テキストとテーブルを PDFファイルから抽出

# JSON with tables — /v2/pdf/extract-text (recommended)
curl -X POST \
  https://api.convertfilefast.com/v2/pdf/extract-text \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@report.pdf" \
  -F "pages=1-5" \
  -F "extract_tables=true"

# Plain text file — /v2/convert/pdf-to-txt
curl -X POST \
  https://api.convertfilefast.com/v2/convert/pdf-to-txt \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@report.pdf" \
  --output extracted.txt

import requests

# Option 1: JSON with tables (extract-text) — rich structured output
response = requests.post(
    "https://api.convertfilefast.com/v2/pdf/extract-text",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"file": open("report.pdf", "rb")},
    data={"pages": "1-5", "extract_tables": "true"}
)

data = response.json()
for page in data["pages"]:
    print(f"Page {page['page_number']}: {page['text'][:100]}...")

# Option 2: Plain text file (pdf-to-txt) — simple .txt output
response = requests.post(
    "https://api.convertfilefast.com/v2/convert/pdf-to-txt",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files={"file": open("report.pdf", "rb")}
)

with open("extracted.txt", "wb") as f:
    f.write(response.content)

const formData = new FormData();
formData.append("file", fs.createReadStream("report.pdf"));
formData.append("pages", "1-5");
formData.append("extract_tables", "true");

const response = await fetch(
  "https://api.convertfilefast.com/v2/pdf/extract-text",
  {
    method: "POST",
    headers: { "Authorization": "Bearer YOUR_API_KEY" },
    body: formData,
  }
);

const data = await response.json();
console.log(`Extracted ${data.total_pages} pages`);

// n8n HTTP Request Node
{
  "method": "POST",
  "url": "https://api.convertfilefast.com/v2/pdf/extract-text",
  "contentType": "multipart-form-data",
  "bodyParameters": {
    "parameters": [
      { "name": "file", "parameterType": "formBinaryData", "inputDataFieldName": "data" },
      { "name": "extract_tables", "value": "true" }
    ]
  },
  "options": { "response": { "responseFormat": "json" } }
}