Best PDF Extraction Tools in 2026

from unstructured.partition.pdf import partition_pdf

elements = partition_pdf(
    filename="contract.pdf",
    strategy="hi_res",
    infer_table_structure=True,
    extract_images_in_pdf=True
)

for element in elements:
    print(f"{element.category}: {element.text[:100]}")
    if element.category == "Table":
        print(element.metadata.text_as_html)

from llama_parse import LlamaParse
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

parser = LlamaParse(
    api_key="llx-...",
    result_type="markdown",
    num_workers=4
)

documents = SimpleDirectoryReader(
    input_files=["report.pdf"],
    file_extractor={".pdf": parser}
).load_data()

index = VectorStoreIndex.from_documents(documents)
query_engine = index.as_query_engine()
response = query_engine.query("What were Q4 revenues?")

from tika import parser

# Extract text and metadata from a PDF
parsed = parser.from_file("document.pdf")

text = parsed["content"]
metadata = parsed["metadata"]

print(f"Title: {metadata.get('title', 'N/A')}")
print(f"Author: {metadata.get('Author', 'N/A')}")
print(f"Pages: {metadata.get('xmpTPg:NPages', 'N/A')}")
print(f"Content preview: {text[:500]}")

from docling.document_converter import DocumentConverter

converter = DocumentConverter()
result = converter.convert("research_paper.pdf")

# Access structured document
doc = result.document
print(f"Title: {doc.title}")

# Export as markdown
markdown = result.document.export_to_markdown()

# Export as structured JSON
json_output = result.document.export_to_dict()
for table in doc.tables:
    print(table.export_to_dataframe())

from mistralai import Mistral

client = Mistral(api_key="...")

response = client.ocr.process(
    model="mistral-ocr-2512",
    document={
        "type": "document_url",
        "document_url": "https://example.com/annual_report.pdf"
    }
)

for page in response.pages:
    print(f"Page {page.index}:")
    print(page.markdown[:500])

from reducto import Reducto

client = Reducto(api_key="r_...")

result = client.parse(
    file="annual_report.pdf",
    options={
        "table_mode": "accurate",
        "return_bounding_boxes": True
    }
)

for chunk in result.chunks:
    print(f"Type: {chunk.type}, Content: {chunk.content[:100]}")
    if chunk.type == "table":
        print(chunk.to_dataframe())

from marker.converters.pdf import PdfConverter
from marker.models import create_model_dict

models = create_model_dict()
converter = PdfConverter(artifact_dict=models)

rendered = converter("paper.pdf")

# Access markdown output
markdown_text = rendered.markdown
print(markdown_text[:500])

# Access extracted images
for img in rendered.images:
    img.save(f"extracted_{img.id}.png")

import fitz  # PyMuPDF

doc = fitz.open("document.pdf")

for page_num, page in enumerate(doc):
    # Extract text with layout preservation
    text = page.get_text("text")

    # Extract text blocks with position info
    blocks = page.get_text("dict")["blocks"]
    for block in blocks:
        if block["type"] == 0:  # text block
            for line in block["lines"]:
                print(line["spans"][0]["text"])

    # Extract images
    for img in page.get_images():
        xref = img[0]
        pix = fitz.Pixmap(doc, xref)
        pix.save(f"page{page_num}_img{xref}.png")

import boto3

textract = boto3.client("textract")

response = textract.analyze_document(
    Document={"S3Object": {"Bucket": "docs", "Name": "form.pdf"}},
    FeatureTypes=["TABLES", "FORMS"]
)

for block in response["Blocks"]:
    if block["BlockType"] == "LINE":
        print(f"Text: {block['Text']}")
    elif block["BlockType"] == "TABLE":
        print(f"Table at confidence: {block['Confidence']:.1f}%")
    elif block["BlockType"] == "KEY_VALUE_SET":
        print(f"Form field detected")

const pdfjsLib = require("pdfjs-dist/legacy/build/pdf.js");

async function extractText(pdfPath) {
  const doc = await pdfjsLib.getDocument(pdfPath).promise;
  const results = [];

  for (let i = 1; i <= doc.numPages; i++) {
    const page = await doc.getPage(i);
    const content = await page.getTextContent();
    const text = content.items.map(item => item.str).join(" ");
    results.push({ page: i, text });
  }

  return results;
}

extractText("report.pdf").then(pages =>
  pages.forEach(p => console.log(`Page ${p.page}: ${p.text.slice(0, 100)}`))
);