spectrawl 0.3.14 → 0.3.15
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/package.json +1 -1
- package/src/search/scraper.js +2 -2
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "spectrawl",
|
|
3
|
-
"version": "0.3.
|
|
3
|
+
"version": "0.3.15",
|
|
4
4
|
"description": "The unified web layer for AI agents. Search (6 engines), stealth browse (Camoufox + Playwright), auth (cookies, multi-account), act (24 adapters, 30+ platforms), proxy rotation. Self-hosted, free.",
|
|
5
5
|
"main": "src/index.js",
|
|
6
6
|
"types": "index.d.ts",
|
package/src/search/scraper.js
CHANGED
|
@@ -12,7 +12,7 @@ const { jinaExtract } = require('./engines/jina')
|
|
|
12
12
|
*/
|
|
13
13
|
async function scrapeUrls(urls, opts = {}) {
|
|
14
14
|
const results = {}
|
|
15
|
-
const timeout = opts.timeout ||
|
|
15
|
+
const timeout = opts.timeout || 5000 // 5s per URL — balances speed vs quality
|
|
16
16
|
const concurrent = opts.concurrent || 5
|
|
17
17
|
const engine = opts.engine || 'auto' // 'jina', 'readability', 'auto'
|
|
18
18
|
|
|
@@ -35,7 +35,7 @@ async function scrapeUrls(urls, opts = {}) {
|
|
|
35
35
|
}
|
|
36
36
|
|
|
37
37
|
async function scrapeUrl(url, opts = {}) {
|
|
38
|
-
const { timeout =
|
|
38
|
+
const { timeout = 5000, engine = 'auto', browse } = opts
|
|
39
39
|
|
|
40
40
|
// Try Jina first if available (better markdown output)
|
|
41
41
|
if (engine === 'jina' || engine === 'auto') {
|