1 day trial then $20.00/month - No credit card required now

PDF Scraper

onidivo/pdf-scraper

1 day trial then $20.00/month - No credit card required now

Scrape and extract text from PDF links.

You can access the PDF Scraper programmatically from your own applications by using the Apify API. You can 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": "zXSnbWJh4gfiYs2uY"
6  },
7  "servers": [
8    {
9      "url": "https://api.apify.com/v2"
10    }
11  ],
12  "paths": {
13    "/acts/onidivo~pdf-scraper/run-sync-get-dataset-items": {
14      "post": {
15        "operationId": "run-sync-get-dataset-items-onidivo-pdf-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                "$ref": "#/components/schemas/inputSchema"
27              }
28            }
29          }
30        },
31        "parameters": [
32          {
33            "name": "token",
34            "in": "query",
35            "required": true,
36            "schema": {
37              "type": "string"
38            },
39            "description": "Enter your Apify token here"
40          }
41        ],
42        "responses": {
43          "200": {
44            "description": "OK"
45          }
46        }
47      }
48    },
49    "/acts/onidivo~pdf-scraper/runs": {
50      "post": {
51        "operationId": "runs-sync-onidivo-pdf-scraper",
52        "x-openai-isConsequential": false,
53        "summary": "Executes an Actor and returns information about the initiated run in response.",
54        "tags": [
55          "Run Actor"
56        ],
57        "requestBody": {
58          "required": true,
59          "content": {
60            "application/json": {
61              "schema": {
62                "$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                  "$ref": "#/components/schemas/runsResponseSchema"
85                }
86              }
87            }
88          }
89        }
90      }
91    },
92    "/acts/onidivo~pdf-scraper/run-sync": {
93      "post": {
94        "operationId": "run-sync-onidivo-pdf-scraper",
95        "x-openai-isConsequential": false,
96        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
97        "tags": [
98          "Run Actor"
99        ],
100        "requestBody": {
101          "required": true,
102          "content": {
103            "application/json": {
104              "schema": {
105                "$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          "pdfUrls"
135        ],
136        "properties": {
137          "pdfUrls": {
138            "title": "PDF URLs",
139            "uniqueItems": true,
140            "type": "array",
141            "description": "The PDF URLs to scrape.",
142            "items": {
143              "type": "object",
144              "required": [
145                "url"
146              ],
147              "properties": {
148                "url": {
149                  "type": "string",
150                  "title": "URL of a web page",
151                  "format": "uri"
152                }
153              }
154            }
155          },
156          "savePdfFile": {
157            "title": "Save the PDF file?",
158            "type": "boolean",
159            "description": "Save the PDF file in the key-value store",
160            "default": false
161          },
162          "downloadTimeout": {
163            "title": "Download timeout (s)",
164            "minimum": 5,
165            "maximum": 600,
166            "type": "integer",
167            "description": "The timeout in seconds to download a PDF file.",
168            "default": 90
169          },
170          "proxyConfiguration": {
171            "title": "Proxy Configuration",
172            "type": "object",
173            "description": "Provided options to configure connection with a proxy server.",
174            "default": {
175              "useApifyProxy": true
176            }
177          }
178        }
179      },
180      "runsResponseSchema": {
181        "type": "object",
182        "properties": {
183          "data": {
184            "type": "object",
185            "properties": {
186              "id": {
187                "type": "string"
188              },
189              "actId": {
190                "type": "string"
191              },
192              "userId": {
193                "type": "string"
194              },
195              "startedAt": {
196                "type": "string",
197                "format": "date-time",
198                "example": "2025-01-08T00:00:00.000Z"
199              },
200              "finishedAt": {
201                "type": "string",
202                "format": "date-time",
203                "example": "2025-01-08T00:00:00.000Z"
204              },
205              "status": {
206                "type": "string",
207                "example": "READY"
208              },
209              "meta": {
210                "type": "object",
211                "properties": {
212                  "origin": {
213                    "type": "string",
214                    "example": "API"
215                  },
216                  "userAgent": {
217                    "type": "string"
218                  }
219                }
220              },
221              "stats": {
222                "type": "object",
223                "properties": {
224                  "inputBodyLen": {
225                    "type": "integer",
226                    "example": 2000
227                  },
228                  "rebootCount": {
229                    "type": "integer",
230                    "example": 0
231                  },
232                  "restartCount": {
233                    "type": "integer",
234                    "example": 0
235                  },
236                  "resurrectCount": {
237                    "type": "integer",
238                    "example": 0
239                  },
240                  "computeUnits": {
241                    "type": "integer",
242                    "example": 0
243                  }
244                }
245              },
246              "options": {
247                "type": "object",
248                "properties": {
249                  "build": {
250                    "type": "string",
251                    "example": "latest"
252                  },
253                  "timeoutSecs": {
254                    "type": "integer",
255                    "example": 300
256                  },
257                  "memoryMbytes": {
258                    "type": "integer",
259                    "example": 1024
260                  },
261                  "diskMbytes": {
262                    "type": "integer",
263                    "example": 2048
264                  }
265                }
266              },
267              "buildId": {
268                "type": "string"
269              },
270              "defaultKeyValueStoreId": {
271                "type": "string"
272              },
273              "defaultDatasetId": {
274                "type": "string"
275              },
276              "defaultRequestQueueId": {
277                "type": "string"
278              },
279              "buildNumber": {
280                "type": "string",
281                "example": "1.0.0"
282              },
283              "containerUrl": {
284                "type": "string"
285              },
286              "usage": {
287                "type": "object",
288                "properties": {
289                  "ACTOR_COMPUTE_UNITS": {
290                    "type": "integer",
291                    "example": 0
292                  },
293                  "DATASET_READS": {
294                    "type": "integer",
295                    "example": 0
296                  },
297                  "DATASET_WRITES": {
298                    "type": "integer",
299                    "example": 0
300                  },
301                  "KEY_VALUE_STORE_READS": {
302                    "type": "integer",
303                    "example": 0
304                  },
305                  "KEY_VALUE_STORE_WRITES": {
306                    "type": "integer",
307                    "example": 1
308                  },
309                  "KEY_VALUE_STORE_LISTS": {
310                    "type": "integer",
311                    "example": 0
312                  },
313                  "REQUEST_QUEUE_READS": {
314                    "type": "integer",
315                    "example": 0
316                  },
317                  "REQUEST_QUEUE_WRITES": {
318                    "type": "integer",
319                    "example": 0
320                  },
321                  "DATA_TRANSFER_INTERNAL_GBYTES": {
322                    "type": "integer",
323                    "example": 0
324                  },
325                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
326                    "type": "integer",
327                    "example": 0
328                  },
329                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
330                    "type": "integer",
331                    "example": 0
332                  },
333                  "PROXY_SERPS": {
334                    "type": "integer",
335                    "example": 0
336                  }
337                }
338              },
339              "usageTotalUsd": {
340                "type": "number",
341                "example": 0.00005
342              },
343              "usageUsd": {
344                "type": "object",
345                "properties": {
346                  "ACTOR_COMPUTE_UNITS": {
347                    "type": "integer",
348                    "example": 0
349                  },
350                  "DATASET_READS": {
351                    "type": "integer",
352                    "example": 0
353                  },
354                  "DATASET_WRITES": {
355                    "type": "integer",
356                    "example": 0
357                  },
358                  "KEY_VALUE_STORE_READS": {
359                    "type": "integer",
360                    "example": 0
361                  },
362                  "KEY_VALUE_STORE_WRITES": {
363                    "type": "number",
364                    "example": 0.00005
365                  },
366                  "KEY_VALUE_STORE_LISTS": {
367                    "type": "integer",
368                    "example": 0
369                  },
370                  "REQUEST_QUEUE_READS": {
371                    "type": "integer",
372                    "example": 0
373                  },
374                  "REQUEST_QUEUE_WRITES": {
375                    "type": "integer",
376                    "example": 0
377                  },
378                  "DATA_TRANSFER_INTERNAL_GBYTES": {
379                    "type": "integer",
380                    "example": 0
381                  },
382                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
383                    "type": "integer",
384                    "example": 0
385                  },
386                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
387                    "type": "integer",
388                    "example": 0
389                  },
390                  "PROXY_SERPS": {
391                    "type": "integer",
392                    "example": 0
393                  }
394                }
395              }
396            }
397          }
398        }
399      }
400    }
401  }
402}

PDF 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 PDF Scraper from the options below:

OpenAPI.json

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:

PDF Scraper API in Python

PDF Scraper API in JavaScript

PDF Scraper API through CLI

PDF Scraper API

Developer

Onidivo Technologies

Actor Metrics

23 monthly users
4 bookmarks
98% runs succeeded
23 hours response time
Created in Apr 2023
Modified 7 days ago

Categories

Linkedin Company Profile Scraper

sanjeta/linkedin-company-profile-scraper

The LinkedIn Company Profile Scraper is a powerful and efficient tool designed to extract valuable information from LinkedIn company profiles with ease. Whether you're a market researcher, sales professional, or just curious about a company's background.

ScrapeVerse

168

Google Scholar Scraper

marco.gullo/google-scholar-scraper

Scrape publication details from scholar.google.com. Add your query, time range, and optionally document type (PDF or HTML only). Extract information about articles such as titles, authors, links, related articles, and more.

Marco Gullo

830

Replicate Blog Scraper

yourapiservice/replicate-blog-scraper

The Replicate Blog Scraper lets you easily extract blog content in HTML or plaintext formats. It also captures key metadata like author and publication date, making it a great tool for content analysis and research.

Your API Service

Browserless Scraper Pro

datavoyantlab/browserless-scraper-pro

Browserless Scraper Pro is designed to automate common web tasks such as web scraping, taking screenshots, and generating PDFs without the need for manual browser interaction.

DataVoyantLab

Website Content Crawler

apify/website-content-crawler

Crawl websites and extract text content to feed AI models, LLM applications, vector databases, or RAG pipelines. The Actor supports rich formatting using Markdown, cleans the HTML, downloads files, and integrates well with 🦜🔗 LangChain, LlamaIndex, and the wider LLM ecosystem.

Apify

37.4k

Cheerio Scraper

apify/cheerio-scraper

Crawls websites using raw HTTP requests, parses the HTML with the Cheerio library, and extracts data from the pages using a Node.js code. Supports both recursive crawling and lists of URLs. This actor is a high-performance alternative to apify/web-scraper for websites that do not require JavaScript.

Apify

6.4k

122

Web Scraper

apify/web-scraper

Crawls arbitrary websites using the Chrome browser and extracts structured data from web pages using a provided JavaScript function. The Actor supports both recursive crawling and lists of URLs, and automatically manages concurrency for maximum performance.

Apify

76.5k

467

Puppeteer Scraper

apify/puppeteer-scraper

Crawls websites with the headless Chrome and Puppeteer library using a provided server-side Node.js code. This crawler is an alternative to apify/web-scraper that gives you finer control over the process. Supports both recursive crawling and list of URLs. Supports login to website.

Apify

5.4k