Substack Scraper
Try for free
1 day trial then $20.00/month - No credit card required now
Go to Store
Substack Scraper
qpayre/substack-scraper
Try for free
1 day trial then $20.00/month - No credit card required now
The Substack Author Scraper is a powerful Apify actor that makes it easy for content creators to scrape and retrieve all posts from their favorite Substack authors. With structured data presented in a user-friendly format, analyzing and processing valuable information has never been easier.
Developer
QPSMaintained by Community
Actor Metrics
19 monthly users
No reviews yet
6 bookmarks
67% runs succeeded
1 days response time
Created in Apr 2023
Modified a year ago
Categories
You can access the Substack Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
1{
2 "openapi": "3.0.1",
3 "info": {
4 "version": "0.1",
5 "x-build-id": "9QfRA4H8F0mYr1qdm"
6 },
7 "servers": [
8 {
9 "url": "https://api.apify.com/v2"
10 }
11 ],
12 "paths": {
13 "/acts/qpayre~substack-scraper/run-sync-get-dataset-items": {
14 "post": {
15 "operationId": "run-sync-get-dataset-items-qpayre-substack-scraper",
16 "x-openai-isConsequential": false,
17 "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
18 "tags": [
19 "Run Actor"
20 ],
21 "requestBody": {
22 "required": true,
23 "content": {
24 "application/json": {
25 "schema": {
26 "$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/qpayre~substack-scraper/runs": {
50 "post": {
51 "operationId": "runs-sync-qpayre-substack-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/qpayre~substack-scraper/run-sync": {
93 "post": {
94 "operationId": "run-sync-qpayre-substack-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 "required": [
134 "author",
135 "limit"
136 ],
137 "properties": {
138 "author": {
139 "title": "Author name",
140 "type": "string",
141 "description": "The substack's author name.",
142 "default": "heathercoxrichardson"
143 },
144 "limit": {
145 "title": "Limit number of posts",
146 "type": "integer",
147 "description": "The number of posts to retrieve. Get the latest <limit> posts",
148 "default": 25
149 },
150 "article_content": {
151 "title": "Article content",
152 "type": "boolean",
153 "description": "Include parsed article content in the results.",
154 "default": false
155 }
156 }
157 },
158 "runsResponseSchema": {
159 "type": "object",
160 "properties": {
161 "data": {
162 "type": "object",
163 "properties": {
164 "id": {
165 "type": "string"
166 },
167 "actId": {
168 "type": "string"
169 },
170 "userId": {
171 "type": "string"
172 },
173 "startedAt": {
174 "type": "string",
175 "format": "date-time",
176 "example": "2025-01-08T00:00:00.000Z"
177 },
178 "finishedAt": {
179 "type": "string",
180 "format": "date-time",
181 "example": "2025-01-08T00:00:00.000Z"
182 },
183 "status": {
184 "type": "string",
185 "example": "READY"
186 },
187 "meta": {
188 "type": "object",
189 "properties": {
190 "origin": {
191 "type": "string",
192 "example": "API"
193 },
194 "userAgent": {
195 "type": "string"
196 }
197 }
198 },
199 "stats": {
200 "type": "object",
201 "properties": {
202 "inputBodyLen": {
203 "type": "integer",
204 "example": 2000
205 },
206 "rebootCount": {
207 "type": "integer",
208 "example": 0
209 },
210 "restartCount": {
211 "type": "integer",
212 "example": 0
213 },
214 "resurrectCount": {
215 "type": "integer",
216 "example": 0
217 },
218 "computeUnits": {
219 "type": "integer",
220 "example": 0
221 }
222 }
223 },
224 "options": {
225 "type": "object",
226 "properties": {
227 "build": {
228 "type": "string",
229 "example": "latest"
230 },
231 "timeoutSecs": {
232 "type": "integer",
233 "example": 300
234 },
235 "memoryMbytes": {
236 "type": "integer",
237 "example": 1024
238 },
239 "diskMbytes": {
240 "type": "integer",
241 "example": 2048
242 }
243 }
244 },
245 "buildId": {
246 "type": "string"
247 },
248 "defaultKeyValueStoreId": {
249 "type": "string"
250 },
251 "defaultDatasetId": {
252 "type": "string"
253 },
254 "defaultRequestQueueId": {
255 "type": "string"
256 },
257 "buildNumber": {
258 "type": "string",
259 "example": "1.0.0"
260 },
261 "containerUrl": {
262 "type": "string"
263 },
264 "usage": {
265 "type": "object",
266 "properties": {
267 "ACTOR_COMPUTE_UNITS": {
268 "type": "integer",
269 "example": 0
270 },
271 "DATASET_READS": {
272 "type": "integer",
273 "example": 0
274 },
275 "DATASET_WRITES": {
276 "type": "integer",
277 "example": 0
278 },
279 "KEY_VALUE_STORE_READS": {
280 "type": "integer",
281 "example": 0
282 },
283 "KEY_VALUE_STORE_WRITES": {
284 "type": "integer",
285 "example": 1
286 },
287 "KEY_VALUE_STORE_LISTS": {
288 "type": "integer",
289 "example": 0
290 },
291 "REQUEST_QUEUE_READS": {
292 "type": "integer",
293 "example": 0
294 },
295 "REQUEST_QUEUE_WRITES": {
296 "type": "integer",
297 "example": 0
298 },
299 "DATA_TRANSFER_INTERNAL_GBYTES": {
300 "type": "integer",
301 "example": 0
302 },
303 "DATA_TRANSFER_EXTERNAL_GBYTES": {
304 "type": "integer",
305 "example": 0
306 },
307 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
308 "type": "integer",
309 "example": 0
310 },
311 "PROXY_SERPS": {
312 "type": "integer",
313 "example": 0
314 }
315 }
316 },
317 "usageTotalUsd": {
318 "type": "number",
319 "example": 0.00005
320 },
321 "usageUsd": {
322 "type": "object",
323 "properties": {
324 "ACTOR_COMPUTE_UNITS": {
325 "type": "integer",
326 "example": 0
327 },
328 "DATASET_READS": {
329 "type": "integer",
330 "example": 0
331 },
332 "DATASET_WRITES": {
333 "type": "integer",
334 "example": 0
335 },
336 "KEY_VALUE_STORE_READS": {
337 "type": "integer",
338 "example": 0
339 },
340 "KEY_VALUE_STORE_WRITES": {
341 "type": "number",
342 "example": 0.00005
343 },
344 "KEY_VALUE_STORE_LISTS": {
345 "type": "integer",
346 "example": 0
347 },
348 "REQUEST_QUEUE_READS": {
349 "type": "integer",
350 "example": 0
351 },
352 "REQUEST_QUEUE_WRITES": {
353 "type": "integer",
354 "example": 0
355 },
356 "DATA_TRANSFER_INTERNAL_GBYTES": {
357 "type": "integer",
358 "example": 0
359 },
360 "DATA_TRANSFER_EXTERNAL_GBYTES": {
361 "type": "integer",
362 "example": 0
363 },
364 "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
365 "type": "integer",
366 "example": 0
367 },
368 "PROXY_SERPS": {
369 "type": "integer",
370 "example": 0
371 }
372 }
373 }
374 }
375 }
376 }
377 }
378 }
379 }
380}Substack Scraper 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 Substack Scraper 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:
