Getting full text

Structure of the returned object from ft_get()

Simple call, pass in a DOI and say where you want to get data from (by default, it’s plos)

res <- ft_get('10.1371/journal.pone.0086169', from = 'plos')

The article text and metadata is stored in the output object.

The res object is a list, with slots for each of the data sources, b/c you can request data from more than 1 data source.

names(res)
#> [1] "plos"          "entrez"        "elife"         "pensoft"      
#> [5] "arxiv"         "biorxiv"       "elsevier"      "sciencedirect"
#> [9] "wiley"

Let’s dig into the plos source object, which is another list, including metadata the text data itself (in the data slot).

res$plos
#> $found
#> [1] 1
#> 
#> $dois
#> [1] "10.1371/journal.pone.0086169"
#> 
#> $data
#> $data$backend
#> [1] "ext"
#> 
#> $data$cache_path
#> [1] "/Users/sckott/Library/Caches/R/fulltext"
#> 
#> $data$path
#> $data$path$`10.1371/journal.pone.0086169`
#> $data$path$`10.1371/journal.pone.0086169`$path
#> [1] "/Users/sckott/Library/Caches/R/fulltext/10_1371_journal_pone_0086169.xml"
#> 
#> $data$path$`10.1371/journal.pone.0086169`$id
#> [1] "10.1371/journal.pone.0086169"
#> 
#> $data$path$`10.1371/journal.pone.0086169`$type
#> [1] "xml"
#> 
#> $data$path$`10.1371/journal.pone.0086169`$error
#> NULL
#> 
#> 
#> 
#> $data$data
#> NULL
#> 
#> 
#> $opts
#> $opts$doi
#> [1] "10.1371/journal.pone.0086169"
#> 
#> $opts$type
#> [1] "xml"
#> 
#> $opts$progress
#> [1] FALSE
#> 
#> 
#> $errors
#>                             id error
#> 1 10.1371/journal.pone.0086169  <NA>

Indexing to the data slot takes us to another list with metadata and the article

res$plos$data
#> $backend
#> [1] "ext"
#> 
#> $cache_path
#> [1] "/Users/sckott/Library/Caches/R/fulltext"
#> 
#> $path
#> $path$`10.1371/journal.pone.0086169`
#> $path$`10.1371/journal.pone.0086169`$path
#> [1] "/Users/sckott/Library/Caches/R/fulltext/10_1371_journal_pone_0086169.xml"
#> 
#> $path$`10.1371/journal.pone.0086169`$id
#> [1] "10.1371/journal.pone.0086169"
#> 
#> $path$`10.1371/journal.pone.0086169`$type
#> [1] "xml"
#> 
#> $path$`10.1371/journal.pone.0086169`$error
#> NULL
#> 
#> 
#> 
#> $data
#> NULL

Going down one more index gets us the data object. There is no actual text as we have to collect it from the file on disk. See ft_collect() to get the text.

res$plos$data
#> $backend
#> [1] "ext"
#> 
#> $cache_path
#> [1] "/Users/sckott/Library/Caches/R/fulltext"
#> 
#> $path
#> $path$`10.1371/journal.pone.0086169`
#> $path$`10.1371/journal.pone.0086169`$path
#> [1] "/Users/sckott/Library/Caches/R/fulltext/10_1371_journal_pone_0086169.xml"
#> 
#> $path$`10.1371/journal.pone.0086169`$id
#> [1] "10.1371/journal.pone.0086169"
#> 
#> $path$`10.1371/journal.pone.0086169`$type
#> [1] "xml"
#> 
#> $path$`10.1371/journal.pone.0086169`$error
#> NULL
#> 
#> 
#> 
#> $data
#> NULL

Fetching many articles

You can get a bunch of DOIs first, e.g., from PLOS using the rplos package

library("rplos")
(dois <- searchplos(q = "*:*", fl = 'id',
   fq = list('doc_type:full', "article_type:\"research article\""), limit = 5)$data$id)
#> [1] "10.1371/journal.pone.0020843" "10.1371/journal.pone.0022257"
#> [3] "10.1371/journal.pone.0023139" "10.1371/journal.pone.0023138"
#> [5] "10.1371/journal.pone.0023119"
ft_get(dois, from = 'plos')
#> <fulltext text>
#> [Docs] 5 
#> [Source] ext - /Users/sckott/Library/Caches/R/fulltext 
#> [IDs] 10.1371/journal.pone.0020843 10.1371/journal.pone.0022257
#>      10.1371/journal.pone.0023139 10.1371/journal.pone.0023138
#>      10.1371/journal.pone.0023119 ...

Different data sources

Articles from eLife

One article

ft_get('10.7554/eLife.04300', from = 'elife')
#> <fulltext text>
#> [Docs] 1 
#> [Source] ext - /Users/sckott/Library/Caches/R/fulltext 
#> [IDs] 10.7554/eLife.04300 ...

Many articles

ft_get(c('10.7554/eLife.04300','10.7554/eLife.03032'), from = 'elife')
#> <fulltext text>
#> [Docs] 2 
#> [Source] ext - /Users/sckott/Library/Caches/R/fulltext 
#> [IDs] 10.7554/eLife.04300 10.7554/eLife.03032 ...

Articles from Frontiers in Pharmacology (publisher: Frontiers)

doi <- '10.3389/fphar.2014.00109'
ft_get(doi, from = "entrez")
#> <fulltext text>
#> [Docs] 1 
#> [Source] ext - /Users/sckott/Library/Caches/R/fulltext 
#> [IDs] 4050532 ...

Search using ft_search()

For example, search entrez, get some DOIs, then fetch some articles

(res <- ft_search(query = 'ecology', from = 'entrez'))
#> Query:
#>   [ecology] 
#> Found:
#>   [PLoS: 0; BMC: 0; Crossref: 0; Entrez: 203062; arxiv: 0; biorxiv: 0; Europe PMC: 0; Scopus: 0; Microsoft: 0] 
#> Returned:
#>   [PLoS: 0; BMC: 0; Crossref: 0; Entrez: 10; arxiv: 0; biorxiv: 0; Europe PMC: 0; Scopus: 0; Microsoft: 0]
res$entrez$data$doi
#>  [1] "10.1111/tesg.12439"               "10.1002/tie.22161"               
#>  [3] "10.1182/bloodadvances.2019001144" "10.1186/s13063-020-04513-w"      
#>  [5] "10.1007/s10109-020-00330-6"       "10.3390/ma13112563"              
#>  [7] "10.3390/molecules25112618"        "10.3390/molecules25112634"       
#>  [9] "10.3390/molecules25112471"        "10.1186/s40168-020-00861-6"

Get articles

ft_get(res$entrez$data$doi[1:3], from = 'entrez')
#> <fulltext text>
#> [Docs] 3 
#> [Source] ext - /Users/sckott/Library/Caches/R/fulltext 
#> [IDs] 7323205 7323122 7322952 ...

Collect full text from file on disk

When using ft_get() you write the files to disk, and you have to pull text out of them as a separate step.

(res <- ft_get('10.1371/journal.pone.0086169', from = 'plos'))
#> <fulltext text>
#> [Docs] 1 
#> [Source] ext - /Users/sckott/Library/Caches/R/fulltext 
#> [IDs] 10.1371/journal.pone.0086169 ...

One way to do that is with ft_collect(). Before running ft_collect() the data slot is NULL.

res$plos$data$data
#> NULL

Run ft_collect()

res <- res %>% ft_collect

After running ft_collect() the data slot has the text. If there’s more than one article they are named by the identifier

res$plos$data$data
#> $`10.1371/journal.pone.0086169`
#> {xml_document}
#> <article article-type="research-article" dtd-version="3.0" lang="en" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">
#> [1] <front>\n  <journal-meta>\n    <journal-id journal-id-type="nlm-ta">PLoS  ...
#> [2] <body>\n  <sec id="s1">\n    <title>Introduction</title>\n    <p>Since th ...
#> [3] <back>\n  <ack>\n    <p>We thank Joan Silk, Julienne Rutherford, and two  ...