@xbrowser/cli 1.7.1 → 1.7.3

package/dist/cli.js

@@ -2795,22 +2795,59 @@ async function extractLinks(page, origin) {
   }, origin);
 }
 async function detectSpaRoutes(page, origin) {
-  return page.evaluate((evalOrigin) => {
-    const routeSet = /* @__PURE__ */ new Set();
+  const routeSet = /* @__PURE__ */ new Set();
+  const pathRegex = /['"`](\/[a-zA-Z0-9_\-/]+)['"`]/g;
+  const isParamRoute = (p) => p.includes(":") || p.includes("*");
+  function extractPaths(source) {
+    let match;
+    while ((match = pathRegex.exec(source)) !== null) {
+      const path3 = match[1];
+      if (!isParamRoute(path3)) routeSet.add(path3);
+    }
+  }
+  const scriptData = await page.evaluate(() => {
+    const scripts = Array.from(document.querySelectorAll("script"));
+    return {
+      inlineContent: scripts.map((s) => s.textContent || "").join("\n"),
+      externalUrls: scripts.map((s) => s.src).filter((src) => src && !src.includes("analytics") && !src.includes("google") && !src.includes("baidu"))
+    };
+  });
+  const { inlineContent, externalUrls } = scriptData;
+  extractPaths(inlineContent);
+  for (const src of externalUrls) {
     try {
-      const scripts = document.querySelectorAll("script");
-      const allContent = Array.from(scripts).map((s) => s.textContent || "").join("\n");
-      const pathRegex = /['"`](\/[a-zA-Z0-9_\-/]+)['"`]/g;
-      let match;
-      while ((match = pathRegex.exec(allContent)) !== null) {
-        const path3 = match[1];
-        if (path3.includes(":") || path3.includes("*") || routeSet.has(path3)) continue;
-        routeSet.add(path3);
+      const absoluteSrc = src.startsWith("http") ? src : new URL(src, page.url()).href;
+      const resp = await fetch(absoluteSrc, { signal: AbortSignal.timeout(5e3) });
+      if (resp.ok) {
+        const text = await resp.text();
+        extractPaths(text);
       }
     } catch {
     }
-    return Array.from(routeSet).map((path3) => `${evalOrigin.replace(/\/$/, "")}${path3}`);
-  }, origin);
+  }
+  try {
+    const vueRoutes = await page.evaluate((evalOrigin) => {
+      const routes2 = [];
+      const win = window;
+      const vueApp = win.__vue_app__;
+      const gp = vueApp?.config?.globalProperties;
+      const router = gp?.$router;
+      const routeList = router?.options?.routes;
+      if (routeList) {
+        for (const r of routeList) {
+          if (r.path && !r.path.includes(":") && r.path !== "/" && r.path !== "") {
+            routes2.push(`${evalOrigin.replace(/\/$/, "")}/#${r.path}`);
+          }
+        }
+      }
+      return routes2;
+    }, origin);
+    for (const r of vueRoutes) routeSet.add(r);
+  } catch {
+  }
+  return Array.from(routeSet).map(
+    (p) => p.startsWith("http") ? p : `${origin.replace(/\/$/, "")}${p.startsWith("/") ? "" : "/"}${p}`
+  );
 }
 function parseRobotsTxt(text) {
   const rules = [];
@@ -2951,7 +2988,7 @@ var crawlCommand = registerCommand({
     allowSubdomains: z17.boolean().default(false),
     allowExternalLinks: z17.boolean().default(false),
     allowBackwardCrawling: z17.boolean().default(false),
-    enableSpa: z17.boolean().default(false).describe("Detect SPA (Vue/React) routes from router config"),
+    enableSpa: z17.boolean().default(true).describe("Disable to skip SPA route detection"),
     format: z17.enum(["markdown", "html"]).default("markdown"),
     onlyMainContent: z17.boolean().default(true),
     concurrency: z17.number().default(3),

package/dist/daemon-main.js

@@ -2762,22 +2762,59 @@ async function extractLinks(page, origin) {
   }, origin);
 }
 async function detectSpaRoutes(page, origin) {
-  return page.evaluate((evalOrigin) => {
-    const routeSet = /* @__PURE__ */ new Set();
+  const routeSet = /* @__PURE__ */ new Set();
+  const pathRegex = /['"`](\/[a-zA-Z0-9_\-/]+)['"`]/g;
+  const isParamRoute = (p) => p.includes(":") || p.includes("*");
+  function extractPaths(source) {
+    let match;
+    while ((match = pathRegex.exec(source)) !== null) {
+      const path2 = match[1];
+      if (!isParamRoute(path2)) routeSet.add(path2);
+    }
+  }
+  const scriptData = await page.evaluate(() => {
+    const scripts = Array.from(document.querySelectorAll("script"));
+    return {
+      inlineContent: scripts.map((s) => s.textContent || "").join("\n"),
+      externalUrls: scripts.map((s) => s.src).filter((src) => src && !src.includes("analytics") && !src.includes("google") && !src.includes("baidu"))
+    };
+  });
+  const { inlineContent, externalUrls } = scriptData;
+  extractPaths(inlineContent);
+  for (const src of externalUrls) {
     try {
-      const scripts = document.querySelectorAll("script");
-      const allContent = Array.from(scripts).map((s) => s.textContent || "").join("\n");
-      const pathRegex = /['"`](\/[a-zA-Z0-9_\-/]+)['"`]/g;
-      let match;
-      while ((match = pathRegex.exec(allContent)) !== null) {
-        const path2 = match[1];
-        if (path2.includes(":") || path2.includes("*") || routeSet.has(path2)) continue;
-        routeSet.add(path2);
+      const absoluteSrc = src.startsWith("http") ? src : new URL(src, page.url()).href;
+      const resp = await fetch(absoluteSrc, { signal: AbortSignal.timeout(5e3) });
+      if (resp.ok) {
+        const text = await resp.text();
+        extractPaths(text);
       }
     } catch {
     }
-    return Array.from(routeSet).map((path2) => `${evalOrigin.replace(/\/$/, "")}${path2}`);
-  }, origin);
+  }
+  try {
+    const vueRoutes = await page.evaluate((evalOrigin) => {
+      const routes = [];
+      const win = window;
+      const vueApp = win.__vue_app__;
+      const gp = vueApp?.config?.globalProperties;
+      const router = gp?.$router;
+      const routeList = router?.options?.routes;
+      if (routeList) {
+        for (const r of routeList) {
+          if (r.path && !r.path.includes(":") && r.path !== "/" && r.path !== "") {
+            routes.push(`${evalOrigin.replace(/\/$/, "")}/#${r.path}`);
+          }
+        }
+      }
+      return routes;
+    }, origin);
+    for (const r of vueRoutes) routeSet.add(r);
+  } catch {
+  }
+  return Array.from(routeSet).map(
+    (p) => p.startsWith("http") ? p : `${origin.replace(/\/$/, "")}${p.startsWith("/") ? "" : "/"}${p}`
+  );
 }
 function parseRobotsTxt(text) {
   const rules = [];
@@ -2918,7 +2955,7 @@ var crawlCommand = registerCommand({
     allowSubdomains: z17.boolean().default(false),
     allowExternalLinks: z17.boolean().default(false),
     allowBackwardCrawling: z17.boolean().default(false),
-    enableSpa: z17.boolean().default(false).describe("Detect SPA (Vue/React) routes from router config"),
+    enableSpa: z17.boolean().default(true).describe("Disable to skip SPA route detection"),
     format: z17.enum(["markdown", "html"]).default("markdown"),
     onlyMainContent: z17.boolean().default(true),
     concurrency: z17.number().default(3),

package/dist/index.js

@@ -2835,22 +2835,59 @@ async function extractLinks(page, origin) {
   }, origin);
 }
 async function detectSpaRoutes(page, origin) {
-  return page.evaluate((evalOrigin) => {
-    const routeSet = /* @__PURE__ */ new Set();
+  const routeSet = /* @__PURE__ */ new Set();
+  const pathRegex = /['"`](\/[a-zA-Z0-9_\-/]+)['"`]/g;
+  const isParamRoute = (p) => p.includes(":") || p.includes("*");
+  function extractPaths(source) {
+    let match;
+    while ((match = pathRegex.exec(source)) !== null) {
+      const path5 = match[1];
+      if (!isParamRoute(path5)) routeSet.add(path5);
+    }
+  }
+  const scriptData = await page.evaluate(() => {
+    const scripts = Array.from(document.querySelectorAll("script"));
+    return {
+      inlineContent: scripts.map((s) => s.textContent || "").join("\n"),
+      externalUrls: scripts.map((s) => s.src).filter((src) => src && !src.includes("analytics") && !src.includes("google") && !src.includes("baidu"))
+    };
+  });
+  const { inlineContent, externalUrls } = scriptData;
+  extractPaths(inlineContent);
+  for (const src of externalUrls) {
     try {
-      const scripts = document.querySelectorAll("script");
-      const allContent = Array.from(scripts).map((s) => s.textContent || "").join("\n");
-      const pathRegex = /['"`](\/[a-zA-Z0-9_\-/]+)['"`]/g;
-      let match;
-      while ((match = pathRegex.exec(allContent)) !== null) {
-        const path5 = match[1];
-        if (path5.includes(":") || path5.includes("*") || routeSet.has(path5)) continue;
-        routeSet.add(path5);
+      const absoluteSrc = src.startsWith("http") ? src : new URL(src, page.url()).href;
+      const resp = await fetch(absoluteSrc, { signal: AbortSignal.timeout(5e3) });
+      if (resp.ok) {
+        const text = await resp.text();
+        extractPaths(text);
       }
     } catch {
     }
-    return Array.from(routeSet).map((path5) => `${evalOrigin.replace(/\/$/, "")}${path5}`);
-  }, origin);
+  }
+  try {
+    const vueRoutes = await page.evaluate((evalOrigin) => {
+      const routes2 = [];
+      const win = window;
+      const vueApp = win.__vue_app__;
+      const gp = vueApp?.config?.globalProperties;
+      const router = gp?.$router;
+      const routeList = router?.options?.routes;
+      if (routeList) {
+        for (const r of routeList) {
+          if (r.path && !r.path.includes(":") && r.path !== "/" && r.path !== "") {
+            routes2.push(`${evalOrigin.replace(/\/$/, "")}/#${r.path}`);
+          }
+        }
+      }
+      return routes2;
+    }, origin);
+    for (const r of vueRoutes) routeSet.add(r);
+  } catch {
+  }
+  return Array.from(routeSet).map(
+    (p) => p.startsWith("http") ? p : `${origin.replace(/\/$/, "")}${p.startsWith("/") ? "" : "/"}${p}`
+  );
 }
 function parseRobotsTxt(text) {
   const rules = [];
@@ -2991,7 +3028,7 @@ var crawlCommand = registerCommand({
     allowSubdomains: z17.boolean().default(false),
     allowExternalLinks: z17.boolean().default(false),
     allowBackwardCrawling: z17.boolean().default(false),
-    enableSpa: z17.boolean().default(false).describe("Detect SPA (Vue/React) routes from router config"),
+    enableSpa: z17.boolean().default(true).describe("Disable to skip SPA route detection"),
     format: z17.enum(["markdown", "html"]).default("markdown"),
     onlyMainContent: z17.boolean().default(true),
     concurrency: z17.number().default(3),

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@xbrowser/cli",
-  "version": "1.7.1",
+  "version": "1.7.3",
   "description": "Browser automation CLI for web scraping, headless browsing, SEO analysis, and AI agent workflows. A command-line alternative to Playwright, Puppeteer, and Selenium.",
   "type": "module",
   "bin": {