rcrossref (version 0.5.0)

cr_ft_text: Get full text from a DOI

Description

Get full text from a DOI

Usage

cr_ft_text(url, type = "xml", path = "~/.crossref", overwrite = TRUE,
  read = TRUE, verbose = TRUE, cache = TRUE, ...)
cr_ft_plain(url, path = "~/.crossref", overwrite = TRUE, read = TRUE,
  verbose = TRUE, ...)
cr_ft_xml(url, path = "~/.crossref", overwrite = TRUE, read = TRUE,
  verbose = TRUE, ...)
cr_ft_pdf(url, path = "~/.crossref", overwrite = TRUE, read = TRUE,
  cache = FALSE, verbose = TRUE, ...)

Arguments

url

(character) A URL.

type

(character) One of xml, plain, pdf, or all

path

(character) Path to store pdfs in. Default: ~/.crossref/

overwrite

(logical) Overwrite file if it exists already? Default: TRUE

read

(logical) If reading a pdf, this toggles whether we extract text from the pdf or simply download. If TRUE, you get the text from the pdf back. If FALSE, you only get back the metadata. Default: TRUE

verbose

(logical) Print progress messages. Default: TRUE

cache

(logical) Use cached files or not. All files are written to your machine locally, so this doesn't affect that. This only states whether you want to use cached version so that you don't have to download the file again. The steps of extracting and reading i

...

Named parameters passed on to GET

Details

Note that cr_ft_text, cr_ft_pdf, cr_ft_xml, cr_ft_plain are not vectorized.

Note that some links returned will not in fact lead you to full text content as you would understandbly think and expect. That is, if you use the filter parameter with e.g., cr_works and filter to only full text content, some links may actually give back only metadata for an article. Elsevier is perhaps the worst offender, for one because they have a lot of entries in Crossref TDM, but most of the links that are apparently full text are not in facct full text, but only metadata.

Examples

# pdf link
cr_ft_links(doi = "10.5555/515151", "pdf")

# xml and plain text links
out <- cr_works(filter=c(has_full_text = TRUE))
dois <- out$data$DOI
cr_ft_links(dois[2], "xml")
cr_ft_links(dois[1], "plain")
cr_ft_links(dois[1], "all")

# No links
cr_ft_links(cr_r(1), "xml")

# get full text
## pensoft
out <- cr_members(2258, filter=c(has_full_text = TRUE), works = TRUE)
(links <- cr_ft_links(out$data$DOI[1], "all"))
### xml
cr_ft_text(links, 'xml')
### pdf
cr_ft_text(links, "pdf", read=FALSE)
cr_ft_text(links, "pdf")

### another pensoft e.g.
links <- cr_ft_links("10.3897/phytokeys.42.7604", "all")
pdf_read <- cr_ft_text(url = links, type = "pdf", read=FALSE, verbose = FALSE)
pdf <- cr_ft_text(links, "pdf", verbose = FALSE)

## hindawi
out <- cr_members(98, filter=c(has_full_text = TRUE), works = TRUE)
(links <- cr_ft_links(out$data$DOI[1], "all"))
### xml
cr_ft_text(links, 'xml')
### pdf
cr_ft_text(links, "pdf", read=FALSE)
cr_ft_text(links, "pdf")

## search for works with full text, and with CC-BY 3.0 license
### you can see available licenses with cr_licenses() function
out <-
 cr_works(filter = list(has_full_text = TRUE,
   license_url="http://creativecommons.org/licenses/by/3.0/"))
(links <- cr_ft_links(out$data$DOI[10], "all"))
cr_ft_text(links, 'xml')

## You can use cr_ft_xml, cr_ft_plain, and cr_ft_pdf to go directly to that format
licenseurl <- "http://creativecommons.org/licenses/by/3.0/"
out <- cr_works(filter = list(has_full_text = TRUE, license_url = licenseurl))
(links <- cr_ft_links(out$data$DOI[10], "all"))
cr_ft_xml(links)
cr_ft_pdf(links)

# Caching, for PDFs
out <- cr_members(2258, filter=c(has_full_text = TRUE), works = TRUE)
(links <- cr_ft_links(out$data$DOI[10], "all"))
cr_ft_text(links, type = "pdf", cache=FALSE)
system.time( cacheyes <- cr_ft_text(links, type = "pdf", cache=TRUE) )
# second time should be faster
system.time( cacheyes <- cr_ft_text(links, type = "pdf", cache=TRUE) )
system.time( cacheno <- cr_ft_text(links, type = "pdf", cache=FALSE) )
identical(cacheyes, cacheno)

## elsevier
## requires extra authentication
out <- cr_members(78, filter=c(has_full_text = TRUE), works = TRUE)
## set key first
# Sys.setenv(CROSSREF_TDM_ELSEVIER = "your-key")
## XML
link <- cr_ft_links(out$data$DOI[1], "xml")
# res <- cr_ft_text(url = link, type = "xml")
## plain text
link <- cr_ft_links(out$data$DOI[1], "plain")
# res <- cr_ft_text(url = link, "plain")

## Wiley
Sys.setenv(CROSSREF_TDM = "your-key")

### all wiley
out <- cr_members(311, filter=c(has_full_text = TRUE, type = 'journal-article'), works = TRUE)
dois <- out$data$DOI[1:10]
# res <- list()
# for (i in seq_along(dois)) {
#   tmp <- cr_ft_links(dois[i], "all")
#   tmp <- setNames(tmp, "pdf")
#   attr(tmp[[1]], "type") <- "pdf"
#   res[[i]] <- cr_ft_text(tmp, type = "pdf", cache=FALSE)
# }
# res

#### older dates 
out <- cr_members(311, filter=c(has_full_text = TRUE, 
      type = 'journal-article', until_created_date = "2013-12-31"), works = TRUE)
     
dois <- out$data$DOI[1:10]
# res <- list()
# for (i in seq_along(dois)) {
#   tmp <- cr_ft_links(dois[i], "all")
#   tmp <- setNames(tmp, "pdf")
#   attr(tmp[[1]], "type") <- "pdf"
#   res[[i]] <- cr_ft_text(tmp, type = "pdf", cache=FALSE)
# }
# res

### wiley subset with CC By 4.0 license
lic <- "http://creativecommons.org/licenses/by/4.0/"
out <- cr_members(311, filter=c(has_full_text = TRUE, license.url = lic), works = TRUE)
dois <- out$data$DOI[1:10]
# res <- list()
# for (i in seq_along(dois)) {
#   tmp <- cr_ft_links(dois[i], "all")
#   tmp <- setNames(tmp, "pdf")
#   attr(tmp[[1]], "type") <- "pdf"
#   res[[i]] <- cr_ft_text(tmp, type = "pdf", cache=FALSE)
# }