@mintlify/cli 4.0.953 → 4.0.955

package/bin/cli.js

@@ -11,6 +11,7 @@ import { jsx as _jsx, jsxs as _jsxs } from "react/jsx-runtime";
 import { validate, getOpenApiDocumentFromUrl, isAllowedLocalSchemaUrl } from '@mintlify/common';
 import { getBrokenInternalLinks, renameFilesAndUpdateLinksInContent } from '@mintlify/link-rot';
 import { addLog, dev, validateBuild, ErrorLog, SpinnerLog, SuccessLog, Logs, clearLogs, BrokenLinksLog, WarningLog, } from '@mintlify/previewing';
+import { checkUrl } from '@mintlify/scraping';
 import { render, Text } from 'ink';
 import path from 'path';
 import yargs from 'yargs';
@@ -20,6 +21,7 @@ import { checkPort, checkForMintJson, checkNodeVersion, upgradeConfig, checkForD
 import { init } from './init.js';
 import { mdxLinter } from './mdxLinter.js';
 import { migrateMdx } from './migrateMdx.js';
+import { scrapeSite, scrapePage, scrapeOpenApi } from './scrape.js';
 import { update } from './update.js';
 export const cli = ({ packageName = 'mint' }) => {
     render(_jsx(Logs, {}));
@@ -290,6 +292,59 @@ export const cli = ({ packageName = 'mint' }) => {
             yield terminate(1);
         }
     }))
+        .command('scrape', 'Scrape documentation from external sites', (yargs) => yargs
+        .command(['$0 <url>', 'site <url>'], 'Scrape an entire documentation site', (yargs) => yargs
+        .positional('url', {
+        describe: 'The URL of the documentation site to scrape',
+        type: 'string',
+        demandOption: true,
+    })
+        .option('filter', {
+        describe: 'Only scrape URLs matching this path filter (e.g. /docs will match /docs and /docs/*)',
+        type: 'string',
+        alias: 'f',
+    })
+        .check(checkUrl), (_a) => __awaiter(void 0, [_a], void 0, function* ({ url, filter }) {
+        yield scrapeSite(url, filter);
+    }))
+        .command('page <url>', 'Scrape a single documentation page', (yargs) => yargs
+        .positional('url', {
+        describe: 'The URL of the documentation page to scrape',
+        type: 'string',
+        demandOption: true,
+    })
+        .check(checkUrl), (_a) => __awaiter(void 0, [_a], void 0, function* ({ url }) {
+        yield scrapePage(url);
+    }))
+        .command('openapi <openapiLocation>', 'Generate MDX files from an OpenAPI spec', (yargs) => yargs
+        .positional('openapiLocation', {
+        describe: 'The filename or URL location of the OpenAPI spec',
+        type: 'string',
+        demandOption: true,
+    })
+        .option('writeFiles', {
+        describe: 'Whether or not to write the frontmatter files',
+        default: true,
+        type: 'boolean',
+        alias: 'w',
+    })
+        .option('outDir', {
+        describe: 'The folder in which to write any created frontmatter files',
+        type: 'string',
+        alias: 'o',
+    })
+        .option('overwrite', {
+        describe: 'Whether or not to overwrite existing files',
+        default: false,
+        type: 'boolean',
+    }), (argv) => __awaiter(void 0, void 0, void 0, function* () {
+        yield scrapeOpenApi({
+            openapiLocation: argv.openapiLocation,
+            writeFiles: argv.writeFiles,
+            outDir: argv.outDir,
+            overwrite: argv.overwrite,
+        });
+    })))
         // Print the help menu when the user enters an invalid command.
         .strictCommands()
         .demandCommand(1, 'unknown command. see above for the list of supported commands.')

package/bin/scrape.js

@@ -0,0 +1,108 @@
+var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
+    function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
+    return new (P || (P = Promise))(function (resolve, reject) {
+        function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
+        function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
+        function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
+        step((generator = generator.apply(thisArg, _arguments || [])).next());
+    });
+};
+import { jsx as _jsx } from "react/jsx-runtime";
+import { addLog, ErrorLog, SuccessLog, SpinnerLog, InfoLog } from '@mintlify/previewing';
+import { scrapePageGroup, scrapeAllSiteTabs, htmlToHast, detectFramework, framework, fetchPageHtml, write, getErrorMessage, generateOpenApiPages, FINAL_SUCCESS_MESSAGE, } from '@mintlify/scraping';
+import { upgradeToDocsConfig } from '@mintlify/validation';
+import { terminate } from './helpers.js';
+export function scrapeSite(url, filter) {
+    return __awaiter(this, void 0, void 0, function* () {
+        try {
+            const urlObj = new URL(url);
+            addLog(_jsx(SpinnerLog, { message: `Fetching ${urlObj.toString()}...` }));
+            const html = yield fetchPageHtml(urlObj);
+            addLog(_jsx(SuccessLog, { message: `Successfully retrieved HTML from ${urlObj.toString()}` }));
+            addLog(_jsx(SpinnerLog, { message: "Scraping site..." }));
+            const result = yield scrapeAllSiteTabs(html, urlObj, { filter });
+            if (result.success) {
+                const mintConfig = result.data;
+                const docsConfig = upgradeToDocsConfig(mintConfig, {
+                    shouldUpgradeTheme: true,
+                });
+                docsConfig.theme = 'aspen';
+                write('docs.json', JSON.stringify(docsConfig, undefined, 2));
+                addLog(_jsx(SuccessLog, { message: FINAL_SUCCESS_MESSAGE }));
+            }
+            else {
+                addLog(_jsx(ErrorLog, { message: result.message }));
+                yield terminate(1);
+            }
+            yield terminate(0);
+        }
+        catch (error) {
+            const errorMessage = getErrorMessage(error);
+            addLog(_jsx(ErrorLog, { message: errorMessage }));
+            yield terminate(1);
+        }
+    });
+}
+export function scrapePage(url) {
+    return __awaiter(this, void 0, void 0, function* () {
+        try {
+            const urlObj = new URL(url);
+            addLog(_jsx(SpinnerLog, { message: `Fetching ${urlObj.toString()}...` }));
+            const html = yield fetchPageHtml(urlObj);
+            addLog(_jsx(SuccessLog, { message: `Successfully retrieved HTML from ${urlObj.toString()}` }));
+            const hast = htmlToHast(html);
+            detectFramework(hast);
+            const needsBrowser = framework.vendor === 'gitbook';
+            addLog(_jsx(SpinnerLog, { message: "Scraping page..." }));
+            const results = yield scrapePageGroup([urlObj], needsBrowser);
+            const result = results[0] || {
+                success: false,
+                message: `An unknown error occurred when scraping ${url}`,
+            };
+            if (result.success) {
+                addLog(_jsx(SuccessLog, { message: `Successfully scraped ${url} ${result.data ? `into ${result.data[1]}` : ''}` }));
+            }
+            else {
+                addLog(_jsx(ErrorLog, { message: result.message }));
+                yield terminate(1);
+            }
+            yield terminate(0);
+        }
+        catch (error) {
+            const errorMessage = getErrorMessage(error);
+            addLog(_jsx(ErrorLog, { message: errorMessage }));
+            yield terminate(1);
+        }
+    });
+}
+export function scrapeOpenApi(_a) {
+    return __awaiter(this, arguments, void 0, function* ({ openapiLocation, writeFiles, outDir, overwrite, }) {
+        try {
+            addLog(_jsx(SpinnerLog, { message: `Processing OpenAPI spec from ${openapiLocation}...` }));
+            const { nav, isUrl } = yield generateOpenApiPages(openapiLocation, {
+                openApiFilePath: undefined,
+                version: undefined,
+                writeFiles,
+                outDir,
+                overwrite,
+            });
+            addLog(_jsx(SuccessLog, { message: "Successfully generated OpenAPI pages" }));
+            addLog(_jsx(InfoLog, { message: "Navigation object suggestion:" }));
+            addLog(_jsx(InfoLog, { message: JSON.stringify(nav, undefined, 2) }));
+            if (isUrl) {
+                addLog(_jsx(InfoLog, { message: "OpenAPI location suggestion:" }));
+                addLog(_jsx(InfoLog, { message: `openapi: ${openapiLocation}` }));
+            }
+            yield terminate(0);
+        }
+        catch (error) {
+            if (error instanceof Error) {
+                addLog(_jsx(ErrorLog, { message: error.message }));
+            }
+            else {
+                addLog(_jsx(ErrorLog, { message: String(error) }));
+            }
+            yield terminate(1);
+        }
+    });
+}