Glassdoor ~ Indeed Jobs Scraper | Remove Duplicate Jobs
Pricing
$5.00/month + usage
Go to Store
Glassdoor ~ Indeed Jobs Scraper | Remove Duplicate Jobs
cheap_scraper/glassdoor-job-scraper
Glassdoor ~ Indeed Jobs Scraper | Remove Duplicate Jobs. The Jobs Scraper allows you to collect jobs by providing one or more start URLs. 🔹 Jobs are solely scraped from Glassdoor, however Indeed and Glassdoor belong to the same company and share the exact same job postings.
5.0 (1)
Pricing
$5.00/month + usage
1
Monthly users
5
Runs succeeded
68%
Last modified
12 days ago
You can access the Glassdoor ~ Indeed Jobs Scraper | Remove Duplicate Jobs programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.0",
5 "x-build-id": "5PKcYkcK83vXydviv"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/cheap_scraper~glassdoor-job-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-cheap_scraper-glassdoor-job-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$ref": "#/components/schemas/inputSchema"
27 }
28 }
29 }
30 },
31 "parameters": [
32 {
33 "name": "token",
34 "in": "query",
35 "required": true,
36 "schema": {
37 "type": "string"
38 },
39 "description": "Enter your Apify token here"
40 }
41 ],
42 "responses": {
43 "200": {
44 "description": "OK"
45 }
46 }
47 }
48 },
49 "/acts/cheap_scraper~glassdoor-job-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-cheap_scraper-glassdoor-job-scraper",
52 "x-openai-isConsequential": false,
53 "summary": "Executes an Actor and returns information about the initiated run in response.",
54 "tags": [
55 "Run Actor"
56 ],
57 "requestBody": {
58 "required": true,
59 "content": {
60 "application/json": {
61 "schema": {
62 "$ref": "#/components/schemas/inputSchema"
63 }
64 }
65 }
66 },
67 "parameters": [
68 {
69 "name": "token",
70 "in": "query",
71 "required": true,
72 "schema": {
73 "type": "string"
74 },
75 "description": "Enter your Apify token here"
76 }
77 ],
78 "responses": {
79 "200": {
80 "description": "OK",
81 "content": {
82 "application/json": {
83 "schema": {
84 "$ref": "#/components/schemas/runsResponseSchema"
85 }
86 }
87 }
88 }
89 }
90 }
91 },
92 "/acts/cheap_scraper~glassdoor-job-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-cheap_scraper-glassdoor-job-scraper",
95 "x-openai-isConsequential": false,
96 "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97 "tags": [
98 "Run Actor"
99 ],
100 "requestBody": {
101 "required": true,
102 "content": {
103 "application/json": {
104 "schema": {
105 "$ref": "#/components/schemas/inputSchema"
106 }
107 }
108 }
109 },
110 "parameters": [
111 {
112 "name": "token",
113 "in": "query",
114 "required": true,
115 "schema": {
116 "type": "string"
117 },
118 "description": "Enter your Apify token here"
119 }
120 ],
121 "responses": {
122 "200": {
123 "description": "OK"
124 }
125 }
126 }
127 }
128 },
129 "components": {
130 "schemas": {
131 "inputSchema": {
132 "type": "object",
133 "properties": {
134 "startUrls": {
135 "title": "Start URLs",
136 "type": "array",
137 "description": "One or more URLs of the pages where the crawler will start. Note that the Actor will additionally crawl job page data.",
138 "items": {
139 "type": "object",
140 "required": [
141 "url"
142 ],
143 "properties": {
144 "url": {
145 "type": "string",
146 "title": "URL of a web page",
147 "format": "uri"
148 }
149 }
150 }
151 },
152 "saveOnlyUniqueItems": {
153 "title": "Save Only Unique Items",
154 "type": "boolean",
155 "description": "If enabled, only unique items will be saved. Default is false. JSON field name: `saveOnlyUniqueItems`",
156 "default": false
157 },
158 "maxItems": {
159 "title": "Maximum Items",
160 "maximum": 10000,
161 "type": "integer",
162 "description": "Maximum number of items to scrape. Default is none, it will scrape all the jobs it finds. JSON field name: `maxItems`"
163 },
164 "includeNoSalaryJob": {
165 "title": "Include No Salary Job",
166 "type": "boolean",
167 "description": "Include jobs with no salary. Default is true. JSON field name `includeNoSalaryJob`",
168 "default": true
169 },
170 "proxy": {
171 "title": "Proxy configuration",
172 "type": "object",
173 "description": "Select proxies to be used by your crawler. JSON field name: `proxy`"
174 }
175 }
176 },
177 "runsResponseSchema": {
178 "type": "object",
179 "properties": {
180 "data": {
181 "type": "object",
182 "properties": {
183 "id": {
184 "type": "string"
185 },
186 "actId": {
187 "type": "string"
188 },
189 "userId": {
190 "type": "string"
191 },
192 "startedAt": {
193 "type": "string",
194 "format": "date-time",
195 "example": "2025-01-08T00:00:00.000Z"
196 },
197 "finishedAt": {
198 "type": "string",
199 "format": "date-time",
200 "example": "2025-01-08T00:00:00.000Z"
201 },
202 "status": {
203 "type": "string",
204 "example": "READY"
205 },
206 "meta": {
207 "type": "object",
208 "properties": {
209 "origin": {
210 "type": "string",
211 "example": "API"
212 },
213 "userAgent": {
214 "type": "string"
215 }
216 }
217 },
218 "stats": {
219 "type": "object",
220 "properties": {
221 "inputBodyLen": {
222 "type": "integer",
223 "example": 2000
224 },
225 "rebootCount": {
226 "type": "integer",
227 "example": 0
228 },
229 "restartCount": {
230 "type": "integer",
231 "example": 0
232 },
233 "resurrectCount": {
234 "type": "integer",
235 "example": 0
236 },
237 "computeUnits": {
238 "type": "integer",
239 "example": 0
240 }
241 }
242 },
243 "options": {
244 "type": "object",
245 "properties": {
246 "build": {
247 "type": "string",
248 "example": "latest"
249 },
250 "timeoutSecs": {
251 "type": "integer",
252 "example": 300
253 },
254 "memoryMbytes": {
255 "type": "integer",
256 "example": 1024
257 },
258 "diskMbytes": {
259 "type": "integer",
260 "example": 2048
261 }
262 }
263 },
264 "buildId": {
265 "type": "string"
266 },
267 "defaultKeyValueStoreId": {
268 "type": "string"
269 },
270 "defaultDatasetId": {
271 "type": "string"
272 },
273 "defaultRequestQueueId": {
274 "type": "string"
275 },
276 "buildNumber": {
277 "type": "string",
278 "example": "1.0.0"
279 },
280 "containerUrl": {
281 "type": "string"
282 },
283 "usage": {
284 "type": "object",
285 "properties": {
286 "ACTOR_COMPUTE_UNITS": {
287 "type": "integer",
288 "example": 0
289 },
290 "DATASET_READS": {
291 "type": "integer",
292 "example": 0
293 },
294 "DATASET_WRITES": {
295 "type": "integer",
296 "example": 0
297 },
298 "KEY_VALUE_STORE_READS": {
299 "type": "integer",
300 "example": 0
301 },
302 "KEY_VALUE_STORE_WRITES": {
303 "type": "integer",
304 "example": 1
305 },
306 "KEY_VALUE_STORE_LISTS": {
307 "type": "integer",
308 "example": 0
309 },
310 "REQUEST_QUEUE_READS": {
311 "type": "integer",
312 "example": 0
313 },
314 "REQUEST_QUEUE_WRITES": {
315 "type": "integer",
316 "example": 0
317 },
318 "DATA_TRANSFER_INTERNAL_GBYTES": {
319 "type": "integer",
320 "example": 0
321 },
322 "DATA_TRANSFER_EXTERNAL_GBYTES": {
323 "type": "integer",
324 "example": 0
325 },
326 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
327 "type": "integer",
328 "example": 0
329 },
330 "PROXY_SERPS": {
331 "type": "integer",
332 "example": 0
333 }
334 }
335 },
336 "usageTotalUsd": {
337 "type": "number",
338 "example": 0.00005
339 },
340 "usageUsd": {
341 "type": "object",
342 "properties": {
343 "ACTOR_COMPUTE_UNITS": {
344 "type": "integer",
345 "example": 0
346 },
347 "DATASET_READS": {
348 "type": "integer",
349 "example": 0
350 },
351 "DATASET_WRITES": {
352 "type": "integer",
353 "example": 0
354 },
355 "KEY_VALUE_STORE_READS": {
356 "type": "integer",
357 "example": 0
358 },
359 "KEY_VALUE_STORE_WRITES": {
360 "type": "number",
361 "example": 0.00005
362 },
363 "KEY_VALUE_STORE_LISTS": {
364 "type": "integer",
365 "example": 0
366 },
367 "REQUEST_QUEUE_READS": {
368 "type": "integer",
369 "example": 0
370 },
371 "REQUEST_QUEUE_WRITES": {
372 "type": "integer",
373 "example": 0
374 },
375 "DATA_TRANSFER_INTERNAL_GBYTES": {
376 "type": "integer",
377 "example": 0
378 },
379 "DATA_TRANSFER_EXTERNAL_GBYTES": {
380 "type": "integer",
381 "example": 0
382 },
383 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
384 "type": "integer",
385 "example": 0
386 },
387 "PROXY_SERPS": {
388 "type": "integer",
389 "example": 0
390 }
391 }
392 }
393 }
394 }
395 }
396 }
397 }
398 }
399}Glassdoor ~ Indeed Jobs Scraper | Remove Duplicate Jobs OpenAPI definition
OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Glassdoor ~ Indeed Jobs Scraper | Remove Duplicate Jobs from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients:
Pricing
Pricing model
RentalTo use this Actor, you have to pay a monthly rental fee to the developer. The rent is subtracted from your prepaid usage every month after the free trial period. You also pay for the Apify platform usage.
Free trial
3 days
Price
$5.00
