@blinkdotnew/cli 0.2.0 → 0.2.2

package/README.md

@@ -36,6 +36,10 @@ blink db query "SELECT count(*) FROM users"
 # Generate AI content
 blink ai image "a glowing blink logo on dark background"
 blink ai text "Summarize this article: ..."
+
+# Scrape websites
+blink scrape https://lovable.dev --extract "pricing tiers and costs"
+blink scrape https://example.com --text
 ```
 
 ---
@@ -218,7 +222,7 @@ blink ai transcribe https://example.com/audio.mp3 --language en
 
 ---
 
-### `blink fetch` and `blink search` — Web & data
+### `blink fetch`, `blink search`, `blink scrape` — Web & data
 
 ```bash
 # Fetch any URL via Blink proxy (handles CORS, auth headers)
@@ -229,8 +233,21 @@ blink fetch https://api.example.com --header "X-API-Key: secret"
 # Web search
 blink search "latest AI news"
 blink search "React Server Components" --count 10 --json
+
+# Scrape web pages
+blink scrape https://example.com                              # Raw response
+blink scrape https://example.com --text                      # Clean text (strips HTML)
+blink scrape https://example.com --extract "all prices"      # AI-extract specific data
+blink scrape https://news.ycombinator.com --extract "top 10 story titles and URLs"
+blink scrape https://example.com --extract "contact email" --json
 ```
 
+No project key needed — `blink scrape` uses your workspace key only.
+
+- `--text` — strips all HTML tags, returns readable text
+- `--extract <instructions>` — uses AI (Gemini Flash) to extract exactly what you ask for
+- Combine with `--json` for `{ url, content }` or `{ url, extracted }` output
+
 ---
 
 ### `blink realtime` — Pub/sub

package/dist/cli.js

@@ -509,6 +509,65 @@ Examples:
     if (typeof result === "string") console.log(result);
     else console.log(JSON.stringify(result, null, 2));
   });
+  program2.command("scrape <url>").description("Scrape a webpage \u2014 returns text content, optionally AI-extracted data").option("--extract <instructions>", 'What to extract using AI (e.g. "all prices and product names")').option("--text", "Strip HTML tags and return clean readable text").addHelpText("after", `
+No project key needed \u2014 scrape runs through the Blink proxy using your workspace key.
+
+Examples:
+  $ blink scrape https://example.com                         Get full page content
+  $ blink scrape https://example.com --text                  Clean text only (no HTML)
+  $ blink scrape https://example.com --extract "all prices"  AI-extract specific data
+  $ blink scrape https://news.ycombinator.com --extract "top 10 story titles and URLs" --json
+`).action(async (url, opts) => {
+    requireToken();
+    const response = await withSpinner(
+      "Fetching page...",
+      () => resourcesRequest("/api/v1/fetch", { body: { url } })
+    );
+    let content;
+    if (typeof response === "string") {
+      content = response;
+    } else if (typeof response?.body === "string") {
+      content = response.body;
+    } else {
+      content = JSON.stringify(response);
+    }
+    if (opts.extract) {
+      const extraction = await withSpinner(
+        `Extracting: ${opts.extract}...`,
+        () => resourcesRequest("/api/v1/ai/chat/completions", {
+          body: {
+            model: "google/gemini-3-flash",
+            messages: [
+              {
+                role: "system",
+                content: "You are a web scraping assistant. Extract exactly the requested information from the webpage content provided. Return only the extracted data, formatted clearly. No commentary."
+              },
+              {
+                role: "user",
+                content: `URL: ${url}
+
+Webpage content:
+${content.slice(0, 5e4)}
+
+Extract: ${opts.extract}`
+              }
+            ],
+            stream: false
+          }
+        })
+      );
+      const extracted = extraction?.choices?.[0]?.message?.content ?? "";
+      if (isJsonMode()) return printJson({ url, extracted, extract_instructions: opts.extract });
+      console.log(extracted);
+    } else if (opts.text) {
+      const text = content.replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, " ").replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, " ").replace(/<[^>]+>/g, " ").replace(/&nbsp;/g, " ").replace(/&amp;/g, "&").replace(/&lt;/g, "<").replace(/&gt;/g, ">").replace(/&quot;/g, '"').replace(/\s+/g, " ").trim();
+      if (isJsonMode()) return printJson({ url, text });
+      console.log(text);
+    } else {
+      if (isJsonMode()) return printJson({ url, content });
+      console.log(content);
+    }
+  });
   program2.command("search <query>").description("Web search \u2014 returns titles, URLs, and snippets").option("--count <n>", "Number of results to return (max 20)", "5").addHelpText("after", `
 Examples:
   $ blink search "latest AI news"
@@ -1539,6 +1598,8 @@ Web & Data:
   $ blink search "latest AI news" --count 10
   $ blink fetch https://api.github.com/users/octocat
   $ blink fetch https://api.example.com --method POST --body '{"key":"val"}'
+  $ blink scrape https://example.com --text              Clean text (no HTML)
+  $ blink scrape https://example.com --extract "prices"  AI-extract specific data
 
 Realtime / RAG / Notify:
   $ blink realtime publish updates '{"type":"refresh"}'

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@blinkdotnew/cli",
-  "version": "0.2.0",
+  "version": "0.2.2",
   "description": "Blink platform CLI — deploy apps, manage databases, generate AI content",
   "bin": {
     "blink": "dist/cli.js"

package/src/cli.ts

@@ -70,6 +70,8 @@ Web & Data:
   $ blink search "latest AI news" --count 10
   $ blink fetch https://api.github.com/users/octocat
   $ blink fetch https://api.example.com --method POST --body '{"key":"val"}'
+  $ blink scrape https://example.com --text              Clean text (no HTML)
+  $ blink scrape https://example.com --extract "prices"  AI-extract specific data
 
 Realtime / RAG / Notify:
   $ blink realtime publish updates '{"type":"refresh"}'

package/src/commands/web.ts

@@ -40,6 +40,80 @@ Examples:
       else console.log(JSON.stringify(result, null, 2))
     })
 
+  program.command('scrape <url>')
+    .description('Scrape a webpage — returns text content, optionally AI-extracted data')
+    .option('--extract <instructions>', 'What to extract using AI (e.g. "all prices and product names")')
+    .option('--text', 'Strip HTML tags and return clean readable text')
+    .addHelpText('after', `
+No project key needed — scrape runs through the Blink proxy using your workspace key.
+
+Examples:
+  $ blink scrape https://example.com                         Get full page content
+  $ blink scrape https://example.com --text                  Clean text only (no HTML)
+  $ blink scrape https://example.com --extract "all prices"  AI-extract specific data
+  $ blink scrape https://news.ycombinator.com --extract "top 10 story titles and URLs" --json
+`)
+    .action(async (url, opts) => {
+      requireToken()
+
+      const response = await withSpinner('Fetching page...', () =>
+        resourcesRequest('/api/v1/fetch', { body: { url } })
+      )
+
+      // Extract the response body — fetch returns { status, contentType, body } or raw string
+      let content: string
+      if (typeof response === 'string') {
+        content = response
+      } else if (typeof response?.body === 'string') {
+        content = response.body
+      } else {
+        content = JSON.stringify(response)
+      }
+
+      if (opts.extract) {
+        // AI extraction — uses workspace key, no project needed
+        const extraction = await withSpinner(`Extracting: ${opts.extract}...`, () =>
+          resourcesRequest('/api/v1/ai/chat/completions', {
+            body: {
+              model: 'google/gemini-3-flash',
+              messages: [
+                {
+                  role: 'system',
+                  content: 'You are a web scraping assistant. Extract exactly the requested information from the webpage content provided. Return only the extracted data, formatted clearly. No commentary.',
+                },
+                {
+                  role: 'user',
+                  content: `URL: ${url}\n\nWebpage content:\n${content.slice(0, 50000)}\n\nExtract: ${opts.extract}`,
+                },
+              ],
+              stream: false,
+            },
+          })
+        )
+        const extracted = extraction?.choices?.[0]?.message?.content ?? ''
+        if (isJsonMode()) return printJson({ url, extracted, extract_instructions: opts.extract })
+        console.log(extracted)
+      } else if (opts.text) {
+        // Strip HTML and return clean text
+        const text = content
+          .replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, ' ')
+          .replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, ' ')
+          .replace(/<[^>]+>/g, ' ')
+          .replace(/&nbsp;/g, ' ')
+          .replace(/&amp;/g, '&')
+          .replace(/&lt;/g, '<')
+          .replace(/&gt;/g, '>')
+          .replace(/&quot;/g, '"')
+          .replace(/\s+/g, ' ')
+          .trim()
+        if (isJsonMode()) return printJson({ url, text })
+        console.log(text)
+      } else {
+        if (isJsonMode()) return printJson({ url, content })
+        console.log(content)
+      }
+    })
+
   program.command('search <query>')
     .description('Web search — returns titles, URLs, and snippets')
     .option('--count <n>', 'Number of results to return (max 20)', '5')