# Document table extraction

> LlamaParse (57%), PDFPlumber (51%), and Azure AI Document Intelligence (35%) lead ChatGPT and Google AI mentions for Document table extraction. See full…

HTML: https://parse.gl/topics/pdf-table-extraction · Site index: https://parse.gl/llms.txt

Market: [AI Document Parsing & Extraction APIs](https://parse.gl/markets/ai-document-parsing-extraction-apis)

## Brands AI mentions

| Rank | Brand | Mentioned in |
| --- | --- | --- |
| #1 | LlamaParse | 57% |
| #2 | PDFPlumber | 51% |
| #2 | Azure AI Document Intelligence | 35% |
| #2 | Unstructured | 34% |
| #5 | Docling | 19% |
| #5 | Datalab | 19% |
| #5 | LlamaIndex | 16% |
| #5 | camelot-py | 14% |
| #5 | Google Cloud Document AI | 14% |
| #5 | Reducto | 11% |
| #11 | Camelot (Python library) | 11% |
| #11 | Amazon Textract | 11% |
| #11 | Docling | 9% |
| #11 | Parsimmon | 9% |
| #11 | Adobe PDF Extract API | 7% |
| #11 | Firecrawl | 8% |
| #11 | Mistral OCR | 5% |
| #18 | Tabula | 9% |
| #18 | PyMuPDF | 6% |
| #18 | Microsoft Table Transformer | 4% |
| #18 | Docparser | 4% |
| #18 | LiteParse | 3% |
| #18 | Nanonets | 3% |
| #18 | MinerU | 3% |
| #18 | PyMuPDF4LLM | 3% |
| #18 | Hardparse | 3% |
| #18 | Able2Extract Professional | 2% |
| #18 | Adobe Acrobat Pro DC | 2% |
| #18 | ByteScout PDF Extractor SDK | 2% |
| #18 | Microsoft Learn | 2% |
| #18 | mdparse | 2% |
| #18 | Mistral | 2% |
| #18 | Nutrient | 2% |
| #18 | ABBYY FineReader PDF | 2% |
| #18 | Parsebridge | 2% |
| #18 | Adobe | 1% |
| #18 | Airparser | 1% |
| #18 | AWS | 1% |
| #18 | Microsoft Azure | 1% |
| #18 | Google Cloud | 1% |
| #18 | DocParsing | 1% |
| #18 | DocuClipper | 1% |
| #18 | DS4SD | 1% |
| #18 | ExtractTable | 1% |
| #18 | Open-Parse | 1% |
| #18 | tabula-py | 1% |
| #18 | PaddleOCR | 1% |
| #18 | TableFormer | 1% |
| #18 | pdfstruct | 1% |
| #18 | GMFT | 1% |
| #18 | Nougat | 1% |
| #18 | IBM | 1% |
| #18 | Docling for IBM watsonx | 1% |
| #18 | LibPDF | 1% |
| #18 | Lido | 1% |
| #18 | Marker | 1% |
| #18 | Microsoft Word | 1% |
| #18 | Nutrient Document AI | 1% |
| #18 | Parseur | 1% |
| #18 | PDF4me | 1% |
| #18 | PDFVector | 1% |
| #18 | PeterParser | 1% |
| #18 | Tabulex | 1% |
| #18 | Cardinal | 1% |
| #18 | LLMWhisperer | 1% |
| #66 | pypdf | 7% |
| #66 | Tablers | 1% |
| #66 | openpyxl | 1% |
| #66 | Apache Tika | 1% |

## Questions

- I need a PDF parser that respects table cell structures and does not just dump raw text.
- Can you recommend a document parsing tool that preserves table structures instead of just outputting raw text?
- What are the top API solutions for turning table information from scanned images or PDFs into structured data?
- I am looking for a document parser that keeps table formatting and does not return unformatted text blocks.

## For agents

- [This page as data](https://parse.gl/api/public/topics/data-mining/ai-document-parsing-extraction-apis/pdf-table-extraction)
- [Every brand's share on this topic, with 95% ranges](https://agent.parse.gl/v1/tools/query_metrics?args=%7B%22measures%22%3A%5B%22share_named%22%5D%2C%22by%22%3A%5B%22brand%22%5D%2C%22filter%22%3A%7B%22topic%22%3A%5B%22top_d4e26d79-b3a7-4b50-aa5a-cdcaedb83e5c%22%5D%7D%7D)
- Search the index: `https://parse.gl/api/public/search?q=<words>`

Reuse: Figures and tables on this page are free to republish with attribution: a link to https://parse.gl/topics/pdf-table-extraction beside them. A standard followed link (dofollow) is preferred.

- No account: Public figures and up to 5 examples per list, about 120 brands a day per address.
- Free account: $5 in credit, your brand's first check (20 buyer questions) and a free weekly check.
- After your first top-up: Exports and deeper search results. The first top-up starts at $5.
- Live checks: $0.01 per question per engine ($0.05 on Gemini and Claude).
- Full public answers and pages: 25 free per day, then $0.005 each.
- Public answers older than 90 days: $0.001 each the first time your workspace counts or lists one, then yours.
- An agent can save work before signup: `POST https://agent.parse.gl/v1/workspaces`
- Connect an assistant: `https://agent.parse.gl/mcp`

[Prices](https://parse.gl/pricing.md) · [Map of the site](https://parse.gl/llms.txt)
