE

web-scraper-experimental-debug

apify.json

const { runActor } = require('@apify/scraper-tools');
const CrawlerSetup = require('./src/crawler_setup');

runActor(CrawlerSetup);


main.js

Crawl web pages using Apify, headless Chrome and Puppeteer

actor-web-scraper

package.json

/* istanbul ignore next */
/**
 * Command to be evaluated for Browser side code injection.
 * @param apifyNamespace
 */
module.exports = (apifyNamespace) => {
    (function (global, namespace) {
        if (typeof window[namespace] !== 'object') window[namespace] = {};
        /**
         * Takes a configuration object with function references
         * as an input and creates a dummy class that proxies
         * function invocations from Browser context to Node context.
         *
         * The configuration is to be provided by the
         * tools.createBrowserHandlesForObject function.
         */
        class NodeProxy {
            constructor(config) {
                if (!config || typeof config !== 'object') {
                    throw new Error('NodeProxy: Parameter config of type Object must be provided.');
                }

                Object.entries(config)
                    .forEach(([key, { value, type }]) => {
                        if (type === 'METHOD') {
                            this[key] = (...args) => global[value](...args);
                        } else if (type === 'GETTER') {
                            Object.defineProperty(this, key, {
                                get: () => global[value](),
                            });
                        } else if (type === 'VALUE') {
                            this[key] = value;
                        } else {
                            throw new Error(`Unsupported function type: ${type} for function: ${key}.`);
                        }
                    });
            }
        }

        /**
         * Exposed factory.
         * @param config
         * @return {NodeProxy}
         */
        global[namespace].createNodeProxy = config => new NodeProxy(config);

        const setup = Symbol('crawler-setup');
        const internalState = Symbol('request-internal-state');

        /**
         * Context represents everything that is available to the user
         * via Page Function. A class is used instead of a simple object
         * to avoid having to create new instances of functions with each
         * request.
         *
         * Some properties need to be accessible to the Context,
         * but should not be exposed to the user thus they are hidden
         * using a Symbol to prevent the user from easily accessing
         * and manipulating them.
         *
         * @param {Object} options
         * @param {Object} options.crawlerSetup
         * @param {Object} options.browserHandles
         * @param {Object} options.pageFunctionArguments
         */
        class Context {
            /* eslint-disable class-methods-use-this */
            constructor(options) {
                const {
                    crawlerSetup,
                    browserHandles,
                    pageFunctionArguments,
                } = options;

                const createProxy = global[namespace].createNodeProxy;

                // Private
                this[setup] = crawlerSetup;
                this[internalState] = {
                    browserHandles,
                    requestQueue: browserHandles.requestQueue ? createProxy(browserHandles.requestQueue) : null,
                    apify: createProxy(browserHandles.apify),
                };

                // Copies of Node objects
                this.input = JSON.parse(crawlerSetup.rawInput);
                this.env = Object.assign({}, crawlerSetup.env);
                this.customData = crawlerSetup.customData;
                this.response = pageFunctionArguments.response;
                this.request = pageFunctionArguments.request;
                // Functions are not converted so we need to add them this way
                // to not be enumerable and thus not polluting the object.
                Reflect.defineProperty(this.request, 'pushErrorMessage', {
                    value(errorOrMessage) {
                        // It's a simplified fake of the original function.
                        const msg = (errorOrMessage && errorOrMessage.message) || `${errorOrMessage}`;
                        this.errorMessages.push(msg);
                    },
                    enumerable: false,
                });

                // Proxied Node objects
                this.globalStore = createProxy(browserHandles.globalStore);
                this.log = createProxy(browserHandles.log);

                // Browser side libraries
                if (this[setup].injectJQuery) this.jQuery = global.jQuery.noConflict(true);
                if (this[setup].injectUnderscore) this.underscoreJs = global._.noConflict();

                // Bind this to allow destructuring off context in pageFunction.
                this.getValue = this.getValue.bind(this);
                this.setValue = this.setValue.bind(this);
                this.saveSnapshot = this.saveSnapshot.bind(this);
                this.skipLinks = this.skipLinks.bind(this);
                this.enqueueRequest = this.enqueueRequest.bind(this);
                this.waitFor = this.waitFor.bind(this);
            }

            async getValue(...args) {
                return this[internalState].apify.getValue(...args);
            }

            async setValue(...args) {
                return this[internalState].apify.setValue(...args);
            }

            async saveSnapshot() {
                const handle = this[internalState].browserHandles.saveSnapshot;
                return global[handle]();
            }

            async skipLinks() {
                const handle = this[internalState].browserHandles.skipLinks;
                return global[handle]();
            }

            async enqueueRequest(requestOpts = {}, options = {}) {
                if (!this[setup].useRequestQueue) {
                    throw new Error('Input parameter "useRequestQueue" must be set to true to be able to enqueue new requests.');
                }

                const defaultRequestOpts = {
                    useExtendedUniqueKey: true,
                    keepUrlFragment: this.input.keepUrlFragments,
                };

                const newRequest = { ...defaultRequestOpts, ...requestOpts };

                const metaKey = this[setup].META_KEY;
                const defaultUserData = {
                    [metaKey]: {
                        parentRequestId: this.request.id || this.request.uniqueKey,
                        depth: this.request.userData[metaKey].depth + 1,
                    },
                };

                newRequest.userData = { ...defaultUserData, ...requestOpts.userData };

                return this[internalState].requestQueue.addRequest(newRequest, options);
            }

            async waitFor(selectorOrNumberOrFunction, options = {}) {
                if (!options || typeof options !== 'object') throw new Error('Parameter options must be an Object');
                const type = typeof selectorOrNumberOrFunction;
                if (type === 'string') return this._waitForSelector(selectorOrNumberOrFunction, options);
                if (type === 'number') return this._waitForMillis(selectorOrNumberOrFunction);
                if (type === 'function') return this._waitForFunction(selectorOrNumberOrFunction, options);
                throw new Error('Parameter selectorOrNumberOrFunction must be one of the said types.');
            }

            async _waitForSelector(selector, options = {}) {
                try {
                    await this._poll(() => {
                        return !!global.document.querySelector(selector);
                    }, options);
                } catch (err) {
                    if (/timeout of \d+ms exceeded/.test(err.message)) {
                        throw new Error(`Timeout Error: waiting for selector failed: ${err.message}`);
                    }
                    throw err;
                }
            }

            async _waitForMillis(millis) {
                return new Promise(res => setTimeout(res, millis));
            }

            async _waitForFunction(predicate, options = {}) {
                try {
                    await this._poll(predicate, options);
                } catch (err) {
                    if (/timeout of \d+ms exceeded/.test(err.message)) {
                        throw new Error(`Timeout Error: waiting for function failed: ${err.message}`);
                    }
                    throw err;
                }
            }

            async _poll(predicate, options = {}) {
                const {
                    pollingIntervalMillis = 50,
                    timeoutMillis = 20000,
                } = options;
                return new Promise((resolve, reject) => {
                    const handler = () => {
                        return predicate() ? resolve() : setTimeout(handler);
                    };
                    const pollTimeout = setTimeout(handler, pollingIntervalMillis);
                    setTimeout(() => {
                        clearTimeout(pollTimeout);
                        return reject(new Error(`timeout of ${timeoutMillis}ms exceeded.`));
                    }, timeoutMillis);
                });
            }
        }

        /**
         * Exposed factory.
         * @param {Object} options
         * @returns {Context}
         */
        global[namespace].createContext = (options) => {
            return new Context(options);
        };
    }(window, apifyNamespace));
};


src/bundle.browser.js

src/crawler_setup.js

/**
 * GlobalStore is a trivial storage that resembles a Map to be used from Browser contexts
 * to retain data through page navigations and browser instances. It limits Map's functionality
 * because it's currently impossible for functions and object references to cross Node-Browser threshold.
 */
class GlobalStore extends Map {
    /* eslint-disable class-methods-use-this */
    get(key) {
        if (typeof key !== 'string') throw new Error('GlobalStore#get parameter "key" must be a string.');
        return super.get(key);
    }

    set(key, value) {
        if (typeof key !== 'string') throw new Error('GlobalStore#set parameter "key" must be a string.');
        return super.set(key, value);
    }

    forEach() {
        throw new Error('GlobalStore#forEach function is not available due to underlying technology limitations.');
    }

    values() {
        return Array.from(super.values());
    }

    keys() {
        return Array.from(super.keys());
    }

    entries() {
        return Array.from(super.entries());
    }

    get size() {
        return super.size;
    }
}

module.exports = GlobalStore;


src/global_store.js

const { expect } = require('chai');
const Apify = require('apify');
const createBundle = require('../src/bundle.browser');

const NAMESPACE = 'Apify';

describe('Bundle', () => {
    let browser;
    let page;
    before(async () => {
        browser = await Apify.launchPuppeteer({ headless: true });
    });
    after(async () => {
        await browser.close();
    });
    beforeEach(async () => {
        page = await browser.newPage();
        await page.evaluateOnNewDocument(createBundle, NAMESPACE);
    });
    afterEach(async () => {
        await page.close();
    });
    describe('Context', () => {
        const CONTEXT_OPTIONS = {
            crawlerSetup: {
                rawInput: '{}',

            },
            browserHandles: {
                apify: {},
                globalStore: {},
                log: {},
            },
            pageFunctionArguments: {
                request: {},
            },
        };
        beforeEach(async () => {
            await page.goto('about:chrome');
            await page.waitFor(namespace => !!window[namespace], {}, NAMESPACE);
            await page.evaluate((namespace, contextOptions) => {
                window.contextInstance = window[namespace].createContext(contextOptions);
            }, NAMESPACE, CONTEXT_OPTIONS);
        });
        describe('waitFor', async () => {
            it('should work with a number', async () => {
                const millis = await page.evaluate(async () => {
                    const ctx = window.contextInstance;
                    const start = Date.now();
                    await ctx.waitFor(10);
                    return Date.now() - start;
                });
                expect(millis).to.be.above(9);
            });
            it('should work with a selector', async () => {
                const millis = await page.evaluate(async () => {
                    const ctx = window.contextInstance;
                    const start = Date.now();
                    setTimeout(() => {
                        const el = document.createElement('div');
                        el.id = 'very-unique-id';
                        document.body.appendChild(el);
                    }, 10);
                    await ctx.waitFor('#very-unique-id');
                    return Date.now() - start;
                });
                expect(millis).to.be.above(9);
            });
            it('should work with a function', async () => {
                const millis = await page.evaluate(async () => {
                    const ctx = window.contextInstance;
                    let done = false;
                    const start = Date.now();
                    setTimeout(() => {
                        done = true;
                    }, 10);
                    await ctx.waitFor(() => done);
                    return Date.now() - start;
                });
                expect(millis).to.be.above(9);
            });
        });
    });
});


Web Scraper Experimental Debug

Where next?