- Crossref API: https://github.com/CrossRef/rest-api-doc/blob/master/rest_api.md
- Crossref metadata search API
- CrossRef DOI Content Negotiation
- Text and Data Mining TDM
Stable version from CRAN
install.packages("rcrossref")Or development version from GitHub
install.packages("devtools")
devtools::install_github("ropensci/rcrossref")Load rcrossref
library('rcrossref')Use CrossRef's DOI Content Negotiation service, where you can citations back in various formats, including apa
cr_cn(dois = "10.1126/science.169.3946.635", format = "text", style = "apa")
#> [1] "Frank, H. S. (1970). The Structure of Ordinary Water: New data and interpretations are yielding new insights into this fascinating substance. Science, 169(3946), 635–641. doi:10.1126/science.169.3946.635"bibtex
cat(cr_cn(dois = "10.1126/science.169.3946.635", format = "bibtex"))
#> @article{Frank_1970,
#> doi = {10.1126/science.169.3946.635},
#> url = {http://dx.doi.org/10.1126/science.169.3946.635},
#> year = 1970,
#> month = {aug},
#> publisher = {American Association for the Advancement of Science ({AAAS})},
#> volume = {169},
#> number = {3946},
#> pages = {635--641},
#> author = {H. S. Frank},
#> title = {The Structure of Ordinary Water: New data and interpretations are yielding new insights into this fascinating substance},
#> journal = {Science}
#> }bibentry
cr_cn(dois = "10.6084/m9.figshare.97218", format = "bibentry")
#> Boettiger C (2012). "Regime shifts in ecology and evolution (PhD
#> Dissertation)." doi: 10.6084/m9.figshare.97218 (URL:
#> http://doi.org/10.6084/m9.figshare.97218), <URL:
#> https://doi.org/10.6084/m9.figshare.97218>.Citation count, using OpenURL
cr_citation_count(doi = "10.1371/journal.pone.0042793")
#> [1] 10The following functions all use the CrossRef API.
cr_funders(query = "NSF")
#> $meta
#> total_results search_terms start_index items_per_page
#> 1 8 NSF 0 20
#>
#> $data
#> # A tibble: 8 × 6
#> id location
#> <chr> <chr>
#> 1 100003187 United States
#> 2 100008367 Denmark
#> 3 501100004190 Norway
#> 4 100000179 United States
#> 5 100006445 United States
#> 6 501100000930 Australia
#> 7 100000001 United States
#> 8 501100001809 China
#> # ... with 4 more variables: name <chr>, alt.names <chr>, uri <chr>,
#> # tokens <chr>cr_agency(dois = '10.13039/100000001')
#> $DOI
#> [1] "10.13039/100000001"
#>
#> $agency
#> $agency$id
#> [1] "crossref"
#>
#> $agency$label
#> [1] "CrossRef"cr_works(filter = c(has_orcid = TRUE, from_pub_date = '2004-04-04'), limit = 1)
#> $meta
#> total_results search_terms start_index items_per_page
#> 1 419228 NA 0 1
#>
#> $data
#> # A tibble: 1 × 24
#> alternative.id container.title created deposited
#> <chr> <chr> <chr> <chr>
#> 1 2015-11-11 2015-11-11
#> # ... with 20 more variables: DOI <chr>, funder <list>, indexed <chr>,
#> # ISBN <chr>, ISSN <chr>, issued <chr>, link <list>, member <chr>,
#> # prefix <chr>, publisher <chr>, reference.count <chr>, score <chr>,
#> # source <chr>, subject <chr>, title <chr>, type <chr>, URL <chr>,
#> # assertion <list>, author <list>, `clinical-trial-number` <list>
#>
#> $facets
#> NULLcr_journals(issn = c('1803-2427','2326-4225'))
#> # A tibble: 2 × 16
#> alternative.id container.title created deposited funder indexed ISBN
#> <chr> <chr> <chr> <chr> <list> <chr> <chr>
#> 1 <NULL>
#> 2 <NULL>
#> # ... with 9 more variables: ISSN <chr>, issued <chr>, link <list>,
#> # publisher <chr>, subject <chr>, title <chr>, assertion <list>,
#> # author <list>, `clinical-trial-number` <list>cr_licenses(query = 'elsevier')
#> $meta
#> total_results search_terms start_index items_per_page
#> 1 13 elsevier 0 20
#>
#> $data
#> # A tibble: 13 × 2
#> URL
#> <chr>
#> 1 http://creativecommons.org/licenses/by-nc-nd/3.0/
#> 2 http://creativecommons.org/licenses/by-nc-nd/4.0/
#> 3 http://creativecommons.org/licenses/by-nc/4.0/
#> 4 http://creativecommons.org/licenses/by/3.0/
#> 5 http://creativecommons.org/licenses/by/4.0/
#> 6 http://doi.wiley.com/10.1002/tdm_license_1
#> 7 http://onlinelibrary.wiley.com/termsAndConditions
#> 8 http://www.acm.org/publications/policies/copyright_policy#Background
#> 9 http://www.elsevier.com/open-access/userlicense/1.0/
#> 10 http://www.elsevier.com/tdm/userlicense/1.0/
#> 11 http://www.springer.com/tdm
#> 12 © 2007 Elsevier Masson SAS. All rights reserved. The patient figure in Figu
#> 13 © 2012, Elsevier Inc., All Rights Reserved. Figure 8, part (B) (images of H
#> # ... with 1 more variables: work.count <int>cr_prefixes(prefixes = c('10.1016','10.1371','10.1023','10.4176','10.1093'))
#> $meta
#> NULL
#>
#> $data
#> member name
#> 1 http://id.crossref.org/member/78 Elsevier BV
#> 2 http://id.crossref.org/member/340 Public Library of Science (PLoS)
#> 3 http://id.crossref.org/member/297 Springer Nature
#> 4 http://id.crossref.org/member/1989 Co-Action Publishing
#> 5 http://id.crossref.org/member/286 Oxford University Press (OUP)
#> prefix
#> 1 http://id.crossref.org/prefix/10.1016
#> 2 http://id.crossref.org/prefix/10.1371
#> 3 http://id.crossref.org/prefix/10.1023
#> 4 http://id.crossref.org/prefix/10.4176
#> 5 http://id.crossref.org/prefix/10.1093
#>
#> $facets
#> list()cr_members(query = 'ecology', limit = 5)
#> $meta
#> total_results search_terms start_index items_per_page
#> 1 18 ecology 0 5
#>
#> $data
#> # A tibble: 5 × 48
#> id
#> <int>
#> 1 7052
#> 2 6933
#> 3 7278
#> 4 7745
#> 5 9167
#> # ... with 47 more variables: primary_name <chr>, location <chr>,
#> # last_status_check_time <date>, backfile.dois <chr>,
#> # current.dois <chr>, total.dois <chr>, prefixes <chr>,
#> # coverge.affiliations.current <chr>, coverge.funders.backfile <chr>,
#> # coverge.licenses.backfile <chr>, coverge.funders.current <chr>,
#> # coverge.affiliations.backfile <chr>,
#> # coverge.resource.links.backfile <chr>, coverge.orcids.backfile <chr>,
#> # coverge.update.policies.current <chr>, coverge.orcids.current <chr>,
#> # coverge.references.backfile <chr>,
#> # coverge.award.numbers.backfile <chr>,
#> # coverge.update.policies.backfile <chr>,
#> # coverge.licenses.current <chr>, coverge.award.numbers.current <chr>,
#> # coverge.abstracts.backfile <chr>,
#> # coverge.resource.links.current <chr>, coverge.abstracts.current <chr>,
#> # coverge.references.current <chr>,
#> # flags.deposits.abstracts.current <chr>,
#> # flags.deposits.orcids.current <chr>, flags.deposits <chr>,
#> # flags.deposits.affiliations.backfile <chr>,
#> # flags.deposits.update.policies.backfile <chr>,
#> # flags.deposits.award.numbers.current <chr>,
#> # flags.deposits.resource.links.current <chr>,
#> # flags.deposits.articles <chr>,
#> # flags.deposits.affiliations.current <chr>,
#> # flags.deposits.funders.current <chr>,
#> # flags.deposits.references.backfile <chr>,
#> # flags.deposits.abstracts.backfile <chr>,
#> # flags.deposits.licenses.backfile <chr>,
#> # flags.deposits.award.numbers.backfile <chr>,
#> # flags.deposits.references.current <chr>,
#> # flags.deposits.resource.links.backfile <chr>,
#> # flags.deposits.orcids.backfile <chr>,
#> # flags.deposits.funders.backfile <chr>,
#> # flags.deposits.update.policies.current <chr>,
#> # flags.deposits.licenses.current <chr>, names <chr>, tokens <chr>
#>
#> $facets
#> NULLcr_r() uses the function cr_works() internally.
cr_r()
#> [1] "10.1039/ct8885300641"
#> [2] "10.1063/1.1709474"
#> [3] "10.1111/j.1708-8305.1996.tb00750.x"
#> [4] "10.1037//1076-898x.2.3.270"
#> [5] "10.4337/9781783471171.00028"
#> [6] "10.1007/978-1-349-07777-9_4"
#> [7] "10.1111/b.9781405116749.2003.00054.x"
#> [8] "10.1016/j.crvi.2004.09.010"
#> [9] "10.1002/uog.15794"
#> [10] "10.14731/kjis.2013.12.11.2.295"You can pass in the number of DOIs you want back (default is 10)
cr_r(2)
#> [1] "10.1038/scibx.2008.713" "10.1007/978-3-642-41714-6_91906"DOIs to PMIDs
UPDATE: as of 2014-12-23 the web API behind these functions is down - we'll update the package once the API is up again
Publishers can optionally provide links in the metadata they provide to Crossref for full text of the work, but that data is often missing. Find out more about it at http://tdmsupport.crossref.org/.
Get some DOIs for articles that provide full text, and that have CC-BY 3.0 licenses (i.e., more likely to actually be open)
out <-
cr_works(filter = list(has_full_text = TRUE,
license_url = "http://creativecommons.org/licenses/by/3.0/"))
(dois <- out$data$DOI)
#> [1] "10.1063/1.4905711" "10.1063/1.4908245" "10.1063/1.4908158"
#> [4] "10.1063/1.4908244" "10.1063/1.4913247" "10.1063/1.4914847"
#> [7] "10.1063/1.4916217" "10.1063/1.4916677" "10.1063/1.4916696"
#> [10] "10.1063/1.4917283" "10.1063/1.4918284" "10.1063/1.4919707"
#> [13] "10.1063/1.4921711" "10.1063/1.4921771" "10.1063/1.4922319"
#> [16] "10.1063/1.4922934" "10.1063/1.4922006" "10.1063/1.4926610"
#> [19] "10.1063/1.4926838" "10.1063/1.4926914"Then get URLs to full text content
(links <- cr_ft_links(dois[1]))
#> NULLThen use those URLs to get full text
cr_ft_text(links, "xml")
#> <?xml version="1.0"?>
#> <article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="http://jats.nlm.nih.gov/publishing/1.1d1/xsd/JATS-journalpublishing1-mathml3.xsd" dtd-version="1.1d1">
#> <front>
#> <journal-meta>
#> <journal-id journal-id-type="publisher-id">SV</journal-id>
#> <journal-title-group>
#> <journal-title>Shock and Vibration</journal-title>
#> </journal-title-group>
#> <issn pub-type="epub">1875-9203</issn>
#> <issn pub-type="ppub">1070-9622</issn>
#> <publisher>
#> <publisher-name>Hindawi Publishing Corporation</publisher-name>
#> </publisher>
#> </journal-meta>
#> .................... cutoff- Please report any issues or bugs.
- License: MIT
- Get citation information for
rcrossrefin R doingcitation(package = 'rcrossref') - Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
This package is part of a richer suite called fulltext, along with several other packages, that provides the ability to search for and retrieve full text of open access scholarly articles.
