{ "openapi": "3.0.1", "info": { "title": "Parser Expert API", "description": "API documentation for Parser Expert.", "license": { "name": "MIT" }, "version": "1.0.0" }, "servers": [ { "url": "https://api.parser.expert" } ], "security": [ { "apiKeyAuth": [] } ], "paths": { "/v1/upload": { "post": { "summary": "Upload Data", "description": "Upload data to the Parser Expert API. You can upload either a file or provide a webpage URL.", "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "type": "object", "properties": { "file": { "type": "string", "format": "binary", "description": "The file to upload. Supported formats are PDF, DOCX, Image, Txt File (maximum of 10 pages per document)." }, "bucket_id": { "type": "string", "description": "The ID of the bucket where the data will be stored.Refer to Quickstart for set extraction fields" }, "webpage_url": { "type": "string", "description": "The URL of the webpage to extract content from. This will be ignored if `file` is provided." } }, "required": ["bucket_id"] } } } }, "responses": { "200": { "description": "Extract upserted successfully", "content": { "application/json": { "schema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "parser_id": { "type": "string", "description": "The ID of the parser." } } }, "message": { "type": "string", "description": "Success message." } } }, "example": { "data": { "parser_id": "f555c13a-846f-4505-95fe-8f72b39edef9" }, "message": "Extract upserted successfully" } } } }, "400": {"$ref": "#/components/responses/BadRequest"}, "401": {"$ref": "#/components/responses/Unauthorized"}, "403": {"$ref": "#/components/responses/Forbidden"}, "404": {"$ref": "#/components/responses/NotFound"}, "405": {"$ref": "#/components/responses/MethodNotAllowed"}, "424": {"$ref": "#/components/responses/FailedDependency"}, "500": {"$ref": "#/components/responses/InternalServerError"} }, "x-codeSamples": [ { "lang": "Python", "source": "import requests\n\nurl = \"https://api.parser.expert/v1/upload\"\n\nheaders = {\n 'X-API-Key': 'sk-xxxx'\n}\n\nfiles = {\n 'file': open('/path/to/your/file.pdf', 'rb'),\n 'bucket_id': (None, '100202')\n}\n\nresponse = requests.post(url, headers=headers, files=files)\n\nprint(response.text)" }, { "lang": "Go", "source": "package main\n\nimport (\n \"bytes\"\n \"fmt\"\n \"mime/multipart\"\n \"net/http\"\n \"os\"\n)\n\nfunc main() {\n url := \"https://api.parser.expert/v1/upload\"\n apiKey := \"sk-xxxxxxxx\"\n filePath := \"/path/to/your/file.pdf\"\n\n file, err := os.Open(filePath)\n if err != nil {\n panic(err)\n }\n defer file.Close()\n\n body := &bytes.Buffer{}\n writer := multipart.NewWriter(body)\n part, err := writer.CreateFormFile(\"file\", \"file.pdf\")\n if err != nil {\n panic(err)\n }\n _, err = io.Copy(part, file)\n if err != nil {\n panic(err)\n }\n\n _ = writer.WriteField(\"bucket_id\", \"100202\")\n writer.Close()\n\n req, err := http.NewRequest(\"POST\", url, body)\n if err != nil {\n panic(err)\n }\n req.Header.Add(\"X-API-Key\", apiKey)\n req.Header.Set(\"Content-Type\", writer.FormDataContentType())\n\n client := &http.Client{}\n resp, err := client.Do(req)\n if err != nil {\n panic(err)\n }\n defer resp.Body.Close()\n\n fmt.Println(\"Response Status:\", resp.Status)\n}" }, { "lang": "Curl", "source": "curl --location --request POST 'https://api.parser.expert/v1/upload' \\\n--header 'X-API-Key: sk-xxxxxxxx' \\\n--form 'file=@\"/path/to/your/file.pdf\"' \\\n--form 'bucket_id=\"100202\"'" }, { "lang": "Java", "source": "import java.io.File;\nimport java.io.FileInputStream;\nimport java.io.IOException;\nimport java.io.OutputStream;\nimport java.net.HttpURLConnection;\nimport java.net.URL;\n\npublic class UploadFile {\n public static void main(String[] args) throws IOException {\n String url = \"https://api.parser.expert/v1/upload\";\n String apiKey = \"sk-xxxxxxxx\";\n String boundary = \"Boundary-\" + System.currentTimeMillis();\n String lineEnd = \"\\r\\n\";\n String twoHyphens = \"--\";\n\n HttpURLConnection connection = (HttpURLConnection) new URL(url).openConnection();\n connection.setDoOutput(true);\n connection.setRequestMethod(\"POST\");\n connection.setRequestProperty(\"X-API-Key\", apiKey);\n connection.setRequestProperty(\"Content-Type\", \"multipart/form-data; boundary=\" + boundary);\n\n OutputStream outputStream = connection.getOutputStream();\n\n // File part\n outputStream.write((twoHyphens + boundary + lineEnd).getBytes());\n outputStream.write(\"Content-Disposition: form-data; name=\\\"file\\\"; filename=\\\"file.pdf\\\"\".getBytes());\n outputStream.write(lineEnd.getBytes());\n outputStream.write(\"Content-Type: application/pdf\".getBytes());\n outputStream.write(lineEnd.getBytes());\n outputStream.write(lineEnd.getBytes());\n\n FileInputStream fileInputStream = new FileInputStream(new File(\"/path/to/your/file.pdf\"));\n int bytesRead;\n byte[] buffer = new byte[4096];\n while ((bytesRead = fileInputStream.read(buffer)) != -1) {\n outputStream.write(buffer, 0, bytesRead);\n }\n outputStream.write(lineEnd.getBytes());\n\n // bucket_id part\n outputStream.write((twoHyphens + boundary + lineEnd).getBytes());\n outputStream.write(\"Content-Disposition: form-data; name=\\\"bucket_id\\\"\".getBytes());\n outputStream.write(lineEnd.getBytes());\n outputStream.write(lineEnd.getBytes());\n outputStream.write(\"100202\".getBytes());\n outputStream.write(lineEnd.getBytes());\n\n // End part\n outputStream.write((twoHyphens + boundary + twoHyphens + lineEnd).getBytes());\n outputStream.flush();\n outputStream.close();\n\n int responseCode = connection.getResponseCode();\n System.out.println(\"Response Code: \" + responseCode);\n }\n}" }, { "lang": "JavaScript", "source": "const axios = require('axios');\nconst FormData = require('form-data');\nconst fs = require('fs');\n\nconst url = 'https://api.parser.expert/v1/upload';\nconst apiKey = 'sk-xxxxxxxx';\nconst filePath = '/path/to/your/file.pdf';\n\nconst form = new FormData();\nform.append('file', fs.createReadStream(filePath));\nform.append('bucket_id', '100202');\n\naxios.post(url, form, {\n headers: {\n 'X-API-Key': apiKey,\n ...form.getHeaders()\n }\n}).then(response => {\n console.log(response.data);\n}).catch(error => {\n console.error(error);\n});" }, { "lang": "PHP", "source": " new CURLFile($filePath),\n 'bucket_id' => '100202'\n);\n$headers = array(\n 'X-API-Key: ' . $apiKey\n);\n\ncurl_setopt($ch, CURLOPT_POSTFIELDS, $post);\ncurl_setopt($ch, CURLOPT_HTTPHEADER, $headers);\n\n$response = curl_exec($ch);\nif (curl_errno($ch)) {\n echo 'Error:' . curl_error($ch);\n}\n\ncurl_close($ch);\n\necho $response;\n?>" } ] } }, "/v1/extracts": { "get": { "summary": "Get Extracted Data", "description": "Retrieve the extracted data using the parser ID and bucket ID.", "parameters": [ { "name": "parser_id", "in": "query", "required": true, "schema": { "type": "string" }, "description": "The ID of the parser. The parser ID is returned when content is uploaded." }, { "name": "bucket_id", "in": "query", "required": true, "schema": { "type": "string" }, "description": "The ID of the bucket." } ], "responses": { "200": { "description": "Processed successfully", "content": { "application/json": { "schema": { "type": "object", "properties": { "data": { "type": "array", "items": { "type": "object", "properties": { "parsed_data": { "type": "object", "additionalProperties": true }, "parser_id": { "type": "string", "description": "The ID of the parser." }, "status": { "type": "string", "description": "The status of the extraction. Available values are `pending` `parsed` `error`." }, "updated_at": { "type": "string", "format": "date-time", "description": "The last update time. The format is ISO 8601. For example, `2024-07-12T20:30:03.042Z`." } } } }, "message": { "type": "string", "description": "Success message." } } }, "examples": { "pending": { "value": { "data": [ { "parsed_data": {}, "parser_id": "f555c13a-846f-4505-95fe-8f72b39edef9", "status": "pending", "updated_at": "2024-07-12T20:30:03.042Z" } ], "message": "Processed successfully" } }, "completed": { "value": { "data": [ { "parsed_data": { "amount_due": 2300, "billing_address": "789 Enterprise Blvd, Innovation City, MA 54321", "currency_code": null, "customer_name": "Innovations Acme", "due_date": "2024-04-19", "invoice_date": "2024-03-20", "invoice_id": "FA20240001", "invoice_total": null, "items": [ { "amount": 300, "description": "Brand Identity Design 1 Hour", "product_code": "BRD", "quantity": 1, "service_date": "2024-03-15", "tax": null, "tax_rate": null, "unit": null, "unit_price": 300 } ], "purchase_order": "PO1234343", "subtotal": 2500, "tax": 200, "total_discount": null, "vendor_address": null, "vendor_name": "Acme Inc." }, "parser_id": "f555c13a-846f-4505-95fe-8f72b39edef9", "status": "parsed", "updated_at": "2024-07-12T20:30:20.286Z" } ], "message": "Processed successfully" } } } } } }, "400": {"$ref": "#/components/responses/BadRequest"}, "401": {"$ref": "#/components/responses/Unauthorized"}, "403": {"$ref": "#/components/responses/Forbidden"}, "404": {"$ref": "#/components/responses/NotFound"}, "405": {"$ref": "#/components/responses/MethodNotAllowed"}, "424": {"$ref": "#/components/responses/FailedDependency"}, "500": {"$ref": "#/components/responses/InternalServerError"} } } } }, "components": { "schemas": { "Error": { "type": "object", "properties": { "error": { "type": "string" }, "message": { "type": "string" } } } }, "securitySchemes": { "apiKeyAuth": { "type": "apiKey", "in": "header", "name": "X-API-Key" } }, "responses": { "BadRequest": { "description": "Bad Request", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "Unauthorized": { "description": "Unauthorized", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "Forbidden": { "description": "Forbidden", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "NotFound": { "description": "Not Found", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "MethodNotAllowed": { "description": "Method Not Allowed", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "FailedDependency": { "description": "Failed Dependency", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "InternalServerError": { "description": "Internal Server Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }