Extract references from PDF and create new library items from them

Greetings!

Input: PDF-file containing a “References” section, listing a number of cited papers mentioning Author1, Author 2, Journal, Volume, Year for each cited paper.
Operation: Endnote X8 extracts list of cited papers from PDF, looks up metadata of each cited paper using a server (Google Scholar, Pubmed, etc.) and adds these as new library items in the users “My Library” folder.
Output: New subcollection of library items containing all papers cited in PDF that was used for input.

How does one can do this with EndNote X8?

Thank you.

at this time, using a 3rd party commercial database (like Scopus or perhaps web of science) and exporting to endnote, or manually.  

Dear Leanne,

  For instance, I have a PDF with article. How do I exctract all items of its Reference section and pass is to the commercial database (Scopus, WoS, etc.) and feed to EndNote.

  Can you clarify workflow in more details please?

Thank you.

Each one will be different. I use Scopus, which allows me to select the article and scroll to cited references and select some or all and export them to endnote.  Currently Endnote has no way to perform this function.  

Thank you for the suggestion on Scopus.

So far I have researched the following workflow:

  1. extract a list of all references from a PDF article using CERMINE;

  2. parse the list using WizFolio (credit to Kumar Vignesh from EndNote technical support team) and export found references to a RIS file;

  3. import the RIS file to EndNote (see http://www.screencast.com/t/NjFkMDc1N).

The way is still long and not straightforward…

I’ve written a Chrome Extension called Scholarcy that extracts the references from a PDF as BibTex.

It does a whole bunch of other stuff too but if you just want the references you can disable the other options.

In the current release, the PDF needs to be at a public URL (i.e. not requiring an institutional log in).

Best

Phil

Does Endnote support import of BibTex files?

I’ve written a Chrome Extension called Scholarcy that extracts the references from a PDF as BibTex.

It does a whole bunch of other stuff too but if you just want the references you can disable the other options.

In the current release, the PDF needs to be at a public URL (i.e. not requiring an institutional log in).

I can add RIS support if there is demand for it.

I have an API also, so if the Endnote developers wanted to add this as an integral feature it would be possible.

Best

Phil

scholarcy.com