@letsscrapedata/scraper 0.0.80 → 0.0.82
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/dist/index.cjs +1 -1
- package/dist/index.js +1 -1
- package/package.json +5 -4
- package/readme.md +4 -2
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@letsscrapedata/scraper",
|
|
3
|
-
"version": "0.0.
|
|
3
|
+
"version": "0.0.82",
|
|
4
4
|
"description": "Web scraper that scraping web pages by LetsScrapeData XML template",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "./dist/index.cjs",
|
|
@@ -37,18 +37,19 @@
|
|
|
37
37
|
"headless",
|
|
38
38
|
"chrome",
|
|
39
39
|
"patchright",
|
|
40
|
+
"camoufox",
|
|
40
41
|
"playwright",
|
|
41
42
|
"puppeteer",
|
|
42
43
|
"cheerio",
|
|
43
44
|
"crawler",
|
|
44
45
|
"scraper",
|
|
45
|
-
"captcha"
|
|
46
|
-
"apify"
|
|
46
|
+
"captcha"
|
|
47
47
|
],
|
|
48
48
|
"dependencies": {
|
|
49
|
-
"@letsscrapedata/controller": "^0.0.
|
|
49
|
+
"@letsscrapedata/controller": "^0.0.60",
|
|
50
50
|
"@letsscrapedata/proxy": "^0.0.25",
|
|
51
51
|
"@letsscrapedata/utils": "^0.0.27",
|
|
52
|
+
"camoufox-js-lsd": "^0.6.2",
|
|
52
53
|
"cheerio": "^1.0.0",
|
|
53
54
|
"dateformat": "^4.6.3",
|
|
54
55
|
"download": "^8.0.0",
|
package/readme.md
CHANGED
|
@@ -20,7 +20,7 @@
|
|
|
20
20
|
|
|
21
21
|
2. Browser operations supported by the [controller](https://www.npmjs.com/package/@letsscrapedata/controller) package
|
|
22
22
|
|
|
23
|
-
- Same interface of playwright, patchright, puppeteer, cheerio: easy to switch between them
|
|
23
|
+
- Same interface of playwright, patchright, camoufox, puppeteer, cheerio: easy to switch between them
|
|
24
24
|
- Web browsing automation: goto(open) / click / input / hover / select / scroll
|
|
25
25
|
- Automatic captcha solver: Recaptcha(v2 & v3), Cloudflare Turnstile, GeeTest(v3 & v4), image/text, cooridinate
|
|
26
26
|
- State data management: cookies, localStorage, HTTP Headers, custom session data
|
|
@@ -87,6 +87,7 @@ const scraperConfig: ScraperConfig = {
|
|
|
87
87
|
// lsdLaunchOptions: { headless: true },
|
|
88
88
|
// loadUnfinishedTasks: true,
|
|
89
89
|
// loadFailedTasksInterval: 5
|
|
90
|
+
// captcha: { clientKey: "xxx" } // to solve captcha using 2captca
|
|
90
91
|
};
|
|
91
92
|
|
|
92
93
|
const newTasks: TemplateTasks[] = [{ tid: 2000008, parasstrs: ["9"] }];
|
|
@@ -151,7 +152,7 @@ export interface ScraperConfig {
|
|
|
151
152
|
*/
|
|
152
153
|
browserType?: LsdBrowserType;
|
|
153
154
|
/**
|
|
154
|
-
* @default { headless: false }
|
|
155
|
+
* @default { headless: false, geoip: true }
|
|
155
156
|
*/
|
|
156
157
|
lsdLaunchOptions?: LsdLaunchOptions;
|
|
157
158
|
/**
|
|
@@ -169,6 +170,7 @@ export interface ScraperConfig {
|
|
|
169
170
|
* clientKey of 2captcha
|
|
170
171
|
*/
|
|
171
172
|
clientKey: string;
|
|
173
|
+
// if you need to solve captcha in camoufox, please contact administrator
|
|
172
174
|
},
|
|
173
175
|
//////////////////////////////////////////////////////////////////////////// template
|
|
174
176
|
/**
|