docs: fix all broken links and enforce we dont add new ones (#251)

website/docusaurus.config.js

@@ -21,9 +21,9 @@ module.exports = {
     projectName: 'apify-sdk-js',
     favicon: 'img/favicon.svg',
     onBrokenLinks:
-    /** @type {import('@docusaurus/types').ReportingSeverity} */ ('warn'),
+    /** @type {import('@docusaurus/types').ReportingSeverity} */ ('throw'),
     onBrokenMarkdownLinks:
-    /** @type {import('@docusaurus/types').ReportingSeverity} */ ('warn'),
+    /** @type {import('@docusaurus/types').ReportingSeverity} */ ('throw'),
     themes: [
         [
             '@apify/docs-theme',
@@ -68,11 +68,35 @@ module.exports = {
                             'className': 'navbar__item', // fixes margin around dropdown - hackish, should be fixed in theme
                             'data-api-links': JSON.stringify([
                                 'reference/next',
-                                ...versions.map((version, i) => (i === 0 ? 'reference' : `reference/${version}`)),
+                                ...versions.map((version, i) => {
+                                    if (i === 0) {
+                                        return 'reference';
+                                    }
+
+                                    if (+version < 3) {
+                                        return `docs/${version}/api/apify`;
+                                    }
+
+                                    return `reference/${version}`;
+                                }),
                             ]),
                             'dropdownItemsBefore': [],
                             'dropdownItemsAfter': [],
                         },
+                        // {
+                        //     type: 'docsVersionDropdown',
+                        //     position: 'left',
+                        //     dropdownItemsAfter: [
+                        //         {
+                        //             href: 'https://sdk.apify.com/docs/guides/getting-started',
+                        //             label: '2.2',
+                        //         },
+                        //         {
+                        //             href: 'https://sdk.apify.com/docs/1.3.1/guides/getting-started',
+                        //             label: '1.3',
+                        //         },
+                        //     ],
+                        // },
                     ],
                 },
             },
@@ -84,8 +108,10 @@ module.exports = {
             /** @type {import('@docusaurus/preset-classic').Options} */
             ({
                 docs: {
-                    showLastUpdateAuthor: true,
-                    showLastUpdateTime: true,
+                    // Docusaurus shows the author and date of last commit to entire repo, which doesn't make sense,
+                    // so let's just disable showing author and last modification
+                    showLastUpdateAuthor: false,
+                    showLastUpdateTime: false,
                     path: '../docs',
                     sidebarPath: './sidebars.js',
                     rehypePlugins: [externalLinkProcessor],

website/src/components/ApiLink.jsx

@@ -8,9 +8,13 @@ const ApiLink = ({ to, children }) => {
     const { version, isLast } = useDocsVersion();
     const { siteConfig } = useDocusaurusContext();
 
+    if (to.toString().startsWith('apify/')) {
+        to = to.toString().substring('apify/'.length);
+    }
+
     if (siteConfig.presets[0][1].docs.disableVersioning) {
         return (
-            <Link to={`/api/${to}`}>{children}</Link>
+            <Link to={`/reference/${to}`}>{children}</Link>
         );
     }
 
@@ -23,7 +27,7 @@ const ApiLink = ({ to, children }) => {
     }
 
     return (
-        <Link to={`/api/${versionSlug}${to}`}>{children}</Link>
+        <Link to={`/reference/${versionSlug}${to}`}>{children}</Link>
     );
 };
 

website/src/theme/NavbarItem/DocsVersionDropdownNavbarItem.js

@@ -67,8 +67,7 @@ export default function DocsVersionDropdownNavbarItem({
         ? translate({
             id: 'theme.navbar.mobileVersionsDropdown.label',
             message: 'Versions',
-            description:
-                    'The label for the navbar versions dropdown on mobile view',
+            description: 'The label for the navbar versions dropdown on mobile view',
         })
         : dropdownVersion.label;
     let dropdownTo = mobile && items.length > 1

website/versioned_docs/version-1.3/examples/basic_crawler.md

@@ -5,11 +5,11 @@ id: basic-crawler
 ---
 
 This is the most bare-bones example of the Apify SDK, which demonstrates some of its building blocks such as the
-[`BasicCrawler`](/docs/api/basic-crawler). You probably don't need to go this deep though, and it would be better to start with one of the full
+[`BasicCrawler`](/docs/1.3/api/basic-crawler). You probably don't need to go this deep though, and it would be better to start with one of the full
 featured crawlers like [`CheerioCrawler`](https://sdk.apify.com/docs/examples/cheerio-crawler) or
 [`PlaywrightCrawler`](https://sdk.apify.com/docs/examples/playwright-crawler).
 
-The script simply downloads several web pages with plain HTTP requests using the [`Apify.utils.requestAsBrowser()`](/docs/api/utils#requestasbrowser)
+The script simply downloads several web pages with plain HTTP requests using the [`Apify.utils.requestAsBrowser()`](/docs/1.3/api/utils#requestasbrowser)
 convenience function and stores their raw HTML and URL in the default dataset. In local configuration, the data will be stored as JSON files in
 `./apify_storage/datasets/default`.
 

website/versioned_docs/version-1.3/examples/call_actor.md

@@ -4,8 +4,8 @@ title: Call actor
 id: call-actor
 ---
 
-This example demonstrates how to start an Apify actor using [`Apify.call()`](/docs/api/apify#call) and how to call the Apify API using
-[`Apify.client`](/docs/api/apify#client). The script gets a random weird word and its explanation from [randomword.com](https://randomword.com/) and
+This example demonstrates how to start an Apify actor using [`Apify.call()`](/docs/1.3/api/apify#call) and how to call the Apify API using
+[`Apify.client`](/docs/1.3/api/apify#client). The script gets a random weird word and its explanation from [randomword.com](https://randomword.com/) and
 sends it to your email using the [`apify/send-mail`](https://apify.com/apify/send-mail) actor.
 
 To make the example work, you'll need an [Apify account](https://my.apify.com/). Go to the

website/versioned_docs/version-1.3/examples/cheerio_crawler.md

@@ -4,7 +4,7 @@ title: Cheerio crawler
 id: cheerio-crawler
 ---
 
-This example demonstrates how to use [`CheerioCrawler`](/docs/api/cheerio-crawler) to crawl a list of URLs from an external file, load each URL using
+This example demonstrates how to use [`CheerioCrawler`](/docs/1.3/api/cheerio-crawler) to crawl a list of URLs from an external file, load each URL using
 a plain HTTP request, parse the HTML using the [Cheerio library](https://www.npmjs.com/package/cheerio) and extract some data from it: the page title
 and all `h1` tags.
 

website/versioned_docs/version-1.3/examples/crawl_relative_links.md

@@ -4,7 +4,7 @@ title: Crawl a website with relative links
 id: crawl-relative-links
 ---
 
-If a website uses relative links, [`CheerioCrawler`](/docs/api/cheerio-crawler) and `Apify.enqueueLinks()` may have trouble following them. This is
+If a website uses relative links, [`CheerioCrawler`](/docs/1.3/api/cheerio-crawler) and `Apify.enqueueLinks()` may have trouble following them. This is
 why it is important to set the `baseUrl` property within `Apify.enqueueLinks()` to `request.loadedUrl`:
 
 ```javascript

website/versioned_docs/version-1.3/examples/crawl_single_url.md

@@ -4,7 +4,7 @@ title: Crawl a single URL
 id: crawl-single-url
 ---
 
-This example uses the [`Apify.utils.requestAsBrowser()`](/docs/api/utils#utilsrequestasbrowseroptions) function to grab the HTML of a web page.
+This example uses the [`Apify.utils.requestAsBrowser()`](/docs/1.3/api/utils#utilsrequestasbrowseroptions) function to grab the HTML of a web page.
 
 ```javascript
 const Apify = require('apify');

website/versioned_docs/version-1.3/examples/crawl_some_links.md

@@ -4,7 +4,7 @@ title: Crawl some links on a website
 id: crawl-some-links
 ---
 
-This [`CheerioCrawler`](/docs/api/cheerio-crawler) example uses the [`pseudoUrls`](/docs/api/pseudo-url) property in the `Apify.enqueueLinks()` method
+This [`CheerioCrawler`](/docs/1.3/api/cheerio-crawler) example uses the [`pseudoUrls`](/docs/1.3/api/pseudo-url) property in the `Apify.enqueueLinks()` method
 to only add links to the `RequestList` queue if they match the specified regular expression.
 
 ```javascript

website/versioned_docs/version-1.3/examples/forms.md

@@ -4,10 +4,10 @@ title: Forms
 id: forms
 ---
 
-This example demonstrates how to use [`PuppeteerCrawler`](/docs/api/puppeteer-crawler) to automatically fill and submit a search form to look up
+This example demonstrates how to use [`PuppeteerCrawler`](/docs/1.3/api/puppeteer-crawler) to automatically fill and submit a search form to look up
 repositories on [GitHub](https://github.com) using headless Chrome / Puppeteer. The actor first fills in the search term, repository owner, start date
 and language of the repository, then submits the form and prints out the results. Finally, the results are saved either on the Apify platform to the
-default [`dataset`](/docs/api/dataset) or on the local machine as JSON files in `./apify_storage/datasets/default`.
+default [`dataset`](/docs/1.3/api/dataset) or on the local machine as JSON files in `./apify_storage/datasets/default`.
 
 > To run this example on the Apify Platform, select the `apify/actor-node-puppeteer-chrome` image for your Dockerfile.
 

website/versioned_docs/version-1.3/examples/map_and_reduce.md

@@ -4,9 +4,9 @@ title: Dataset Map and Reduce methods
 id: map-and-reduce
 ---
 
-This example shows an easy use-case of the [Apify dataset](https://docs.apify.com/storage/dataset) [`map`](/docs/api/dataset#map) and
-[`reduce`](/docs/api/dataset#reduce) methods. Both methods can be used to simplify the dataset results workflow process. Both can be called on the
-[dataset](/docs/api/dataset) directly.
+This example shows an easy use-case of the [Apify dataset](https://docs.apify.com/storage/dataset) [`map`](/docs/1.3/api/dataset#map) and
+[`reduce`](/docs/1.3/api/dataset#reduce) methods. Both methods can be used to simplify the dataset results workflow process. Both can be called on the
+[dataset](/docs/1.3/api/dataset) directly.
 
 Important to mention is that both methods return a new result (`map` returns a new array and `reduce` can return any type) - neither method updates
 the dataset in any way.
@@ -15,7 +15,7 @@ Examples for both methods are demonstrated on a simple dataset containing the re
 `h1` - `h3` header elements under the `headingCount` key.
 
 This data structure is stored in the default dataset under `{PROJECT_FOLDER}/apify_storage/datasets/default/`. If you want to simulate the
-functionality, you can use the [`dataset.PushData()`](/docs/api/dataset#pushdata) method to save the example `JSON array` to your dataset.
+functionality, you can use the [`dataset.PushData()`](/docs/1.3/api/dataset#pushdata) method to save the example `JSON array` to your dataset.
 
 ```json
 [
@@ -58,7 +58,7 @@ Apify.main(async () => {
 
 The `moreThan5headers` variable is an array of `headingCount` attributes where the number of headers is greater than 5.
 
-The `map` method's result value saved to the [`key-value store`](/docs/api/key-value-store) should be:
+The `map` method's result value saved to the [`key-value store`](/docs/1.3/api/key-value-store) should be:
 
 ```javascript
 [11, 8];
@@ -67,7 +67,7 @@ The `map` method's result value saved to the [`key-value store`](/docs/api/key-v
 ### Reduce
 
 The dataset `reduce` method does not produce a new array of values - it reduces a list of values down to a single value. The method iterates through
-the items in the dataset using the [`memo` argument](/docs/api/dataset#datasetreduceiteratee-memo-options). After performing the necessary
+the items in the dataset using the [`memo` argument](/docs/1.3/api/dataset#datasetreduceiteratee-memo-options). After performing the necessary
 calculation, the `memo` is sent to the next iteration, while the item just processed is reduced (removed).
 
 Using the `reduce` method to get the total number of headers scraped (all items in the dataset):
@@ -93,7 +93,7 @@ Apify.main(async () => {
 The original dataset will be reduced to a single value, `pagesHeadingCount`, which contains the count of all headers for all scraped pages (all
 dataset items).
 
-The `reduce` method's result value saved to the [key-value store](/docs/api/key-value-store) should be:
+The `reduce` method's result value saved to the [key-value store](/docs/1.3/api/key-value-store) should be:
 
 ```javascript
 23;

website/versioned_docs/version-1.3/examples/puppeteer_crawler.md

@@ -4,7 +4,7 @@ title: Puppeteer crawler
 id: puppeteer-crawler
 ---
 
-This example demonstrates how to use [`PuppeteerCrawler`](/docs/api/puppeteer-crawler) in combination with [`RequestQueue`](/docs/api/request-queue)
+This example demonstrates how to use [`PuppeteerCrawler`](/docs/1.3/api/puppeteer-crawler) in combination with [`RequestQueue`](/docs/1.3/api/request-queue)
 to recursively scrape the [Hacker News website](https://news.ycombinator.com) using headless Chrome / Puppeteer. The crawler starts with a single URL,
 finds links to next pages, enqueues them and continues until no more desired links are available. The results are stored to the default dataset. In
 local configuration, the results are stored as JSON files in `./apify_storage/datasets/default`

website/versioned_docs/version-1.3/examples/puppeteer_recursive_crawl.md

@@ -4,7 +4,7 @@ title: Puppeteer recursive crawl
 id: puppeteer-recursive-crawl
 ---
 
-Run the following example to perform a recursive crawl of a website using [`PuppeteerCrawler`](/docs/api/puppeteer-crawler).
+Run the following example to perform a recursive crawl of a website using [`PuppeteerCrawler`](/docs/1.3/api/puppeteer-crawler).
 
 > To run this example on the Apify Platform, select the `apify/actor-node-puppeteer-chrome` image for your Dockerfile.
 

website/versioned_docs/version-1.3/examples/puppeteer_sitemap.md

@@ -4,7 +4,7 @@ title: Puppeteer sitemap
 id: puppeteer-sitemap
 ---
 
-This example demonstrates how to use [`PuppeteerCrawler`](/docs/api/puppeteer-crawler) to crawl a list of web pages specified in a sitemap. The
+This example demonstrates how to use [`PuppeteerCrawler`](/docs/1.3/api/puppeteer-crawler) to crawl a list of web pages specified in a sitemap. The
 crawler extracts the page title and URL from each page and stores them as a record in the default dataset. In local configuration, the results are
 stored as JSON files in `./apify_storage/datasets/default`.
 

website/versioned_docs/version-1.3/examples/screenshots.md

@@ -4,8 +4,8 @@ title: Screenshots
 id: screenshots
 ---
 
-This example demonstrates how to read and write data to the default key-value store using [`Apify.getValue()`](/docs/api/apify#apifygetvaluekey) and
-[`Apify.setValue()`](/docs/api/apify#apifysetvaluekey-value-options).
+This example demonstrates how to read and write data to the default key-value store using [`Apify.getValue()`](/docs/1.3/api/apify#apifygetvaluekey) and
+[`Apify.setValue()`](/docs/1.3/api/apify#apifysetvaluekey-value-options).
 
 The script crawls a list of URLs using Puppeteer, captures a screenshot of each page, and saves it to the store. The list of URLs is provided as actor
 input that is also read from the store.

website/versioned_docs/version-1.3/guides/quick_start.md

@@ -51,7 +51,7 @@ Apify.main(async () => {
 });
 ```
 
-> To read more about what pseudo-URL is, check the [getting-started](getting_started#introduction-to-pseudo-urls).
+> To read more about what pseudo-URL is, check the [getting-started](./getting_started.md#introduction-to-pseudo-urls).
 
 When you run the example, you should see Apify SDK automating a Chrome browser.
 

website/versioned_docs/version-1.3/guides/request_storage.md

@@ -21,7 +21,7 @@ The request queue is a storage of URLs to crawl. The queue is used for the deep
 
 Each actor run is associated with a **default request queue**, which is created exclusively for the actor run. Typically, it is used to store URLs to crawl in the specific actor run. Its usage is optional.
 
-In Apify SDK, the request queue is represented by the [`RequestQueue`](/docs/api/request-queue) class.
+In Apify SDK, the request queue is represented by the [`RequestQueue`](/docs/1.3/api/request-queue) class.
 
 In local configuration, the request queue is emulated by [@apify/storage-local](https://github.com/apify/apify-storage-local-js) NPM package and its data is stored in SQLite database in the directory specified by the `APIFY_LOCAL_STORAGE_DIR` environment variable as follows:
 
@@ -55,11 +55,11 @@ To see more detailed example of how to use the request queue with a crawler, see
 
 ## Request list
 
-The request list is not a storage per se - it represents the list of URLs to crawl that is stored in a run memory (or optionally in default [Key-Value Store](../guides/results-storage#key-value-store) associated with the run, if specified). The list is used for the crawling of a large number of URLs, when you know all the URLs which should be visited by the crawler and no URLs would be added during the run. The URLs can be provided either in code or parsed from a text file hosted on the web.
+The request list is not a storage per se - it represents the list of URLs to crawl that is stored in a run memory (or optionally in default [Key-Value Store](./result_storage.md#key-value-store) associated with the run, if specified). The list is used for the crawling of a large number of URLs, when you know all the URLs which should be visited by the crawler and no URLs would be added during the run. The URLs can be provided either in code or parsed from a text file hosted on the web.
 
 Request list is created exclusively for the actor run and only if its usage is explicitly specified in the code. Its usage is optional.
 
-In Apify SDK, the request list is represented by the [`RequestList`](/docs/api/request-list) class.
+In Apify SDK, the request list is represented by the [`RequestList`](/docs/1.3/api/request-list) class.
 
 The following code demonstrates basic operations of the request list:
 

website/versioned_docs/version-1.3/typedefs/DatasetConsumer.md

@@ -11,7 +11,7 @@ User-function used in the `Dataset.forEach()` API.
 **Parameters**:
 
 -   **`item`**: `object` - Current [`Dataset`](../api/dataset) entry being processed.
--   **`index`**: `number` - Position of current {Dataset} entry.
+-   **`index`**: `number` - Position of current [`Dataset`](../api/dataset) entry.
 
 **Returns**:
 

website/versioned_docs/version-1.3/typedefs/DatasetMapper.md

@@ -11,7 +11,7 @@ User-function used in the `Dataset.map()` API.
 **Parameters**:
 
 -   **`item`**: `object` - Currect [`Dataset`](../api/dataset) entry being processed.
--   **`index`**: `number` - Position of current {Dataset} entry.
+-   **`index`**: `number` - Position of current [`Dataset`](../api/dataset) entry.
 
 **Returns**:
 

website/versioned_docs/version-1.3/typedefs/DatasetReducer.md

@@ -12,7 +12,7 @@ User-function used in the `Dataset.reduce()` API.
 
 -   **`memo`**: `object` - Previous state of the reduction.
 -   **`item`**: `object` - Currect [`Dataset`](../api/dataset) entry being processed.
--   **`index`**: `number` - Position of current {Dataset} entry.
+-   **`index`**: `number` - Position of current [`Dataset`](../api/dataset) entry.
 
 **Returns**:
 

website/versioned_docs/version-1.3/typedefs/KeyConsumer.md

@@ -10,7 +10,7 @@ User-function used in the [`KeyValueStore.forEachKey()`](../api/key-value-store#
 
 **Parameters**:
 
--   **`key`**: `string` - Current {KeyValue} key being processed.
+-   **`key`**: `string` - Current key being processed.
 -   **`index`**: `number` - Position of the current key in [`KeyValueStore`](../api/key-value-store).
 -   **`info`**: `*` - Information about the current [`KeyValueStore`](../api/key-value-store) entry.
     -   **`size`**: `number` - Size of the value associated with the current key in bytes.

website/versioned_docs/version-1.3/typedefs/RequestTransform.md

@@ -6,7 +6,7 @@ id: request-transform
 
 <a name="requesttransform"></a>
 
-Takes an Apify {RequestOptions} object and changes it's attributes in a desired way. This user-function is used
+Takes an Apify [`RequestOptions`](./request-options) object and changes it's attributes in a desired way. This user-function is used
 [`utils.enqueueLinks()`](../api/utils#enqueuelinks) to modify requests before enqueuing them.
 
 **Parameters**: