Skip to main content

PDF References to CSV — Extract Bibliography Metadata

Extract references from a PDF bibliography, verify the metadata, and download a CSV table for literature review tracking, spreadsheets, or manual QA.

No signup · No credit card · Works in your browser

How does it work?

1

Step 1

Upload your PDF bibliography

Drop a PDF that contains a references section. CiteMe extracts the bibliography server-side and discards the file.

2

Step 2

Verify extracted metadata

Each parsed reference is matched against OpenAlex, CrossRef, and Semantic Scholar so titles, authors, years, journals, and DOIs come from canonical records where possible.

3

Step 3

Download a CSV table

CiteMe returns references.csv with title, authors, year, DOI, journal, match status, source, and confidence columns for review workflows.

By CiteMe Editorial Team·

Which citation styles are supported?

Need it in a specific citation style?

Format the result in the style your paper requires — APA, MLA, Harvard, Vancouver, Chicago, or IEEE.

Related PDF tools

Also try

Frequently asked questions

What does the CSV export include?
The CSV includes title, authors, year, DOI, journal, match status, match source, and confidence columns.
Are the extracted fields verified?
Yes. CiteMe matches parsed references against academic databases such as CrossRef, OpenAlex, and Semantic Scholar before export, so canonical metadata is used when available.
Does this work with scanned PDFs?
Scanned PDFs need OCR first. If no selectable text can be extracted, use the OCR retry flow or run OCR before uploading the bibliography.

Other tools

Generate Citations

Convert & Import

Each result shows its match evidence and metadata source.