@only-cli/oc 0.5.6 → 0.5.8
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 +3 -1
- package/package.json +1 -1
- package/skills/web-browsing-cli/SKILL.md +10 -10
- package/src/act.js +21 -5
- package/src/cli.js +2 -2
- package/src/cookies.js +51 -3
- package/src/distill.js +48 -7
- package/src/render.js +4 -1
- package/src/session.js +19 -6
package/README.md
CHANGED
|
@@ -29,6 +29,8 @@ npm install -g @only-cli/oc
|
|
|
29
29
|
|
|
30
30
|
Requires Node 20+. Requests impersonate Chrome via [impers](https://github.com/lexiforest/impers). When a site, or the local copy of libcurl-impersonate, refuses the Chrome identity, the request downgrades to Firefox, and to native fetch when impers is unavailable or refuses both.
|
|
31
31
|
|
|
32
|
+
Red Hat OpenShift also installs an `oc`, and both define `login` and `logout` with unrelated meanings, so whichever lands first on `PATH` shadows the other. If you use OpenShift, call this one with `npx @only-cli/oc` instead of installing it globally, or alias the global install to another name.
|
|
33
|
+
|
|
32
34
|
### Agent skill
|
|
33
35
|
|
|
34
36
|
Install the [web-browsing-cli skill](https://www.skills.sh/only-cli/oc/web-browsing-cli) for Claude Code, Cursor, Codex, Copilot, and other compatible agents:
|
|
@@ -139,7 +141,7 @@ Copy the `Cookie` header from your browser's devtools (Application → Cookies,
|
|
|
139
141
|
|
|
140
142
|
Seeded cookies are https-only. They almost always come from an https browser session, so `oc` marks them secure and never sends them over plain `http`, including on a hop an `https` page redirects into, where you never typed the downgrade. A site that really is http-only needs `--allow-http` at login. Cookies a site sets over https are pinned the same way.
|
|
141
143
|
|
|
142
|
-
Cookies live in a separate sidecar file (`<session>.cookies.json`) under `~/.only-cli/sessions/`, owner-only (mode `0600
|
|
144
|
+
Cookies live in a separate sidecar file (`<session>.cookies.json`) under `~/.only-cli/sessions/`, owner-only (mode `0600` in a `0700` directory, or on Windows the ACL the directory hands down), not in the page-state JSON and never in `--json` output. The default lifetime is one hour (`--expires 1h`), and a jar holds at most 50 cookies so a page cannot bloat it. When cookies expire or the site returns a login page, `oc` says so plainly (exit 2) instead of distilling the login form as content.
|
|
143
145
|
|
|
144
146
|
`oc logout` forgets the whole session, not just its cookies: a page saved under that name can hold the distilled text of something only the login could reach, so the snapshot goes with the jar. `oc session rm [name]` forgets a session the same way (page plus cookies) without switching to it first, and `oc session ls` lists what is on disk (`[cookies]` marks a live jar). State lives in `~/.only-cli` (`%USERPROFILE%\.only-cli` on Windows, override with `OC_HOME`), one JSON per session plus search-index caches. Delete the directory to start over.
|
|
145
147
|
|
package/package.json
CHANGED
|
@@ -8,17 +8,17 @@ description: Token-efficient web browsing and web content extraction for AI agen
|
|
|
8
8
|
Renders a web page as a compact, numbered terminal view instead of raw HTML. A typical page is under 500 tokens.
|
|
9
9
|
|
|
10
10
|
```
|
|
11
|
-
npx --yes @only-cli/oc@0.5.
|
|
12
|
-
npx --yes @only-cli/oc@0.5.
|
|
13
|
-
npx --yes @only-cli/oc@0.5.
|
|
11
|
+
npx --yes @only-cli/oc@0.5.8 open <url> compact view, numbered elements
|
|
12
|
+
npx --yes @only-cli/oc@0.5.8 do <n> follow link [n], or read it if [n] is text
|
|
13
|
+
npx --yes @only-cli/oc@0.5.8 find <query> where a string appears, or that place itself
|
|
14
14
|
when only one matches
|
|
15
|
-
npx --yes @only-cli/oc@0.5.
|
|
16
|
-
npx --yes @only-cli/oc@0.5.
|
|
17
|
-
npx --yes @only-cli/oc@0.5.
|
|
18
|
-
npx --yes @only-cli/oc@0.5.
|
|
19
|
-
npx --yes @only-cli/oc@0.5.
|
|
20
|
-
npx --yes @only-cli/oc@0.5.
|
|
21
|
-
npx --yes @only-cli/oc@0.5.
|
|
15
|
+
npx --yes @only-cli/oc@0.5.8 next next ~500 tokens of the page already open
|
|
16
|
+
npx --yes @only-cli/oc@0.5.8 read <n> full text of region [n]
|
|
17
|
+
npx --yes @only-cli/oc@0.5.8 raw [url] whole page as markdown (--html for cleaned HTML)
|
|
18
|
+
npx --yes @only-cli/oc@0.5.8 login seed cookies (--cookie, --domain, --expires)
|
|
19
|
+
npx --yes @only-cli/oc@0.5.8 logout [session] forget a session: cookies and saved page
|
|
20
|
+
npx --yes @only-cli/oc@0.5.8 session ls list saved sessions (name, url, title)
|
|
21
|
+
npx --yes @only-cli/oc@0.5.8 session rm [name] forget a saved session: page and cookies
|
|
22
22
|
```
|
|
23
23
|
|
|
24
24
|
None of these except `open`/`do`/`raw <url>` fetch anything; they replay the page `open` already saved.
|
package/src/act.js
CHANGED
|
@@ -42,17 +42,31 @@ function requireBlocks(session) {
|
|
|
42
42
|
return state;
|
|
43
43
|
}
|
|
44
44
|
|
|
45
|
+
/**
|
|
46
|
+
* The number a handle was printed as. The compact view writes `[2]`, and
|
|
47
|
+
* agents copy that form into `oc do [2]` / `oc read [2]`. Number('[2]') is
|
|
48
|
+
* NaN, so the printed form used to fail the usage check.
|
|
49
|
+
* @param {unknown} value
|
|
50
|
+
* @returns {number}
|
|
51
|
+
*/
|
|
52
|
+
export function parseHandle(value) {
|
|
53
|
+
const s = String(value ?? '').trim();
|
|
54
|
+
const m = /^\[(\d+)\]$/.exec(s) || /^(\d+)$/.exec(s);
|
|
55
|
+
return m ? Number(m[1]) : NaN;
|
|
56
|
+
}
|
|
57
|
+
|
|
45
58
|
/**
|
|
46
59
|
* Resolve a numbered handle from the last render into something to open.
|
|
47
60
|
* Returns the target URL; the caller fetches and renders it exactly as
|
|
48
61
|
* `oc open` would, so `do` and `open` always agree on what a page looks like.
|
|
49
62
|
* When the number is text rather than a link it returns `{read}` instead, and
|
|
50
63
|
* the caller reads it.
|
|
51
|
-
* @param {
|
|
64
|
+
* @param {unknown} n
|
|
52
65
|
* @param {{session?: string}} [opts]
|
|
53
66
|
* @returns {{url?: string, read?: number, text: string}}
|
|
54
67
|
*/
|
|
55
68
|
export function activate(n, { session = DEFAULT_SESSION } = {}) {
|
|
69
|
+
n = parseHandle(n);
|
|
56
70
|
if (!Number.isInteger(n) || n < 1) {
|
|
57
71
|
throw new Error('usage: oc do <n>, where <n> is a number from the last page');
|
|
58
72
|
}
|
|
@@ -67,7 +81,8 @@ export function activate(n, { session = DEFAULT_SESSION } = {}) {
|
|
|
67
81
|
// and opening it is what `do` was asked for. Reading the title back instead
|
|
68
82
|
// cost a turn, and then another to find the number that does navigate, so a
|
|
69
83
|
// heading that has an href falls through to the link below.
|
|
70
|
-
|
|
84
|
+
// A link with no href, a fragment or mailto:, has nothing to fetch either.
|
|
85
|
+
if (['text', 'heading', 'link'].includes(handle.type) && !handle.href) {
|
|
71
86
|
// There is nothing to follow, but the agent asked to see what is at [n],
|
|
72
87
|
// and that is what read prints. Refusing would spend a whole turn to name
|
|
73
88
|
// the command that should have run, and a turn costs more than the page.
|
|
@@ -100,6 +115,7 @@ const TRAIL = 6;
|
|
|
100
115
|
* @returns {string}
|
|
101
116
|
*/
|
|
102
117
|
export function read(n, { session = DEFAULT_SESSION, budget = 2000 } = {}) {
|
|
118
|
+
n = parseHandle(n);
|
|
103
119
|
if (!Number.isInteger(n) || n < 1) {
|
|
104
120
|
throw new Error('usage: oc read <n>, where <n> is a number from the last page');
|
|
105
121
|
}
|
|
@@ -230,7 +246,7 @@ export function find(query, { session = DEFAULT_SESSION, budget = 500 } = {}) {
|
|
|
230
246
|
// the example it names was in the block after it.
|
|
231
247
|
if (hits.length === 1 && hits[0].n != null) {
|
|
232
248
|
const only = hits[0];
|
|
233
|
-
const follow = only.
|
|
249
|
+
const follow = only.href ? 'do <n> | ' : '';
|
|
234
250
|
return [
|
|
235
251
|
`1 match for "${query}"${separately}, region [${only.n}]`,
|
|
236
252
|
read(only.n, { session, budget: budget * FINISH }),
|
|
@@ -258,7 +274,7 @@ export function find(query, { session = DEFAULT_SESSION, budget = 500 } = {}) {
|
|
|
258
274
|
if (spent + cost > cap && shown) break;
|
|
259
275
|
spent += cost;
|
|
260
276
|
shown++;
|
|
261
|
-
if (hit.
|
|
277
|
+
if (hit.href) hasLinks = true;
|
|
262
278
|
lines.push(line);
|
|
263
279
|
}
|
|
264
280
|
if (shown < hits.length) {
|
|
@@ -298,7 +314,7 @@ function search(blocks, terms) {
|
|
|
298
314
|
// are read rather than indexed: the whole-match mode above, and `read`.
|
|
299
315
|
const window = block.text.slice(start, end).replace(/\n/g, ' ');
|
|
300
316
|
const snippet = `${start > 0 ? '... ' : ''}${window}${end < block.text.length ? ' ...' : ''}`;
|
|
301
|
-
out.push({ n, type: block.type, snippet, text: block.text });
|
|
317
|
+
out.push({ n, type: block.type, snippet, text: block.text, href: block.href });
|
|
302
318
|
}
|
|
303
319
|
return out;
|
|
304
320
|
}
|
package/src/cli.js
CHANGED
|
@@ -237,7 +237,7 @@ async function main() {
|
|
|
237
237
|
// view's footer offers when it has cut something.
|
|
238
238
|
let url;
|
|
239
239
|
if (command === 'do') {
|
|
240
|
-
const target = act.activate(
|
|
240
|
+
const target = act.activate(args[0], { session: sessionName });
|
|
241
241
|
// A number that points at text has no page behind it, so `do` reads it
|
|
242
242
|
// rather than making the agent pay for a second command to be told.
|
|
243
243
|
if (target.read != null) {
|
|
@@ -369,7 +369,7 @@ async function main() {
|
|
|
369
369
|
}
|
|
370
370
|
return;
|
|
371
371
|
}
|
|
372
|
-
case 'read': return console.log(act.read(
|
|
372
|
+
case 'read': return console.log(act.read(args[0], { session: sessionName, budget: asked || 2000 }));
|
|
373
373
|
case 'next': return console.log(act.next({ session: sessionName, budget: asked || 500 }));
|
|
374
374
|
case 'find': return console.log(act.find(args.join(' '), { session: sessionName, budget: asked || 500 }));
|
|
375
375
|
case 'fill': return act.fill(Number(args[0]), args.slice(1).join(' '));
|
package/src/cookies.js
CHANGED
|
@@ -411,6 +411,38 @@ export function withheldForScheme(jar, urlStr) {
|
|
|
411
411
|
return jar.cookies.some((c) => c.secure && scopeMatches(c, jar, host, path));
|
|
412
412
|
}
|
|
413
413
|
|
|
414
|
+
/**
|
|
415
|
+
* An ISO timestamp, or undefined when the instant is outside what Date can
|
|
416
|
+
* name. A huge Max-Age used to throw RangeError from toISOString and abort
|
|
417
|
+
* the render of a page that was otherwise fine.
|
|
418
|
+
* @param {number} ms
|
|
419
|
+
* @returns {string | undefined}
|
|
420
|
+
*/
|
|
421
|
+
function expiryISO(ms) {
|
|
422
|
+
try {
|
|
423
|
+
return new Date(ms).toISOString();
|
|
424
|
+
} catch {
|
|
425
|
+
return undefined;
|
|
426
|
+
}
|
|
427
|
+
}
|
|
428
|
+
|
|
429
|
+
/**
|
|
430
|
+
* Strip one pair of wrapping double quotes from a Path. ASP.NET and several
|
|
431
|
+
* Java containers send Path="/admin"; storing the quotes left pathMatches
|
|
432
|
+
* matching nothing, so the cookie was silently never sent again and the login
|
|
433
|
+
* looked gone on the page it was scoped to.
|
|
434
|
+
*
|
|
435
|
+
* Only Path gets this. A cookie value is stored and echoed back verbatim, as
|
|
436
|
+
* RFC 6265 5.2 and every browser have it, as jarFromCookieHeader already
|
|
437
|
+
* treats a seeded one, and because quoting is how a server protects a value
|
|
438
|
+
* holding a space or a comma.
|
|
439
|
+
* @param {string} s
|
|
440
|
+
* @returns {string}
|
|
441
|
+
*/
|
|
442
|
+
function unquotePath(s) {
|
|
443
|
+
return s.length >= 2 && s.startsWith('"') && s.endsWith('"') ? s.slice(1, -1) : s;
|
|
444
|
+
}
|
|
445
|
+
|
|
414
446
|
/**
|
|
415
447
|
* Parse one Set-Cookie header value.
|
|
416
448
|
* @param {string} header
|
|
@@ -444,6 +476,16 @@ export function parseSetCookie(header, requestUrl) {
|
|
|
444
476
|
...(url.protocol === 'https:' ? { secure: true } : {}),
|
|
445
477
|
};
|
|
446
478
|
|
|
479
|
+
// Max-Age and Expires are collected separately: RFC 6265 5.3 says Max-Age
|
|
480
|
+
// wins even when Expires is written last. Express writes them in that order,
|
|
481
|
+
// and Expires is the server's clock, so a host whose clock is behind would
|
|
482
|
+
// otherwise look expired the moment it was set.
|
|
483
|
+
/** @type {string | undefined} */
|
|
484
|
+
let maxAgeExpires;
|
|
485
|
+
let sawMaxAge = false;
|
|
486
|
+
/** @type {string | undefined} */
|
|
487
|
+
let expiresAt;
|
|
488
|
+
|
|
447
489
|
for (const attr of parts.slice(1)) {
|
|
448
490
|
const sep = attr.indexOf('=');
|
|
449
491
|
const key = (sep === -1 ? attr : attr.slice(0, sep)).trim().toLowerCase();
|
|
@@ -455,7 +497,7 @@ export function parseSetCookie(header, requestUrl) {
|
|
|
455
497
|
// dependency this project will not take. User-seeded cookies still scope by
|
|
456
498
|
// the --domain they pass, which normalizeDomain holds to the same floor.
|
|
457
499
|
if (key === 'path') {
|
|
458
|
-
cookie.path = val || '/';
|
|
500
|
+
cookie.path = unquotePath(val) || '/';
|
|
459
501
|
} else if (key === 'secure') {
|
|
460
502
|
cookie.secure = true;
|
|
461
503
|
} else if (key === 'httponly') {
|
|
@@ -463,13 +505,19 @@ export function parseSetCookie(header, requestUrl) {
|
|
|
463
505
|
} else if (key === 'max-age') {
|
|
464
506
|
const age = Number(val);
|
|
465
507
|
if (Number.isFinite(age)) {
|
|
466
|
-
|
|
508
|
+
sawMaxAge = true;
|
|
509
|
+
maxAgeExpires = age <= 0 ? new Date(0).toISOString() : expiryISO(Date.now() + age * 1000);
|
|
467
510
|
}
|
|
468
511
|
} else if (key === 'expires') {
|
|
469
512
|
const exp = Date.parse(val);
|
|
470
|
-
if (!Number.isNaN(exp))
|
|
513
|
+
if (!Number.isNaN(exp)) expiresAt = expiryISO(exp);
|
|
471
514
|
}
|
|
472
515
|
}
|
|
516
|
+
if (sawMaxAge) {
|
|
517
|
+
if (maxAgeExpires) cookie.expires = maxAgeExpires;
|
|
518
|
+
} else if (expiresAt) {
|
|
519
|
+
cookie.expires = expiresAt;
|
|
520
|
+
}
|
|
473
521
|
return cookie;
|
|
474
522
|
}
|
|
475
523
|
|
package/src/distill.js
CHANGED
|
@@ -119,19 +119,46 @@ const asHTML = (text, url = '', opts = {}) =>
|
|
|
119
119
|
* Every heading in the Rust book and every one on an AWS CLI reference page
|
|
120
120
|
* carries a permalink to its own id, so following those would refetch the
|
|
121
121
|
* page the agent is already reading, which is worse than the reading it
|
|
122
|
-
* already gets. A bare fragment is never a destination
|
|
122
|
+
* already gets. A bare fragment is never a destination, and neither is a
|
|
123
|
+
* mailto: or tel: href, which is not a page.
|
|
123
124
|
* @param {any} node - the heading element
|
|
124
125
|
* @param {string} text - its cleaned text
|
|
126
|
+
* @param {string} base - document base, to resolve the href
|
|
127
|
+
* @param {string} pageUrl - the page itself, for same-document checks
|
|
125
128
|
* @returns {string|null}
|
|
126
129
|
*/
|
|
127
|
-
function headingHref(node, text) {
|
|
130
|
+
function headingHref(node, text, base, pageUrl) {
|
|
128
131
|
const anchors = node.querySelectorAll('a[href]');
|
|
129
132
|
if (anchors.length !== 1) return null;
|
|
130
133
|
const href = anchors[0].getAttribute('href') ?? '';
|
|
131
|
-
if (!href || href
|
|
134
|
+
if (!href || !isFollowableHref(href, base, pageUrl)) return null;
|
|
132
135
|
return clean(anchors[0].textContent) === text ? href : null;
|
|
133
136
|
}
|
|
134
137
|
|
|
138
|
+
/**
|
|
139
|
+
* Whether this href is a page oc can fetch, other than the one already open.
|
|
140
|
+
* A bare fragment is the current page. mailto:/tel:/javascript: are not
|
|
141
|
+
* pages: fetchPage prefixes https:// onto a URL with no http(s) scheme, so
|
|
142
|
+
* mailto:hi@example.com became a GET of example.com with password "hi".
|
|
143
|
+
* The href resolves against <base href>, but "here" is the page URL: under
|
|
144
|
+
* <base href="/">, a link to / is the home page, not this one.
|
|
145
|
+
* @param {string} href
|
|
146
|
+
* @param {string} base
|
|
147
|
+
* @param {string} pageUrl
|
|
148
|
+
* @returns {boolean}
|
|
149
|
+
*/
|
|
150
|
+
function isFollowableHref(href, base, pageUrl) {
|
|
151
|
+
try {
|
|
152
|
+
const dest = new URL(href, base || pageUrl || undefined);
|
|
153
|
+
if (!/^https?:$/i.test(dest.protocol)) return false;
|
|
154
|
+
if (!pageUrl) return true;
|
|
155
|
+
const here = new URL(pageUrl);
|
|
156
|
+
return dest.origin !== here.origin || dest.pathname !== here.pathname || dest.search !== here.search;
|
|
157
|
+
} catch {
|
|
158
|
+
return false;
|
|
159
|
+
}
|
|
160
|
+
}
|
|
161
|
+
|
|
135
162
|
/**
|
|
136
163
|
* Reduce raw HTML to an interaction tree: readable text plus numbered
|
|
137
164
|
* elements, in document order. The walk is deterministic and numbering is a
|
|
@@ -217,12 +244,19 @@ export function distill(html, url = '') {
|
|
|
217
244
|
if (/^h[1-6]$/.test(tag)) {
|
|
218
245
|
const text = clean(node.textContent);
|
|
219
246
|
if (text) {
|
|
220
|
-
const href = headingHref(node, text);
|
|
247
|
+
const href = headingHref(node, text, base, url);
|
|
221
248
|
blocks.push({ type: 'heading', level: Number(tag[1]), text, ...(href ? { href } : {}) });
|
|
222
249
|
}
|
|
223
250
|
return;
|
|
224
251
|
}
|
|
225
252
|
if (tag === 'a' && node.getAttribute('href')) {
|
|
253
|
+
// Same rule as headingHref: a fragment is this page, mailto: is not a
|
|
254
|
+
// page. The link keeps its number without the href, because a fragment
|
|
255
|
+
// is often the one handle on a place: rdoc's method signature links to
|
|
256
|
+
// its own id, and as plain text find borrowed the number above it,
|
|
257
|
+
// which read then opened on the method before.
|
|
258
|
+
const raw = node.getAttribute('href');
|
|
259
|
+
const href = isFollowableHref(raw, base, url) ? raw : null;
|
|
226
260
|
// An icon button already takes aria-label or title because it has no
|
|
227
261
|
// text. An anchor around an image is the same shape: img alt is the
|
|
228
262
|
// accessible name and is not a text node, so textContent is empty and
|
|
@@ -233,12 +267,16 @@ export function distill(html, url = '') {
|
|
|
233
267
|
|| clean(node.getAttribute('title') ?? '')
|
|
234
268
|
|| clean(node.querySelector('img')?.getAttribute('alt') ?? '');
|
|
235
269
|
if (text) {
|
|
236
|
-
blocks.push({ type: 'link', text, href:
|
|
270
|
+
blocks.push({ type: 'link', text, ...(href ? { href } : {}) });
|
|
237
271
|
}
|
|
238
272
|
return;
|
|
239
273
|
}
|
|
240
274
|
if (tag === 'input' || tag === 'textarea' || tag === 'select') {
|
|
241
|
-
|
|
275
|
+
// HTML's type attribute is ASCII case-insensitive. type=HIDDEN used to
|
|
276
|
+
// appear as a numbered input, type=SUBMIT as an input rather than a
|
|
277
|
+
// button, and type=PASSWORD as a field named PASSWORD, so a login wall
|
|
278
|
+
// written that way was not detected.
|
|
279
|
+
const kind = (node.getAttribute('type') ?? 'text').toLowerCase();
|
|
242
280
|
if (kind === 'hidden') return;
|
|
243
281
|
if (kind === 'submit' || kind === 'button') {
|
|
244
282
|
blocks.push({ type: 'button', text: node.getAttribute('value') ?? 'submit' });
|
|
@@ -465,7 +503,10 @@ function cleanDocument(html, url = '') {
|
|
|
465
503
|
for (const tag of DROP) {
|
|
466
504
|
for (const el of [...document.querySelectorAll(tag)]) el.remove();
|
|
467
505
|
}
|
|
468
|
-
for (const el of [...document.querySelectorAll('[hidden], [aria-hidden="true"]
|
|
506
|
+
for (const el of [...document.querySelectorAll('[hidden], [aria-hidden="true"]')]) el.remove();
|
|
507
|
+
for (const el of [...document.querySelectorAll('input')]) {
|
|
508
|
+
if ((el.getAttribute('type') ?? '').toLowerCase() === 'hidden') el.remove();
|
|
509
|
+
}
|
|
469
510
|
for (const el of [...document.querySelectorAll('[style]')]) {
|
|
470
511
|
if (/display:\s*none/.test(el.getAttribute('style') ?? '')) el.remove();
|
|
471
512
|
}
|
package/src/render.js
CHANGED
|
@@ -127,7 +127,10 @@ export function render(page, { budget = 500, from = 0 } = {}) {
|
|
|
127
127
|
if (spent + cost > limit && lines.length > head.length) break;
|
|
128
128
|
spent += cost;
|
|
129
129
|
lines.push(line);
|
|
130
|
-
|
|
130
|
+
// A heading that is a link (search result titles) is what do follows, so
|
|
131
|
+
// it has to count here or the footer omits do on a page of only those. A
|
|
132
|
+
// link with no href is a fragment or mailto:, which do only reads.
|
|
133
|
+
if (block.type === 'button' || block.href) hasLinks = true;
|
|
131
134
|
}
|
|
132
135
|
|
|
133
136
|
const rest = blocks.slice(i);
|
package/src/session.js
CHANGED
|
@@ -104,16 +104,29 @@ function unwrapRedirect(url) {
|
|
|
104
104
|
|
|
105
105
|
/**
|
|
106
106
|
* Absolute URL for a handle, or null when the link is not followable
|
|
107
|
-
* (javascript: handlers, malformed
|
|
107
|
+
* (javascript: handlers, mailto:/tel:, same-document fragments, malformed
|
|
108
|
+
* hrefs). fetchPage prefixes https:// onto anything that is not already
|
|
109
|
+
* http(s), so mailto:hi@example.com used to become a GET of example.com
|
|
110
|
+
* with password "hi". A bare fragment is the page already open.
|
|
108
111
|
* @param {string} href
|
|
109
|
-
* @param {string} base
|
|
112
|
+
* @param {string} base - <base href>, or the page URL when it set none
|
|
113
|
+
* @param {string} [pageUrl] - the page itself, for same-document checks
|
|
110
114
|
* @returns {string|null}
|
|
111
115
|
*/
|
|
112
|
-
export function resolveHref(href, base) {
|
|
113
|
-
if (!href
|
|
116
|
+
export function resolveHref(href, base, pageUrl = base) {
|
|
117
|
+
if (!href) return null;
|
|
114
118
|
try {
|
|
115
119
|
const url = new URL(href, base || undefined);
|
|
116
|
-
|
|
120
|
+
if (!/^https?:$/i.test(url.protocol)) return null;
|
|
121
|
+
const dest = unwrapRedirect(url) ?? url.href;
|
|
122
|
+
if (pageUrl) {
|
|
123
|
+
const here = new URL(pageUrl);
|
|
124
|
+
const there = new URL(dest);
|
|
125
|
+
if (here.origin === there.origin && here.pathname === there.pathname && here.search === there.search) {
|
|
126
|
+
return null;
|
|
127
|
+
}
|
|
128
|
+
}
|
|
129
|
+
return dest;
|
|
117
130
|
} catch {
|
|
118
131
|
return null;
|
|
119
132
|
}
|
|
@@ -145,7 +158,7 @@ export function sessionFromPage(page, previous, { cursor = 0 } = {}) {
|
|
|
145
158
|
continue;
|
|
146
159
|
}
|
|
147
160
|
// Relative hrefs are against <base href> when the page set one.
|
|
148
|
-
const href = block.href ? resolveHref(block.href, page.base || page.url) : null;
|
|
161
|
+
const href = block.href ? resolveHref(block.href, page.base || page.url, page.url) : null;
|
|
149
162
|
blocks.push({
|
|
150
163
|
type: block.type,
|
|
151
164
|
text: block.text,
|