@mintlify/scraping 3.0.14 → 3.0.16

package/src/scraping/scrapePage.ts

@@ -1,5 +1,6 @@
-import path from "path";
-import { createPage, getOrigin } from "../util.js";
+import path from 'path';
+
+import { createPage, getOrigin } from '../util.js';
 
 export async function scrapePage(
   scrapeFunc: ScrapePageFn,
@@ -10,7 +11,7 @@ export async function scrapePage(
 ) {
   const origin = getOrigin(href);
   const cwd = process.cwd();
-  const imageBaseDir = path.join(cwd, "images");
+  const imageBaseDir = path.join(cwd, 'images');
 
   const { title, description, markdown } = await scrapeFunc(
     html,

package/src/scraping/scrapePageCommands.ts

@@ -1,23 +1,22 @@
-import axios from "axios";
-import { scrapePage } from "./scrapePage.js";
-import { scrapeDocusaurusPage } from "./site-scrapers/scrapeDocusaurusPage.js";
-import { scrapeGitBookPage } from "./site-scrapers/scrapeGitBookPage.js";
-import { scrapeReadMePage } from "./site-scrapers/scrapeReadMePage.js";
-import { detectFramework, Frameworks } from "./detectFramework.js";
-import { getHrefFromArgs } from "../util.js";
-import { getHtmlWithPuppeteer } from "../browser.js";
-import { ArgumentsCamelCase } from "yargs";
-import { scrapeIntercomPage } from "./site-scrapers/Intercom/scrapeIntercomPage.js";
+import axios from 'axios';
+import { ArgumentsCamelCase } from 'yargs';
+
+import { getHtmlWithPuppeteer } from '../browser.js';
+import { getHrefFromArgs } from '../util.js';
+import { detectFramework, Frameworks } from './detectFramework.js';
+import { scrapePage } from './scrapePage.js';
+import { scrapeIntercomPage } from './site-scrapers/Intercom/scrapeIntercomPage.js';
+import { scrapeDocusaurusPage } from './site-scrapers/scrapeDocusaurusPage.js';
+import { scrapeGitBookPage } from './site-scrapers/scrapeGitBookPage.js';
+import { scrapeReadMePage } from './site-scrapers/scrapeReadMePage.js';
 
 function validateFramework(framework) {
   if (!framework) {
-    console.log(
-      "Could not detect the framework automatically. Please use one of:"
-    );
-    console.log("scrape-page-docusaurus");
-    console.log("scrape-page-gitbook");
-    console.log("scrape-page-readme");
-    console.log("scrape-page-intercom");
+    console.log('Could not detect the framework automatically. Please use one of:');
+    console.log('scrape-page-docusaurus');
+    console.log('scrape-page-gitbook');
+    console.log('scrape-page-readme');
+    console.log('scrape-page-intercom');
     return process.exit(1);
   }
 }
@@ -47,7 +46,7 @@ export async function scrapePageAutomatically(argv: any) {
 
   validateFramework(framework);
 
-  console.log("Detected framework: " + framework);
+  console.log('Detected framework: ' + framework);
 
   switch (framework) {
     case Frameworks.DOCUSAURUS:

package/src/scraping/scrapeSection.ts

@@ -1,5 +1,6 @@
-import path from "path";
-import { objToReadableString } from "../util.js";
+import path from 'path';
+
+import { objToReadableString } from '../util.js';
 
 export async function scrapeSection(
   scrapeFunc: ScrapeSectionFn,
@@ -8,21 +9,12 @@ export async function scrapeSection(
   overwrite: boolean,
   version: string | undefined
 ) {
-  console.log(
-    `Started scraping${overwrite ? ", overwrite mode is on" : ""}...`
-  );
+  console.log(`Started scraping${overwrite ? ', overwrite mode is on' : ''}...`);
   const cwd = process.cwd();
-  const imageBaseDir = path.join(cwd, "images");
+  const imageBaseDir = path.join(cwd, 'images');
 
-  const groupsConfig = await scrapeFunc(
-    html,
-    origin,
-    cwd,
-    imageBaseDir,
-    overwrite,
-    version
-  );
-  console.log("Finished scraping.");
-  console.log("Add the following to your navigation in mint.json:");
+  const groupsConfig = await scrapeFunc(html, origin, cwd, imageBaseDir, overwrite, version);
+  console.log('Finished scraping.');
+  console.log('Add the following to your navigation in mint.json:');
   console.log(objToReadableString(groupsConfig));
 }

package/src/scraping/scrapeSectionCommands.ts

@@ -1,15 +1,16 @@
-import axios from "axios";
-import { detectFramework, Frameworks } from "./detectFramework.js";
-import { getHrefFromArgs, getOrigin } from "../util.js";
-import { scrapeSection } from "./scrapeSection.js";
-import { scrapeDocusaurusSection } from "./site-scrapers/scrapeDocusaurusSection.js";
-import openNestedDocusaurusMenus from "./site-scrapers/openNestedDocusaurusMenus.js";
-import { scrapeGitBookSection } from "./site-scrapers/scrapeGitBookSection.js";
-import openNestedGitbookMenus from "./site-scrapers/openNestedGitbookMenus.js";
-import { scrapeReadMeSection } from "./site-scrapers/scrapeReadMeSection.js";
-import { startBrowser } from "../browser.js";
-import { ArgumentsCamelCase } from "yargs";
-import { scrapeIntercomSection } from "./site-scrapers/Intercom/scrapeIntercomSection.js";
+import axios from 'axios';
+import { ArgumentsCamelCase } from 'yargs';
+
+import { startBrowser } from '../browser.js';
+import { getHrefFromArgs, getOrigin } from '../util.js';
+import { detectFramework, Frameworks } from './detectFramework.js';
+import { scrapeSection } from './scrapeSection.js';
+import { scrapeIntercomSection } from './site-scrapers/Intercom/scrapeIntercomSection.js';
+import openNestedDocusaurusMenus from './site-scrapers/openNestedDocusaurusMenus.js';
+import openNestedGitbookMenus from './site-scrapers/openNestedGitbookMenus.js';
+import { scrapeDocusaurusSection } from './site-scrapers/scrapeDocusaurusSection.js';
+import { scrapeGitBookSection } from './site-scrapers/scrapeGitBookSection.js';
+import { scrapeReadMeSection } from './site-scrapers/scrapeReadMeSection.js';
 
 export async function scrapeSectionAxiosWrapper(
   argv: ArgumentsCamelCase,
@@ -18,13 +19,7 @@ export async function scrapeSectionAxiosWrapper(
   const href = getHrefFromArgs(argv);
   const res = await axios.get(href);
   const html = res.data;
-  await scrapeSection(
-    scrapeFunc,
-    html,
-    getOrigin(href),
-    !!argv.overwrite,
-    undefined
-  );
+  await scrapeSection(scrapeFunc, html, getOrigin(href), !!argv.overwrite, undefined);
   process.exit(0);
 }
 
@@ -41,11 +36,7 @@ export async function scrapeDocusaurusSectionCommand(
 }
 
 export async function scrapeGitbookSectionCommand(argv: any) {
-  await scrapeSectionOpeningAllNested(
-    argv,
-    openNestedGitbookMenus,
-    scrapeGitBookSection
-  );
+  await scrapeSectionOpeningAllNested(argv, openNestedGitbookMenus, scrapeGitBookSection);
 }
 
 async function scrapeSectionOpeningAllNested(
@@ -59,18 +50,12 @@ async function scrapeSectionOpeningAllNested(
   const browser = await startBrowser();
   const page = await browser.newPage();
   await page.goto(href, {
-    waitUntil: "networkidle2",
+    waitUntil: 'networkidle2',
   });
 
   const html = await openLinks(page);
   browser.close();
-  await scrapeSection(
-    scrapeFunc,
-    html,
-    getOrigin(href),
-    !!argv.overwrite,
-    version
-  );
+  await scrapeSection(scrapeFunc, html, getOrigin(href), !!argv.overwrite, version);
   process.exit(0);
 }
 
@@ -81,7 +66,7 @@ export async function scrapeSectionAutomatically(argv: any) {
   const { framework, version } = detectFramework(html);
 
   validateFramework(framework);
-  console.log("Detected framework: " + framework);
+  console.log('Detected framework: ' + framework);
 
   switch (framework) {
     case Frameworks.DOCUSAURUS:
@@ -102,7 +87,7 @@ export async function scrapeSectionAutomatically(argv: any) {
 function validateFramework(framework: Frameworks | undefined) {
   if (!framework) {
     console.log(
-      "Could not detect the framework automatically. We only support Docusaurus (V2 and V3), GitBook, and ReadMe."
+      'Could not detect the framework automatically. We only support Docusaurus (V2 and V3), GitBook, and ReadMe.'
     );
     process.exit();
   }

package/src/scraping/site-scrapers/Intercom/scrapeIntercomPage.ts

@@ -1,7 +1,8 @@
-import cheerio from "cheerio";
-import { NodeHtmlMarkdown } from "node-html-markdown";
-import downloadAllImages from "../../downloadAllImages.js";
-import replaceImagePaths from "../../replaceImagePaths.js";
+import cheerio from 'cheerio';
+import { NodeHtmlMarkdown } from 'node-html-markdown';
+
+import downloadAllImages from '../../downloadAllImages.js';
+import replaceImagePaths from '../../replaceImagePaths.js';
 
 export async function scrapeIntercomPage(
   html: string,
@@ -13,11 +14,11 @@ export async function scrapeIntercomPage(
 ) {
   const $ = cheerio.load(html);
 
-  const titleComponent = $(".t__h1").first();
+  const titleComponent = $('.t__h1').first();
   const title = titleComponent.text().trim();
-  const description = $(".article__desc", titleComponent.parent()).text().trim();
+  const description = $('.article__desc', titleComponent.parent()).text().trim();
 
-  const content = $("article").first();
+  const content = $('article').first();
   const contentHtml = $.html(content);
 
   const origToWritePath = await downloadAllImages(
@@ -33,16 +34,16 @@ export async function scrapeIntercomPage(
   let markdown = nhm.translate(contentHtml);
 
   // Keep headers on one line
-  markdown = markdown.replace(/# \n\n/g, "# ");
+  markdown = markdown.replace(/# \n\n/g, '# ');
 
   // Remove unnecessary nonwidth blank space characters
-  markdown = markdown.replace(/\u200b/g, "");
+  markdown = markdown.replace(/\u200b/g, '');
 
   // Reduce unnecessary blank lines
-  markdown = markdown.replace(/\n\n\n/g, "\n\n");
+  markdown = markdown.replace(/\n\n\n/g, '\n\n');
 
   // Mintlify doesn't support bolded headers, remove the asterisks
-  markdown = markdown.replace(/(\n#+) \*\*(.*)\*\*\n/g, "$1 $2\n");
+  markdown = markdown.replace(/(\n#+) \*\*(.*)\*\*\n/g, '$1 $2\n');
   if (origToWritePath) {
     markdown = replaceImagePaths(origToWritePath, cliDir, markdown);
   }

package/src/scraping/site-scrapers/Intercom/scrapeIntercomSection.ts

@@ -1,8 +1,9 @@
-import cheerio from "cheerio";
-import { scrapeIntercomPage } from "./scrapeIntercomPage.js";
-import { scrapeGettingFileNameFromUrl } from "../../scrapeGettingFileNameFromUrl.js";
-import downloadLogoImage from "../../downloadLogoImage.js";
-import axios from "axios";
+import axios from 'axios';
+import cheerio from 'cheerio';
+
+import downloadLogoImage from '../../downloadLogoImage.js';
+import { scrapeGettingFileNameFromUrl } from '../../scrapeGettingFileNameFromUrl.js';
+import { scrapeIntercomPage } from './scrapeIntercomPage.js';
 
 export async function scrapeIntercomSection(
   html: string,
@@ -14,27 +15,25 @@ export async function scrapeIntercomSection(
 ): Promise<MintNavigationEntry[]> {
   let $ = cheerio.load(html);
 
-  const logoSrc = $(".header__logo img").first().attr("src");
+  const logoSrc = $('.header__logo img').first().attr('src');
   downloadLogoImage(logoSrc, imageBaseDir, origin, overwrite);
 
-  const collectionsLink = $(".section .g__space a");
-  const collectionsMap = collectionsLink
-    .toArray()
-    .map(async (s: cheerio.Element) => {
-      const href = $(s).attr("href");
-      const res = await axios.get(`${origin}${href}`);
-      const html = res.data;
-      $ = cheerio.load(html);
-      const sectionTitle = $(".collection h1").first().text().trim();
-      const sectionPages = $(".section .g__space a")
-        .toArray()
-        .map((s: cheerio.Element) => $(s).attr("href"))
-        .filter((page) => page !== undefined) as string[];
-      return {
-        group: sectionTitle,
-        pages: sectionPages,
-      };
-    });
+  const collectionsLink = $('.section .g__space a');
+  const collectionsMap = collectionsLink.toArray().map(async (s: cheerio.Element) => {
+    const href = $(s).attr('href');
+    const res = await axios.get(`${origin}${href}`);
+    const html = res.data;
+    $ = cheerio.load(html);
+    const sectionTitle = $('.collection h1').first().text().trim();
+    const sectionPages = $('.section .g__space a')
+      .toArray()
+      .map((s: cheerio.Element) => $(s).attr('href'))
+      .filter((page) => page !== undefined) as string[];
+    return {
+      group: sectionTitle,
+      pages: sectionPages,
+    };
+  });
 
   const collections: MintNavigation[] = await Promise.all(collectionsMap);
 

package/src/scraping/site-scrapers/alternateGroupTitle.ts

@@ -4,5 +4,5 @@ export default function alternateGroupTitle(firstLink: cheerio.Cheerio, pages) {
   if (pages.length > 0) {
     return firstLink?.text();
   }
-  return "";
+  return '';
 }

package/src/scraping/site-scrapers/links-per-group/getDocusaurusLinksPerGroup.ts

@@ -1,12 +1,12 @@
-import alternateGroupTitle from "../alternateGroupTitle.js";
-import getLinksRecursively from "./getLinksRecursively.js";
+import alternateGroupTitle from '../alternateGroupTitle.js';
+import getLinksRecursively from './getLinksRecursively.js';
 
 export function getDocusaurusLinksPerGroup(
   navigationSections: any,
   $: any,
   version: string | undefined
 ) {
-  if (version === "3" || version === "2") {
+  if (version === '3' || version === '2') {
     return getDocusaurusLinksPerGroupLoop(navigationSections, $);
   }
   return [];
@@ -17,21 +17,18 @@ function getDocusaurusLinksPerGroupLoop(navigationSections: any, $: any) {
     const section = $(s);
 
     // Links without a group
-    if (section.hasClass("theme-doc-sidebar-item-link")) {
-      const linkHref = section.find("a[href]").first().attr("href");
+    if (section.hasClass('theme-doc-sidebar-item-link')) {
+      const linkHref = section.find('a[href]').first().attr('href');
       return {
-        group: "",
+        group: '',
         pages: [linkHref],
       };
     }
 
-    const firstLink = section
-      .find(".menu__list-item-collapsible")
-      .first()
-      .find("a[href]");
+    const firstLink = section.find('.menu__list-item-collapsible').first().find('a[href]');
 
     const sectionTitle = firstLink.text();
-    const firstHref = firstLink.attr("href");
+    const firstHref = firstLink.attr('href');
     const linkSections = section.children().eq(1).children();
 
     const pages = getLinksRecursively(linkSections, $);

package/src/scraping/site-scrapers/links-per-group/getLinksRecursively.ts

@@ -9,20 +9,20 @@ export default function getLinksRecursively(linkSections: any, $: any) {
       const subsection = $(s);
       let link = subsection.children().first();
 
-      if (!link.attr("href")) {
+      if (!link.attr('href')) {
         // Docusaurus nests the <a> inside a <div>
-        link = link.find("a[href]").first();
+        link = link.find('a[href]').first();
       }
-      const linkHref = link.attr("href");
+      const linkHref = link.attr('href');
 
       // Skip missing links. For example, GitBook uses
       // empty divs are used for styling a line beside the nav.
       // Skip external links until Mintlify supports them
       if (
         !linkHref ||
-        linkHref === "#" ||
-        linkHref.startsWith("https://") ||
-        linkHref.startsWith("http://")
+        linkHref === '#' ||
+        linkHref.startsWith('https://') ||
+        linkHref.startsWith('http://')
       ) {
         return undefined;
       }

package/src/scraping/site-scrapers/links-per-group/getLinksRecursivelyGitBook.ts

@@ -14,16 +14,16 @@ export default function getLinksRecursivelyGitBook(linkSections: any, $: any) {
       }
 
       const link = subsection.children().first();
-      const linkHref = link.attr("href");
+      const linkHref = link.attr('href');
 
       // Skip missing links. For example, GitBook uses
       // empty divs are used for styling a line beside the nav.
       // Skip external links until Mintlify supports them
       if (
         !linkHref ||
-        linkHref === "#" ||
-        linkHref.startsWith("https://") ||
-        linkHref.startsWith("http://")
+        linkHref === '#' ||
+        linkHref.startsWith('https://') ||
+        linkHref.startsWith('http://')
       ) {
         return undefined;
       }

package/src/scraping/site-scrapers/openNestedDocusaurusMenus.ts

@@ -1,8 +1,8 @@
-import { Page } from "puppeteer";
+import { Page } from 'puppeteer';
 
 export default async function openNestedDocusaurusMenus(page: Page) {
   let prevEncountered: string[] = [];
-  let encounteredHref = ["fake-href-to-make-loop-run-at-least-once"];
+  let encounteredHref = ['fake-href-to-make-loop-run-at-least-once'];
 
   // Loop until we've encountered every link
   while (!encounteredHref.every((href) => prevEncountered.includes(href))) {
@@ -10,15 +10,15 @@ export default async function openNestedDocusaurusMenus(page: Page) {
     encounteredHref = await page.evaluate(
       (encounteredHref) => {
         const collapsible: HTMLElement[] = Array.from(
-          document.querySelectorAll(".menu__link.menu__link--sublist")
+          document.querySelectorAll('.menu__link.menu__link--sublist')
         );
 
         const linksFound: string[] = [];
         collapsible.forEach(async (collapsibleItem: HTMLElement) => {
-          const href = collapsibleItem?.getAttribute("href");
+          const href = collapsibleItem?.getAttribute('href');
 
           // Should never occur but we keep it as a fail-safe
-          if (href?.startsWith("https://") || href?.startsWith("http://")) {
+          if (href?.startsWith('https://') || href?.startsWith('http://')) {
             return;
           }
 

package/src/scraping/site-scrapers/openNestedGitbookMenus.ts

@@ -1,4 +1,4 @@
-import { Page } from "puppeteer";
+import { Page } from 'puppeteer';
 
 export default async function openNestedGitbookMenus(page: Page) {
   let clickedAny = true;
@@ -7,9 +7,7 @@ export default async function openNestedGitbookMenus(page: Page) {
   while (clickedAny) {
     clickedAny = await page.evaluate(() => {
       // Right pointing arrow. Only closed menus have this icon
-      const icons: HTMLElement[] = Array.from(
-        document.querySelectorAll('path[d="M9 18l6-6-6-6"]')
-      );
+      const icons: HTMLElement[] = Array.from(document.querySelectorAll('path[d="M9 18l6-6-6-6"]'));
 
       icons.forEach(async (icon: HTMLElement) => {
         const toClick = icon?.parentElement?.parentElement;

package/src/scraping/site-scrapers/scrapeDocusaurusPage.ts

@@ -1,7 +1,8 @@
-import cheerio from "cheerio";
-import { NodeHtmlMarkdown } from "node-html-markdown";
-import downloadAllImages from "../downloadAllImages.js";
-import replaceImagePaths from "../replaceImagePaths.js";
+import cheerio from 'cheerio';
+import { NodeHtmlMarkdown } from 'node-html-markdown';
+
+import downloadAllImages from '../downloadAllImages.js';
+import replaceImagePaths from '../replaceImagePaths.js';
 
 export async function scrapeDocusaurusPage(
   html: string,
@@ -17,24 +18,22 @@ export async function scrapeDocusaurusPage(
 }> {
   const $ = cheerio.load(html);
 
-  const article =
-    version === "3" ? $(".theme-doc-markdown").first() : $("article").first();
+  const article = version === '3' ? $('.theme-doc-markdown').first() : $('article').first();
 
   if (article.length === 0) {
     // Index pages with no additional text don't have the markdown class
     return {
-      title: ''
+      title: '',
     };
   }
 
-  const titleComponent = article.find("h1");
+  const titleComponent = article.find('h1');
   const title = titleComponent.text().trim();
 
   // Do not include title in the content when we insert it in our metadata
   titleComponent.remove();
 
-  const markdownContent =
-    version === "3" ? article : article.find(".markdown").first();
+  const markdownContent = version === '3' ? article : article.find('.markdown').first();
 
   const origToWritePath = await downloadAllImages(
     $,
@@ -50,10 +49,8 @@ export async function scrapeDocusaurusPage(
   let markdown = markdownHtml ? nhm.translate(markdownHtml) : null;
 
   if (markdown == null) {
-    console.error(
-      "We do not support scraping this page. Content will be empty"
-    );
-    return { title, description: undefined, markdown: "" };
+    console.error('We do not support scraping this page. Content will be empty');
+    return { title, description: undefined, markdown: '' };
   }
 
   // Description only exists in meta tags. The code is commented out because its prone to incorrectly
@@ -70,16 +67,16 @@ export async function scrapeDocusaurusPage(
   // When we parse their HTML the parser adds things like:
   // [](#setup "Direct link to heading")
   // to the end of each header.
-  markdown = markdown.replace(/\[\]\(#.+ ".+"\)\n/g, "\n");
+  markdown = markdown.replace(/\[\]\(#.+ ".+"\)\n/g, '\n');
 
   // Remove unnecessary nonwidth blank space characters
-  markdown = markdown.replace(/\u200b/g, "");
+  markdown = markdown.replace(/\u200b/g, '');
 
   // Reduce unnecessary blank lines
-  markdown = markdown.replace(/\n\n\n/g, "\n\n");
+  markdown = markdown.replace(/\n\n\n/g, '\n\n');
 
   // Mintlify doesn't support bolded headers, remove the asterisks
-  markdown = markdown.replace(/(\n#+) \*\*(.*)\*\*\n/g, "$1 $2\n");
+  markdown = markdown.replace(/(\n#+) \*\*(.*)\*\*\n/g, '$1 $2\n');
   if (origToWritePath) {
     markdown = replaceImagePaths(origToWritePath, cliDir, markdown);
   }

package/src/scraping/site-scrapers/scrapeDocusaurusSection.ts

@@ -1,9 +1,10 @@
-import cheerio from "cheerio";
-import { scrapeGettingFileNameFromUrl } from "../scrapeGettingFileNameFromUrl.js";
-import combineNavWithEmptyGroupTitles from "../combineNavWithEmptyGroupTitles.js";
-import { scrapeDocusaurusPage } from "./scrapeDocusaurusPage.js";
-import { getDocusaurusLinksPerGroup } from "./links-per-group/getDocusaurusLinksPerGroup.js";
-import downloadLogoImage from "../downloadLogoImage.js";
+import cheerio from 'cheerio';
+
+import combineNavWithEmptyGroupTitles from '../combineNavWithEmptyGroupTitles.js';
+import downloadLogoImage from '../downloadLogoImage.js';
+import { scrapeGettingFileNameFromUrl } from '../scrapeGettingFileNameFromUrl.js';
+import { getDocusaurusLinksPerGroup } from './links-per-group/getDocusaurusLinksPerGroup.js';
+import { scrapeDocusaurusPage } from './scrapeDocusaurusPage.js';
 
 export async function scrapeDocusaurusSection(
   html: string,
@@ -16,18 +17,14 @@ export async function scrapeDocusaurusSection(
   const $ = cheerio.load(html);
 
   // Download the logo
-  const logoSrc = $(".navbar__logo img").attr("src");
+  const logoSrc = $('.navbar__logo img').attr('src');
   downloadLogoImage(logoSrc, imageBaseDir, origin, overwrite);
 
   // Get all the navigation sections
-  const navigationSections = $(".theme-doc-sidebar-menu").first().children();
+  const navigationSections = $('.theme-doc-sidebar-menu').first().children();
 
   // Get all links per group
-  const groupsConfig: MintNavigation[] = getDocusaurusLinksPerGroup(
-    navigationSections,
-    $,
-    version
-  );
+  const groupsConfig: MintNavigation[] = getDocusaurusLinksPerGroup(navigationSections, $, version);
 
   // Merge groups with empty titles together
   const reducedGroupsConfig = combineNavWithEmptyGroupTitles(groupsConfig);
@@ -48,7 +45,7 @@ export async function scrapeDocusaurusSection(
               scrapeDocusaurusPage,
               false,
               version,
-              "/docs"
+              '/docs'
             )
           )
         )

package/src/scraping/site-scrapers/scrapeGitBookPage.ts

@@ -1,7 +1,8 @@
-import cheerio from "cheerio";
-import { NodeHtmlMarkdown } from "node-html-markdown";
-import downloadAllImages from "../downloadAllImages.js";
-import replaceImagePaths from "../replaceImagePaths.js";
+import cheerio from 'cheerio';
+import { NodeHtmlMarkdown } from 'node-html-markdown';
+
+import downloadAllImages from '../downloadAllImages.js';
+import replaceImagePaths from '../replaceImagePaths.js';
 
 export async function scrapeGitBookPage(
   html: string,
@@ -16,9 +17,7 @@ export async function scrapeGitBookPage(
   const titleComponent = $('[data-testid="page.title"]').first();
   const titleAndDescription = titleComponent.parent().parent().parent().text();
 
-  const description = titleAndDescription
-    .replace(titleComponent.text(), "")
-    .trim();
+  const description = titleAndDescription.replace(titleComponent.text(), '').trim();
   const title = titleComponent.text().trim();
 
   const content = $('[data-testid="page.contentEditor"]').first();
@@ -32,8 +31,8 @@ export async function scrapeGitBookPage(
       .children()
       .toArray()
       .map((d) => $(d).text())
-      .filter((text) => text !== "")
-      .join("\n");
+      .filter((text) => text !== '')
+      .join('\n');
     code.replaceWith(`<pre><code>${codeContent}</code></pre>`);
   });
 
@@ -42,7 +41,7 @@ export async function scrapeGitBookPage(
   const modifyFileName = (fileName: string) =>
     // Remove GitBook metadata from the start
     // The first four %2F split metadata fields. Remaining ones are part of the file name.
-    fileName.split("%2F").slice(4).join("%2F");
+    fileName.split('%2F').slice(4).join('%2F');
 
   const origToWritePath = await downloadAllImages(
     $,
@@ -57,16 +56,16 @@ export async function scrapeGitBookPage(
   let markdown = nhm.translate(contentHtml);
 
   // Keep headers on one line
-  markdown = markdown.replace(/# \n\n/g, "# ");
+  markdown = markdown.replace(/# \n\n/g, '# ');
 
   // Remove unnecessary nonwidth blank space characters
-  markdown = markdown.replace(/\u200b/g, "");
+  markdown = markdown.replace(/\u200b/g, '');
 
   // Reduce unnecessary blank lines
-  markdown = markdown.replace(/\n\n\n/g, "\n\n");
+  markdown = markdown.replace(/\n\n\n/g, '\n\n');
 
   // Mintlify doesn't support bolded headers, remove the asterisks
-  markdown = markdown.replace(/(\n#+) \*\*(.*)\*\*\n/g, "$1 $2\n");
+  markdown = markdown.replace(/(\n#+) \*\*(.*)\*\*\n/g, '$1 $2\n');
   if (origToWritePath) {
     markdown = replaceImagePaths(origToWritePath, cliDir, markdown);
   }