chore(release): 2.0.5 [skip ci]

## [2.0.5](v2.0.4...v2.0.5) (2021-11-15) ### Bug Fixes * export utilities and add managed jsdom example ([132038b](132038b))
armand1m · Nov 15, 2021 · 8e3eca6 · 8e3eca6
1 parent 1100792
commit 8e3eca6
Show file tree

Hide file tree

Showing 13 changed files with 129 additions and 38 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,10 @@
+## [2.0.5](https://github.com/armand1m/papercut/compare/v2.0.4...v2.0.5) (2021-11-15)
+
+
+### Bug Fixes
+
+* export utilities and add managed jsdom example ([132038b](https://github.com/armand1m/papercut/commit/132038bd46bf6386b168967925f0cadf8a906241))
+
 ## [2.0.4](https://github.com/armand1m/papercut/compare/v2.0.3...v2.0.4) (2021-11-15)
 
 

diff --git a/README.md b/README.md
@@ -97,7 +97,10 @@ const main = async () => {
     baseUrl: "https://news.ycombinator.com/",
     target: ".athing",
     selectors: {
-      rank: ({ text }) => text('.rank'),
+      rank: (utils) => {
+        const value = utils.text('.rank').replace(/^\D+/g, '');
+        return Number(value);
+      },
       name: ({ text }) => text('.titlelink'),
       url: ({ href }) => href('.titlelink'),
       score: ({ element }) => {
@@ -229,6 +232,76 @@ Then run it using `node` or `ts-node`:
 npx ts-node ./paginated-scraper.ts
 ```
 
+#### Managed JSDOM
+
+In case you want to use your own JSDOM and Pino instance and tweak/configure as much as you prefer, you can use the `scrape` function instead.
+
+In the example below, we use the exposed `createWindow` and `fetchPage` utilities for convenience. You can use JSDOM constructor directly and any other strategy to fetch your page HTML as desired.
+
+```ts file=./examples/typescript/src/managed-jsdom/scraper.ts
+import pino from 'pino'
+import { scrape, fetchPage, createWindow } from '@armand1m/papercut';
+
+const main = async () => {
+  const logger = pino({
+    name: 'Hacker News',
+    enabled: false
+  });
+
+  const rawHTML = await fetchPage('https://news.ycombinator.com/')
+  const window = createWindow(rawHTML);
+
+  const results = await scrape({
+    strict: true,
+    logger,
+    document: window.document,
+    target: ".athing",
+    selectors: {
+      rank: (utils) => {
+        const value = utils.text('.rank').replace(/^\D+/g, '');
+        return Number(value);
+      },
+      name: ({ text }) => text('.titlelink'),
+      url: ({ href }) => href('.titlelink'),
+      score: ({ element }) => {
+        return element.nextElementSibling?.querySelector('.score')
+          ?.textContent;
+      },
+      createdBy: ({ element }) => {
+        return element.nextElementSibling?.querySelector('.hnuser')
+          ?.textContent;
+      },
+      createdAt: ({ element }) => {
+        return element.nextElementSibling
+          ?.querySelector('.age')
+          ?.getAttribute('title');
+      },
+    },
+    options: {
+      log: false,
+      cache: true,
+      concurrency: {
+        page: 2,
+        node: 2,
+        selector: 2
+      }
+    }
+  });
+
+  window.close();
+
+  console.log(JSON.stringify(results, null, 2));
+};
+
+main();
+```
+
+Then run it using `node` or `ts-node`:
+
+```sh
+npx ts-node ./managed-jsdom.ts
+```
+
 ## API Reference
 
 [Click here to open the API reference.](https://armand1m.github.io/papercut)

diff --git a/docs/assets/highlight.css b/docs/assets/highlight.css
@@ -13,16 +13,16 @@
     --dark-hl-5: #569CD6;
     --light-hl-6: #0070C1;
     --dark-hl-6: #4FC1FF;
-    --light-hl-7: #267F99;
-    --dark-hl-7: #4EC9B0;
-    --light-hl-8: #098658;
-    --dark-hl-8: #B5CEA8;
-    --light-hl-9: #811F3F;
-    --dark-hl-9: #D16969;
-    --light-hl-10: #000000;
-    --dark-hl-10: #D7BA7D;
-    --light-hl-11: #EE0000;
-    --dark-hl-11: #DCDCAA;
+    --light-hl-7: #811F3F;
+    --dark-hl-7: #D16969;
+    --light-hl-8: #EE0000;
+    --dark-hl-8: #DCDCAA;
+    --light-hl-9: #000000;
+    --dark-hl-9: #D7BA7D;
+    --light-hl-10: #267F99;
+    --dark-hl-10: #4EC9B0;
+    --light-hl-11: #098658;
+    --dark-hl-11: #B5CEA8;
     --light-hl-12: #008000;
     --dark-hl-12: #6A9955;
     --light-code-background: #FFFFFF;

diff --git a/docs/assets/search.js b/docs/assets/search.js
diff --git a/docs/index.html b/docs/index.html
diff --git a/docs/interfaces/CreateRunnerProps.html b/docs/interfaces/CreateRunnerProps.html
@@ -1,6 +1,6 @@
-<!DOCTYPE html><html class="default"><head><meta charSet="utf-8"/><meta http-equiv="x-ua-compatible" content="IE=edge"/><title>CreateRunnerProps | @armand1m/papercut</title><meta name="description" content="Documentation for @armand1m/papercut"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="../assets/style.css"/><link rel="stylesheet" href="../assets/highlight.css"/><script async src="../assets/search.js" id="search-script"></script></head><body><script>document.body.classList.add(localStorage.getItem("tsd-theme") || "os")</script><header><div class="tsd-page-toolbar"><div class="container"><div class="table-wrap"><div class="table-cell" id="tsd-search" data-base=".."><div class="field"><label for="tsd-search-field" class="tsd-widget search no-caption">Search</label><input type="text" id="tsd-search-field"/></div><ul class="results"><li class="state loading">Preparing search index...</li><li class="state failure">The search index is not available</li></ul><a href="../index.html" class="title">@armand1m/papercut</a></div><div class="table-cell" id="tsd-widgets"><div id="tsd-filter"><a href="#" class="tsd-widget options no-caption" data-toggle="options">Options</a><div class="tsd-filter-group"><div class="tsd-select" id="tsd-filter-visibility"><span class="tsd-select-label">All</span><ul class="tsd-select-list"><li data-value="public">Public</li><li data-value="protected">Public/Protected</li><li data-value="private" class="selected">All</li></ul></div> <input type="checkbox" id="tsd-filter-inherited" checked/><label class="tsd-widget" for="tsd-filter-inherited">Inherited</label><input type="checkbox" id="tsd-filter-externals" checked/><label class="tsd-widget" for="tsd-filter-externals">Externals</label></div></div><a href="#" class="tsd-widget menu no-caption" data-toggle="menu">Menu</a></div></div></div></div><div class="tsd-page-title"><div class="container"><ul class="tsd-breadcrumb"><li><a href="../modules.html">@armand1m/papercut</a></li><li><a href="CreateRunnerProps.html">CreateRunnerProps</a></li></ul><h1>Interface CreateRunnerProps</h1></div></div></header><div class="container container-main"><div class="row"><div class="col-8 col-content"><section class="tsd-panel tsd-hierarchy"><h3>Hierarchy</h3><ul class="tsd-hierarchy"><li><span class="target">CreateRunnerProps</span></li></ul></section><section class="tsd-panel-group tsd-index-group"><h2>Index</h2><section class="tsd-panel tsd-index-panel"><div class="tsd-index-content"><section class="tsd-index-section "><h3>Properties</h3><ul class="tsd-index-list"><li class="tsd-kind-property tsd-parent-kind-interface"><a href="CreateRunnerProps.html#logger" class="tsd-kind-icon">logger</a></li><li class="tsd-kind-property tsd-parent-kind-interface"><a href="CreateRunnerProps.html#options" class="tsd-kind-icon">options</a></li></ul></section></div></section></section><section class="tsd-panel-group tsd-member-group "><h2>Properties</h2><section class="tsd-panel tsd-member tsd-kind-property tsd-parent-kind-interface"><a id="logger" class="tsd-anchor"></a><h3>logger</h3><div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Logger</span></div><aside class="tsd-sources"><ul><li>Defined in <a href="https://github.com/armand1m/papercut/blob/32146cd/src/scraper/createRunner.ts#L68">scraper/createRunner.ts:68</a></li></ul></aside><div class="tsd-comment tsd-typography"><div class="lead">
+<!DOCTYPE html><html class="default"><head><meta charSet="utf-8"/><meta http-equiv="x-ua-compatible" content="IE=edge"/><title>CreateRunnerProps | @armand1m/papercut</title><meta name="description" content="Documentation for @armand1m/papercut"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="../assets/style.css"/><link rel="stylesheet" href="../assets/highlight.css"/><script async src="../assets/search.js" id="search-script"></script></head><body><script>document.body.classList.add(localStorage.getItem("tsd-theme") || "os")</script><header><div class="tsd-page-toolbar"><div class="container"><div class="table-wrap"><div class="table-cell" id="tsd-search" data-base=".."><div class="field"><label for="tsd-search-field" class="tsd-widget search no-caption">Search</label><input type="text" id="tsd-search-field"/></div><ul class="results"><li class="state loading">Preparing search index...</li><li class="state failure">The search index is not available</li></ul><a href="../index.html" class="title">@armand1m/papercut</a></div><div class="table-cell" id="tsd-widgets"><div id="tsd-filter"><a href="#" class="tsd-widget options no-caption" data-toggle="options">Options</a><div class="tsd-filter-group"><div class="tsd-select" id="tsd-filter-visibility"><span class="tsd-select-label">All</span><ul class="tsd-select-list"><li data-value="public">Public</li><li data-value="protected">Public/Protected</li><li data-value="private" class="selected">All</li></ul></div> <input type="checkbox" id="tsd-filter-inherited" checked/><label class="tsd-widget" for="tsd-filter-inherited">Inherited</label><input type="checkbox" id="tsd-filter-externals" checked/><label class="tsd-widget" for="tsd-filter-externals">Externals</label></div></div><a href="#" class="tsd-widget menu no-caption" data-toggle="menu">Menu</a></div></div></div></div><div class="tsd-page-title"><div class="container"><ul class="tsd-breadcrumb"><li><a href="../modules.html">@armand1m/papercut</a></li><li><a href="CreateRunnerProps.html">CreateRunnerProps</a></li></ul><h1>Interface CreateRunnerProps</h1></div></div></header><div class="container container-main"><div class="row"><div class="col-8 col-content"><section class="tsd-panel tsd-hierarchy"><h3>Hierarchy</h3><ul class="tsd-hierarchy"><li><span class="target">CreateRunnerProps</span></li></ul></section><section class="tsd-panel-group tsd-index-group"><h2>Index</h2><section class="tsd-panel tsd-index-panel"><div class="tsd-index-content"><section class="tsd-index-section "><h3>Properties</h3><ul class="tsd-index-list"><li class="tsd-kind-property tsd-parent-kind-interface"><a href="CreateRunnerProps.html#logger" class="tsd-kind-icon">logger</a></li><li class="tsd-kind-property tsd-parent-kind-interface"><a href="CreateRunnerProps.html#options" class="tsd-kind-icon">options</a></li></ul></section></div></section></section><section class="tsd-panel-group tsd-member-group "><h2>Properties</h2><section class="tsd-panel tsd-member tsd-kind-property tsd-parent-kind-interface"><a id="logger" class="tsd-anchor"></a><h3>logger</h3><div class="tsd-signature tsd-kind-icon">logger<span class="tsd-signature-symbol">:</span> <span class="tsd-signature-type">Logger</span></div><aside class="tsd-sources"><ul><li>Defined in <a href="https://github.com/armand1m/papercut/blob/1100792/src/scraper/createRunner.ts#L68">scraper/createRunner.ts:68</a></li></ul></aside><div class="tsd-comment tsd-typography"><div class="lead">
 <p>A pino.Logger instance.</p>
-</div></div></section><section class="tsd-panel tsd-member tsd-kind-property tsd-parent-kind-interface"><a id="options" class="tsd-anchor"></a><h3>options</h3><div class="tsd-signature tsd-kind-icon">options<span class="tsd-signature-symbol">:</span> <a href="ScraperOptions.html" class="tsd-signature-type" data-tsd-kind="Interface">ScraperOptions</a></div><aside class="tsd-sources"><ul><li>Defined in <a href="https://github.com/armand1m/papercut/blob/32146cd/src/scraper/createRunner.ts#L73">scraper/createRunner.ts:73</a></li></ul></aside><div class="tsd-comment tsd-typography"><div class="lead">
+</div></div></section><section class="tsd-panel tsd-member tsd-kind-property tsd-parent-kind-interface"><a id="options" class="tsd-anchor"></a><h3>options</h3><div class="tsd-signature tsd-kind-icon">options<span class="tsd-signature-symbol">:</span> <a href="ScraperOptions.html" class="tsd-signature-type" data-tsd-kind="Interface">ScraperOptions</a></div><aside class="tsd-sources"><ul><li>Defined in <a href="https://github.com/armand1m/papercut/blob/1100792/src/scraper/createRunner.ts#L73">scraper/createRunner.ts:73</a></li></ul></aside><div class="tsd-comment tsd-typography"><div class="lead">
 <p>The scraper options.
 Use this to tweak log, cache and concurrency settings.</p>
 </div></div></section></section></div><div class="col-4 col-menu menu-sticky-wrap menu-highlight"><nav class="tsd-navigation primary"><ul><li class=""><a href="../modules.html">Exports</a></li></ul></nav><nav class="tsd-navigation secondary menu-sticky"><ul><li class="current tsd-kind-interface"><a href="CreateRunnerProps.html" class="tsd-kind-icon">Create<wbr/>Runner<wbr/>Props</a><ul><li class="tsd-kind-property tsd-parent-kind-interface"><a href="CreateRunnerProps.html#logger" class="tsd-kind-icon">logger</a></li><li class="tsd-kind-property tsd-parent-kind-interface"><a href="CreateRunnerProps.html#options" class="tsd-kind-icon">options</a></li></ul></li></ul></nav></div></div></div><footer class="with-border-bottom"><div class="container"><h2>Legend</h2><div class="tsd-legend-group"><ul class="tsd-legend"><li class="tsd-kind-property tsd-parent-kind-interface"><span class="tsd-kind-icon">Property</span></li></ul></div><h2>Settings</h2><p>Theme <select id="theme"><option value="os">OS</option><option value="light">Light</option><option value="dark">Dark</option></select></p></div></footer><div class="container tsd-generator"><p>Generated using <a href="https://typedoc.org/" target="_blank">TypeDoc</a></p></div><div class="overlay"></div><script src="../assets/main.js"></script></body></html>