PDF to Text OCR: Turn PDF and Image Links into Clean Text

[
  {
    "url": "https://www.irs.gov/pub/irs-pdf/fw9.pdf",
    "finalUrl": "https://www.irs.gov/pub/irs-pdf/fw9.pdf",
    "status": "complete",
    "fileType": "pdf",
    "contentType": "application/pdf",
    "fileSizeBytes": 140815,
    "pageCount": 6,
    "pagesProcessed": 6,
    "pagesTruncated": false,
    "textPages": 6,
    "ocrPages": 0,
    "format": "text",
    "ocrLanguages": null,
    "charCount": 37820,
    "text": "W-9\n\nForm\n(Rev. March 2024)\nDepartment of the Treasury\nInternal Revenue Service\n\nRequest for Taxpayer\nIdentification Number and Certification…",
    "pages": [
      { "pageNumber": 1, "method": "text", "charCount": 5703, "ocrConfidence": null, "text": "W-9\n\nForm\n(Rev. March 2024)…", "error": null }
    ],
    "title": "Form W-9 (Rev. March 2024)",
    "metadata": { "subject": "Request for Taxpayer Identification Number and Certification", "creator": "Designer 6.5", "pdfVersion": "1.7" },
    "encrypted": false,
    "error": null,
    "warnings": [],
    "fetchedAt": "2026-10-13T05:23:31.200Z",
    "processedAt": "2026-10-13T05:23:31.254Z"
  },
  {
    "url": "https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png",
    "status": "complete",
    "fileType": "png",
    "pageCount": 1,
    "textPages": 0,
    "ocrPages": 1,
    "ocrLanguages": ["eng"],
    "charCount": 414,
    "text": "The (quick) [brown] {fox} jumps!\nOver the $43,456.78 <lazy> #90 dog\n& duck/goose, as 12.5% of E-mail\nfrom [email protected] is spam.…",
    "pages": [
      { "pageNumber": 1, "method": "ocr", "charCount": 414, "ocrConfidence": 90.2, "text": "The (quick) [brown] {fox} jumps!…", "error": null }
    ],
    "title": null,
    "metadata": null,
    "error": null,
    "warnings": []
  }
]

from apify_client import ApifyClient

client = ApifyClient("YOUR_APIFY_TOKEN")
run = client.actor("cliqtomedia/pdf-text-ocr").call(run_input={
    "urls": [
        "https://www.irs.gov/pub/irs-pdf/fw9.pdf"
    ],
    "ocr": "auto"
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

curl -X POST "https://api.apify.com/v2/acts/cliqtomedia~pdf-text-ocr/run-sync-get-dataset-items?token=YOUR_APIFY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"urls": ["https://www.irs.gov/pub/irs-pdf/fw9.pdf"], "ocr": "auto"}'

# pip install langchain-apify
# set APIFY_TOKEN in your environment
from langchain_apify import ApifyActorsTool

tool = ApifyActorsTool("cliqtomedia/pdf-text-ocr")
result = tool.invoke({"run_input": {"urls": ["https://www.irs.gov/pub/irs-pdf/fw9.pdf"], "ocr": "auto"}})
print(result)