job-scout 1.0.0
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 +120 -0
- package/package.json +41 -0
package/README.md
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
1
|
+
# job-scout
|
|
2
|
+
|
|
3
|
+
TypeScript-first job scraping library for LinkedIn, Indeed, ZipRecruiter, Glassdoor, Google Jobs, Bayt, Naukri, and BDJobs.
|
|
4
|
+
|
|
5
|
+
## Install
|
|
6
|
+
|
|
7
|
+
```bash
|
|
8
|
+
bun add job-scout
|
|
9
|
+
```
|
|
10
|
+
|
|
11
|
+
Node `>=20` is required.
|
|
12
|
+
|
|
13
|
+
## Quick Start
|
|
14
|
+
|
|
15
|
+
```ts
|
|
16
|
+
import { scoutJobs } from 'job-scout'
|
|
17
|
+
|
|
18
|
+
const jobs = await scoutJobs(
|
|
19
|
+
{
|
|
20
|
+
sites: ['indeed', 'linkedin', 'zipRecruiter', 'google'],
|
|
21
|
+
query: 'software engineer',
|
|
22
|
+
location: 'San Francisco, CA',
|
|
23
|
+
pagination: { limitPerSite: 20 },
|
|
24
|
+
filters: { postedWithinHours: 72 },
|
|
25
|
+
google: {
|
|
26
|
+
query: 'software engineer jobs near San Francisco, CA since yesterday',
|
|
27
|
+
},
|
|
28
|
+
indeed: { country: 'usa' },
|
|
29
|
+
linkedin: { fetchDescription: true },
|
|
30
|
+
},
|
|
31
|
+
{
|
|
32
|
+
transport: {
|
|
33
|
+
timeoutMs: 20_000,
|
|
34
|
+
},
|
|
35
|
+
logging: {
|
|
36
|
+
level: 'warn',
|
|
37
|
+
},
|
|
38
|
+
},
|
|
39
|
+
)
|
|
40
|
+
|
|
41
|
+
console.log(jobs.length)
|
|
42
|
+
console.log(jobs[0])
|
|
43
|
+
```
|
|
44
|
+
|
|
45
|
+
## Client API
|
|
46
|
+
|
|
47
|
+
```ts
|
|
48
|
+
import { createClient } from 'job-scout'
|
|
49
|
+
|
|
50
|
+
const client = createClient({
|
|
51
|
+
transport: { timeoutMs: 20_000 },
|
|
52
|
+
logging: { level: 'warn' },
|
|
53
|
+
})
|
|
54
|
+
|
|
55
|
+
const jobs = await client.scoutJobs({
|
|
56
|
+
sites: ['indeed'],
|
|
57
|
+
query: 'backend engineer',
|
|
58
|
+
location: 'Austin, TX',
|
|
59
|
+
indeed: { country: 'usa' },
|
|
60
|
+
})
|
|
61
|
+
```
|
|
62
|
+
|
|
63
|
+
## Public API
|
|
64
|
+
|
|
65
|
+
- `createClient(config?: JobScoutConfig): JobScoutClient`
|
|
66
|
+
- `scoutJobs(request: JobSearchRequest, config?: JobScoutConfig): Promise<Job[]>`
|
|
67
|
+
- `scoutJobRows(request: JobSearchRequest, config?: JobScoutConfig): Promise<JobRow[]>`
|
|
68
|
+
- `toJobRows(jobs: Job[]): JobRow[]`
|
|
69
|
+
|
|
70
|
+
## Request Model
|
|
71
|
+
|
|
72
|
+
`JobSearchRequest` supports:
|
|
73
|
+
|
|
74
|
+
- `sites?: JobSite[]`
|
|
75
|
+
- `query?: string`
|
|
76
|
+
- `location?: string`
|
|
77
|
+
- `pagination?: { limitPerSite?: number; offset?: number }`
|
|
78
|
+
- `filters?: { distanceMiles?: number; remote?: boolean; easyApply?: boolean; employmentType?: ...; postedWithinHours?: number }`
|
|
79
|
+
- `linkedin?: { fetchDescription?: boolean; companyIds?: number[] }`
|
|
80
|
+
- `indeed?: { country?: string }`
|
|
81
|
+
- `google?: { query?: string }`
|
|
82
|
+
|
|
83
|
+
Constraint rules enforced at runtime:
|
|
84
|
+
|
|
85
|
+
- If `sites` includes `google`, `google.query` is required.
|
|
86
|
+
- For Indeed, use only one filter group at a time:
|
|
87
|
+
- `filters.postedWithinHours`
|
|
88
|
+
- `filters.easyApply`
|
|
89
|
+
- `filters.employmentType`/`filters.remote`
|
|
90
|
+
- For LinkedIn, `filters.postedWithinHours` and `filters.easyApply` cannot both be enabled.
|
|
91
|
+
|
|
92
|
+
## Configuration
|
|
93
|
+
|
|
94
|
+
`JobScoutConfig`:
|
|
95
|
+
|
|
96
|
+
- `transport`: proxies, user agent, CA cert path, timeout
|
|
97
|
+
- `performance`: global/site concurrency, retry policy, adaptive concurrency
|
|
98
|
+
- `output`: description format, salary annualization, salary fallback behavior
|
|
99
|
+
- `logging`: `error | warn | info | debug`
|
|
100
|
+
|
|
101
|
+
## Testing
|
|
102
|
+
|
|
103
|
+
Unit tests:
|
|
104
|
+
|
|
105
|
+
```bash
|
|
106
|
+
bun run test
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
Live integration tests:
|
|
110
|
+
|
|
111
|
+
```bash
|
|
112
|
+
JOBSCOUT_TEST_PROXIES="host1:port1,host2:port2" \
|
|
113
|
+
bun run test:integration:live
|
|
114
|
+
```
|
|
115
|
+
|
|
116
|
+
Full suite:
|
|
117
|
+
|
|
118
|
+
```bash
|
|
119
|
+
bun run test:all
|
|
120
|
+
```
|
package/package.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
{
|
|
2
|
+
"name": "job-scout",
|
|
3
|
+
"version": "1.0.0",
|
|
4
|
+
"description": "TypeScript-native job-scout library",
|
|
5
|
+
"type": "module",
|
|
6
|
+
"main": "dist/index.js",
|
|
7
|
+
"types": "dist/index.d.ts",
|
|
8
|
+
"exports": {
|
|
9
|
+
".": {
|
|
10
|
+
"types": "./dist/index.d.ts",
|
|
11
|
+
"import": "./dist/index.js"
|
|
12
|
+
}
|
|
13
|
+
},
|
|
14
|
+
"files": [
|
|
15
|
+
"dist"
|
|
16
|
+
],
|
|
17
|
+
"packageManager": "bun@1.3.5",
|
|
18
|
+
"scripts": {
|
|
19
|
+
"build": "tsc -p tsconfig.build.json",
|
|
20
|
+
"typecheck": "tsc -p tsconfig.json --noEmit",
|
|
21
|
+
"test": "bun run test:unit",
|
|
22
|
+
"test:unit": "bun test ./test/*.test.ts",
|
|
23
|
+
"test:integration:live": "bun test ./test/integration/live",
|
|
24
|
+
"test:all": "bun run test:unit && bun run test:integration:live",
|
|
25
|
+
"test:watch": "bun test --watch ./test/*.test.ts"
|
|
26
|
+
},
|
|
27
|
+
"engines": {
|
|
28
|
+
"node": ">=20"
|
|
29
|
+
},
|
|
30
|
+
"dependencies": {
|
|
31
|
+
"cheerio": "^1.1.2",
|
|
32
|
+
"turndown": "^7.2.0",
|
|
33
|
+
"undici": "^7.16.0",
|
|
34
|
+
"zod": "^4.1.5"
|
|
35
|
+
},
|
|
36
|
+
"devDependencies": {
|
|
37
|
+
"@types/node": "^24.3.0",
|
|
38
|
+
"@types/turndown": "^5.0.5",
|
|
39
|
+
"typescript": "^5.9.2"
|
|
40
|
+
}
|
|
41
|
+
}
|