mdrip 0.1.0 → 0.1.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md
CHANGED
|
@@ -9,6 +9,15 @@ This repo also includes an AI-consumable skills catalog in `skills/`, following
|
|
|
9
9
|
- Skill index: `skills/README.md`
|
|
10
10
|
- mdrip skill: `skills/mdrip/SKILL.md`
|
|
11
11
|
|
|
12
|
+
### Install skills from this repo
|
|
13
|
+
|
|
14
|
+
If you use a Skills-compatible agent setup, you can add these skills directly:
|
|
15
|
+
|
|
16
|
+
```bash
|
|
17
|
+
# install skills from this repo
|
|
18
|
+
npx skills add charl-kruger/mdrip
|
|
19
|
+
```
|
|
20
|
+
|
|
12
21
|
## Why
|
|
13
22
|
|
|
14
23
|
For agent workflows, markdown is often better than HTML:
|
|
@@ -21,6 +30,22 @@ For agent workflows, markdown is often better than HTML:
|
|
|
21
30
|
If a site does not return `text/markdown`, `mdrip` can automatically fall back to converting `text/html` into markdown.
|
|
22
31
|
The fallback uses an in-project converter optimized for common documentation/blog content (headings, links, lists, code blocks, tables, blockquotes).
|
|
23
32
|
|
|
33
|
+
## Why Cloudflare Markdown for Agents matters
|
|
34
|
+
|
|
35
|
+
Cloudflare's blog and docs describe Markdown for Agents as content negotiation at the edge:
|
|
36
|
+
- clients request `Accept: text/markdown`
|
|
37
|
+
- Cloudflare converts HTML to markdown in real time (for enabled zones)
|
|
38
|
+
- response includes `x-markdown-tokens` for token-size awareness
|
|
39
|
+
|
|
40
|
+
For AI workflows this is high-value:
|
|
41
|
+
- better structure for LLM parsing than raw HTML
|
|
42
|
+
- less token waste in context windows
|
|
43
|
+
- predictable markdown snapshots you can store and reuse in your repo
|
|
44
|
+
|
|
45
|
+
References:
|
|
46
|
+
- [Cloudflare blog: Markdown for Agents](https://blog.cloudflare.com/markdown-for-agents/)
|
|
47
|
+
- [Cloudflare docs: Markdown for Agents](https://developers.cloudflare.com/fundamentals/reference/markdown-for-agents/)
|
|
48
|
+
|
|
24
49
|
## Installation
|
|
25
50
|
|
|
26
51
|
```bash
|
package/dist/index.js
CHANGED
|
@@ -8,7 +8,7 @@ const program = new Command();
|
|
|
8
8
|
program
|
|
9
9
|
.name("mdrip")
|
|
10
10
|
.description("Fetch markdown snapshots for URLs using Cloudflare Markdown for Agents")
|
|
11
|
-
.version("0.1.
|
|
11
|
+
.version("0.1.1")
|
|
12
12
|
.option("--cwd <path>", "working directory (default: current directory)");
|
|
13
13
|
program
|
|
14
14
|
.argument("[urls...]", "URLs to fetch as markdown")
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"cloudflare.d.ts","sourceRoot":"","sources":["../../src/lib/cloudflare.ts"],"names":[],"mappings":"
|
|
1
|
+
{"version":3,"file":"cloudflare.d.ts","sourceRoot":"","sources":["../../src/lib/cloudflare.ts"],"names":[],"mappings":"AAMA,MAAM,WAAW,oBAAoB;IACnC,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,YAAY,CAAC,EAAE,OAAO,CAAC;IACvB,SAAS,CAAC,EAAE,OAAO,KAAK,CAAC;CAC1B;AAED,MAAM,WAAW,gBAAgB;IAC/B,QAAQ,EAAE,MAAM,CAAC;IACjB,MAAM,EAAE,MAAM,CAAC;IACf,WAAW,EAAE,MAAM,CAAC;IACpB,WAAW,EAAE,MAAM,CAAC;IACpB,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,MAAM,EAAE,qBAAqB,GAAG,eAAe,CAAC;CACjD;AAWD,wBAAsB,iBAAiB,CACrC,GAAG,EAAE,MAAM,EACX,OAAO,GAAE,oBAAyB,GACjC,OAAO,CAAC,gBAAgB,CAAC,CA6E3B"}
|
package/dist/lib/cloudflare.js
CHANGED
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
import { convertHtmlToMarkdown, estimateTokenCount } from "./html-to-markdown.js";
|
|
2
2
|
const DEFAULT_TIMEOUT_MS = 30_000;
|
|
3
3
|
const DEFAULT_ACCEPT = "text/markdown, text/html;q=0.9, */*;q=0.1";
|
|
4
|
+
const DEFAULT_ACCEPT_ENCODING = "identity";
|
|
4
5
|
function parseTokenHeader(value) {
|
|
5
6
|
if (!value) {
|
|
6
7
|
return undefined;
|
|
@@ -19,6 +20,7 @@ export async function fetchMarkdownPage(url, options = {}) {
|
|
|
19
20
|
method: "GET",
|
|
20
21
|
headers: {
|
|
21
22
|
Accept: DEFAULT_ACCEPT,
|
|
23
|
+
"Accept-Encoding": DEFAULT_ACCEPT_ENCODING,
|
|
22
24
|
"User-Agent": options.userAgent ?? "mdrip-cli",
|
|
23
25
|
},
|
|
24
26
|
redirect: "follow",
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"cloudflare.js","sourceRoot":"","sources":["../../src/lib/cloudflare.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,qBAAqB,EAAE,kBAAkB,EAAE,MAAM,uBAAuB,CAAC;AAElF,MAAM,kBAAkB,GAAG,MAAM,CAAC;AAClC,MAAM,cAAc,GAAG,2CAA2C,CAAC;
|
|
1
|
+
{"version":3,"file":"cloudflare.js","sourceRoot":"","sources":["../../src/lib/cloudflare.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,qBAAqB,EAAE,kBAAkB,EAAE,MAAM,uBAAuB,CAAC;AAElF,MAAM,kBAAkB,GAAG,MAAM,CAAC;AAClC,MAAM,cAAc,GAAG,2CAA2C,CAAC;AACnE,MAAM,uBAAuB,GAAG,UAAU,CAAC;AAmB3C,SAAS,gBAAgB,CAAC,KAAoB;IAC5C,IAAI,CAAC,KAAK,EAAE,CAAC;QACX,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,MAAM,MAAM,GAAG,MAAM,CAAC,QAAQ,CAAC,KAAK,EAAE,EAAE,CAAC,CAAC;IAC1C,OAAO,MAAM,CAAC,QAAQ,CAAC,MAAM,CAAC,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,SAAS,CAAC;AACtD,CAAC;AAED,MAAM,CAAC,KAAK,UAAU,iBAAiB,CACrC,GAAW,EACX,UAAgC,EAAE;IAElC,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,kBAAkB,CAAC;IAC1D,MAAM,YAAY,GAAG,OAAO,CAAC,YAAY,IAAI,IAAI,CAAC;IAClD,MAAM,UAAU,GAAG,IAAI,eAAe,EAAE,CAAC;IACzC,MAAM,SAAS,GAAG,OAAO,CAAC,SAAS,IAAI,KAAK,CAAC;IAC7C,MAAM,OAAO,GAAG,UAAU,CAAC,GAAG,EAAE,CAAC,UAAU,CAAC,KAAK,EAAE,EAAE,SAAS,CAAC,CAAC;IAEhE,IAAI,CAAC;QACH,MAAM,QAAQ,GAAG,MAAM,SAAS,CAAC,GAAG,EAAE;YACpC,MAAM,EAAE,KAAK;YACb,OAAO,EAAE;gBACP,MAAM,EAAE,cAAc;gBACtB,iBAAiB,EAAE,uBAAuB;gBAC1C,YAAY,EAAE,OAAO,CAAC,SAAS,IAAI,WAAW;aAC/C;YACD,QAAQ,EAAE,QAAQ;YAClB,MAAM,EAAE,UAAU,CAAC,MAAM;SAC1B,CAAC,CAAC;QAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;YACjB,MAAM,IAAI,KAAK,CAAC,mBAAmB,QAAQ,CAAC,MAAM,IAAI,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAC;QAC/E,CAAC;QAED,MAAM,WAAW,GAAG,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,cAAc,CAAC,IAAI,EAAE,CAAC;QAE/D,MAAM,cAAc,GAAG,WAAW,CAAC,WAAW,EAAE,CAAC;QAEjD,IAAI,cAAc,CAAC,QAAQ,CAAC,eAAe,CAAC,EAAE,CAAC;YAC7C,MAAM,QAAQ,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;YAEvC,OAAO;gBACL,QAAQ;gBACR,MAAM,EAAE,QAAQ,CAAC,MAAM;gBACvB,WAAW;gBACX,WAAW,EAAE,QAAQ,CAAC,GAAG,IAAI,GAAG;gBAChC,cAAc,EAAE,gBAAgB,CAAC,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,mBAAmB,CAAC,CAAC;gBAC3E,aAAa,EAAE,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,gBAAgB,CAAC,IAAI,SAAS;gBAClE,MAAM,EAAE,qBAAqB;aAC9B,CAAC;QACJ,CAAC;QAED,MAAM,cAAc,GAClB,cAAc,CAAC,QAAQ,CAAC,WAAW,CAAC;YACpC,cAAc,CAAC,QAAQ,CAAC,uBAAuB,CAAC,CAAC;QAEnD,IAAI,cAAc,IAAI,YAAY,EAAE,CAAC;YACnC,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC;YACnC,MAAM,QAAQ,GAAG,qBAAqB,CAAC,IAAI,EAAE,QAAQ,CAAC,GAAG,IAAI,GAAG,CAAC,CAAC;YAElE,OAAO;gBACL,QAAQ;gBACR,MAAM,EAAE,QAAQ,CAAC,MAAM;gBACvB,WAAW;gBACX,WAAW,EAAE,QAAQ,CAAC,GAAG,IAAI,GAAG;gBAChC,cAAc,EAAE,kBAAkB,CAAC,QAAQ,CAAC;gBAC5C,aAAa,EAAE,QAAQ,CAAC,OAAO,CAAC,GAAG,CAAC,gBAAgB,CAAC,IAAI,SAAS;gBAClE,MAAM,EAAE,eAAe;aACxB,CAAC;QACJ,CAAC;QAED,IAAI,cAAc,IAAI,CAAC,YAAY,EAAE,CAAC;YACpC,MAAM,IAAI,KAAK,CACb,wCAAwC,WAAW,IAAI,SAAS,8DAA8D,CAC/H,CAAC;QACJ,CAAC;QAED,MAAM,IAAI,KAAK,CACb,wCAAwC,WAAW,IAAI,SAAS,uDAAuD,CACxH,CAAC;IACJ,CAAC;IAAC,OAAO,GAAG,EAAE,CAAC;QACb,IAAI,GAAG,YAAY,KAAK,IAAI,GAAG,CAAC,IAAI,KAAK,YAAY,EAAE,CAAC;YACtD,MAAM,IAAI,KAAK,CAAC,2BAA2B,SAAS,IAAI,CAAC,CAAC;QAC5D,CAAC;QACD,MAAM,GAAG,CAAC;IACZ,CAAC;YAAS,CAAC;QACT,YAAY,CAAC,OAAO,CAAC,CAAC;IACxB,CAAC;AACH,CAAC"}
|
|
@@ -2,14 +2,18 @@ import { describe, it, expect } from "vitest";
|
|
|
2
2
|
import { fetchMarkdownPage } from "./cloudflare.js";
|
|
3
3
|
describe("fetchMarkdownPage", () => {
|
|
4
4
|
it("uses Cloudflare markdown response when available", async () => {
|
|
5
|
-
|
|
6
|
-
|
|
7
|
-
|
|
8
|
-
|
|
9
|
-
|
|
10
|
-
|
|
11
|
-
|
|
12
|
-
|
|
5
|
+
let receivedInit;
|
|
6
|
+
const mockFetch = async (_input, init) => {
|
|
7
|
+
receivedInit = init;
|
|
8
|
+
return new Response("# Hello", {
|
|
9
|
+
status: 200,
|
|
10
|
+
headers: {
|
|
11
|
+
"content-type": "text/markdown; charset=utf-8",
|
|
12
|
+
"x-markdown-tokens": "22",
|
|
13
|
+
"content-signal": "ai-input=yes",
|
|
14
|
+
},
|
|
15
|
+
});
|
|
16
|
+
};
|
|
13
17
|
const result = await fetchMarkdownPage("https://example.com", {
|
|
14
18
|
fetchImpl: mockFetch,
|
|
15
19
|
});
|
|
@@ -17,6 +21,8 @@ describe("fetchMarkdownPage", () => {
|
|
|
17
21
|
expect(result.markdown).toBe("# Hello");
|
|
18
22
|
expect(result.markdownTokens).toBe(22);
|
|
19
23
|
expect(result.contentSignal).toBe("ai-input=yes");
|
|
24
|
+
expect((receivedInit?.headers)["Accept"]).toContain("text/markdown");
|
|
25
|
+
expect((receivedInit?.headers)["Accept-Encoding"]).toBe("identity");
|
|
20
26
|
});
|
|
21
27
|
it("falls back to HTML conversion when markdown is not returned", async () => {
|
|
22
28
|
const mockFetch = async () => new Response("<html><body><main><h1>Welcome</h1><p>Page</p></main></body></html>", {
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"version":3,"file":"cloudflare.test.js","sourceRoot":"","sources":["../../src/lib/cloudflare.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAC9C,OAAO,EAAE,iBAAiB,EAAE,MAAM,iBAAiB,CAAC;AAEpD,QAAQ,CAAC,mBAAmB,EAAE,GAAG,EAAE;IACjC,EAAE,CAAC,kDAAkD,EAAE,KAAK,IAAI,EAAE;QAChE,MAAM,SAAS,GAAiB,KAAK,IAAI,EAAE,
|
|
1
|
+
{"version":3,"file":"cloudflare.test.js","sourceRoot":"","sources":["../../src/lib/cloudflare.test.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,QAAQ,EAAE,EAAE,EAAE,MAAM,EAAE,MAAM,QAAQ,CAAC;AAC9C,OAAO,EAAE,iBAAiB,EAAE,MAAM,iBAAiB,CAAC;AAEpD,QAAQ,CAAC,mBAAmB,EAAE,GAAG,EAAE;IACjC,EAAE,CAAC,kDAAkD,EAAE,KAAK,IAAI,EAAE;QAChE,IAAI,YAAqC,CAAC;QAC1C,MAAM,SAAS,GAAiB,KAAK,EAAE,MAAM,EAAE,IAAI,EAAE,EAAE;YACrD,YAAY,GAAG,IAAI,CAAC;YACpB,OAAO,IAAI,QAAQ,CAAC,SAAS,EAAE;gBAC7B,MAAM,EAAE,GAAG;gBACX,OAAO,EAAE;oBACP,cAAc,EAAE,8BAA8B;oBAC9C,mBAAmB,EAAE,IAAI;oBACzB,gBAAgB,EAAE,cAAc;iBACjC;aACF,CAAC,CAAC;QACL,CAAC,CAAC;QAEF,MAAM,MAAM,GAAG,MAAM,iBAAiB,CAAC,qBAAqB,EAAE;YAC5D,SAAS,EAAE,SAAS;SACrB,CAAC,CAAC;QAEH,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,qBAAqB,CAAC,CAAC;QAClD,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,IAAI,CAAC,SAAS,CAAC,CAAC;QACxC,MAAM,CAAC,MAAM,CAAC,cAAc,CAAC,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;QACvC,MAAM,CAAC,MAAM,CAAC,aAAa,CAAC,CAAC,IAAI,CAAC,cAAc,CAAC,CAAC;QAClD,MAAM,CAAC,CAAC,YAAY,EAAE,OAAkC,CAAA,CAAC,QAAQ,CAAC,CAAC,CAAC,SAAS,CAC3E,eAAe,CAChB,CAAC;QACF,MAAM,CACJ,CAAC,YAAY,EAAE,OAAkC,CAAA,CAAC,iBAAiB,CAAC,CACrE,CAAC,IAAI,CAAC,UAAU,CAAC,CAAC;IACrB,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,6DAA6D,EAAE,KAAK,IAAI,EAAE;QAC3E,MAAM,SAAS,GAAiB,KAAK,IAAI,EAAE,CACzC,IAAI,QAAQ,CACV,oEAAoE,EACpE;YACE,MAAM,EAAE,GAAG;YACX,OAAO,EAAE;gBACP,cAAc,EAAE,0BAA0B;aAC3C;SACF,CACF,CAAC;QAEJ,MAAM,MAAM,GAAG,MAAM,iBAAiB,CAAC,qBAAqB,EAAE;YAC5D,SAAS,EAAE,SAAS;SACrB,CAAC,CAAC;QAEH,MAAM,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC,IAAI,CAAC,eAAe,CAAC,CAAC;QAC5C,MAAM,CAAC,MAAM,CAAC,QAAQ,CAAC,CAAC,SAAS,CAAC,WAAW,CAAC,CAAC;QAC/C,MAAM,CAAC,MAAM,CAAC,cAAc,CAAC,CAAC,eAAe,CAAC,CAAC,CAAC,CAAC;IACnD,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,0CAA0C,EAAE,KAAK,IAAI,EAAE;QACxD,MAAM,SAAS,GAAiB,KAAK,IAAI,EAAE,CACzC,IAAI,QAAQ,CAAC,gCAAgC,EAAE;YAC7C,MAAM,EAAE,GAAG;YACX,OAAO,EAAE;gBACP,cAAc,EAAE,0BAA0B;aAC3C;SACF,CAAC,CAAC;QAEL,MAAM,MAAM,CACV,iBAAiB,CAAC,qBAAqB,EAAE;YACvC,SAAS,EAAE,SAAS;YACpB,YAAY,EAAE,KAAK;SACpB,CAAC,CACH,CAAC,OAAO,CAAC,OAAO,CAAC,yBAAyB,CAAC,CAAC;IAC/C,CAAC,CAAC,CAAC;IAEH,EAAE,CAAC,kDAAkD,EAAE,KAAK,IAAI,EAAE;QAChE,MAAM,SAAS,GAAiB,KAAK,IAAI,EAAE,CACzC,IAAI,QAAQ,CAAC,aAAa,EAAE;YAC1B,MAAM,EAAE,GAAG;YACX,OAAO,EAAE;gBACP,cAAc,EAAE,kBAAkB;aACnC;SACF,CAAC,CAAC;QAEL,MAAM,MAAM,CACV,iBAAiB,CAAC,qBAAqB,EAAE;YACvC,SAAS,EAAE,SAAS;SACrB,CAAC,CACH,CAAC,OAAO,CAAC,OAAO,CAAC,kCAAkC,CAAC,CAAC;IACxD,CAAC,CAAC,CAAC;AACL,CAAC,CAAC,CAAC"}
|