scrapenames.md

The scrapenames() function in taxize resolves names using the Global Names Recognition and Discovery web service.

install

install from github to get fixes to the function

devtools::install_github("ropensci/scrapenames")

Load the library

library("taxize")

From a website using its URL

res <- scrapenames(url = 'http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0080498')

detailed metadat on the response

res$meta

## $token_url
## [1] "http://gnrd.globalnames.org/name_finder.json?token=J3YNA1xETsKykQeQOjFmJg"
## 
## $input_url
## [1] "http://www.plosone.org/article/info%3Adoi%2F10.1371%2Fjournal.pone.0080498"
## 
## $file
## [1] ""
## 
## $status
## [1] 200
## 
## $engines
## [1] "TaxonFinder" "NetiNeti"   
## 
## $unique
## [1] FALSE
## 
## $verbatim
## [1] TRUE
## 
## $english
## [1] TRUE
## 
## $execution_time
## $execution_time$find_names_duration
## [1] 5.184621
## 
## $execution_time$total_duration
## [1] 11.38191
## 
## 
## $agent
## $agent$code
## [1] "200"
## 
## $agent$content_type
## [1] "text/html;charset=UTF-8"
## 
## $agent$filename
## [1] "article.html_id=10.1371_journal.pone.0080498"
## 
## 
## $created
## [1] "2015-08-06T00:37:42Z"
## 
## $total
## [1] 362

and the data itself

head(res$data)

##            verbatim    scientificName offsetStart offsetEnd
## 1 Cyatta abscondita Cyatta abscondita          12        28
## 2            Scopus            Scopus        2786      2791
## 3 Cyatta abscondita Cyatta abscondita        3036      3052
## 4          Curitiba          Curitiba        4489      4496
## 5          Paulista          Paulista        4938      4945
## 6 Cyatta abscondita Cyatta abscondita        5440      5456
##      identifiedName
## 1 Cyatta abscondita
## 2            Scopus
## 3 Cyatta abscondita
## 4          Curitiba
## 5          Paulista
## 6 Cyatta abscondita

From a pdf at a URL

url <- 'http://www.plosone.org/article/fetchObject.action?uri=info%3Adoi%2F10.1371%2Fjournal.pone.0058268&representation=PDF'
res2 <- scrapenames(url = url)
head(res2$data)

##               verbatim      scientificName offsetStart offsetEnd
## 1              Xylaria             Xylaria          24        30
## 2 Dendrobium  precious Dendrobium precious          37        56
## 3              Petrini             Petrini        1495      1501
## 4              Petrini             Petrini        1505      1511
## 5           Dendrobium          Dendrobium        2027      2036
## 6         Xylariaceae,         Xylariaceae        2967      2978
##        identifiedName
## 1             Xylaria
## 2 Dendrobium precious
## 3             Petrini
## 4             Petrini
## 5          Dendrobium
## 6         Xylariaceae

From a file

Contents of the file

speciesfile <- system.file("examples", "species.txt", package = "taxize")
readLines(speciesfile)

##  [1] "Achnatherum eminens"      "Achnatherum inebrians"   
##  [3] "Achnatherum lettermanii"  "Achnatherum lobatum"     
##  [5] "Achnatherum nelsonii"     "Achnatherum pinetorum"   
##  [7] "Achnatherum purpurascens" "Achnatherum robustum"    
##  [9] "Achnatherum sibiricum"    "Achnatherum speciosum"

Find names in the file (this is too easy, but you can imagine files with other text mixed in with the names)

res3 <- scrapenames(file = speciesfile)
head(res3$data)

##                  verbatim          scientificName offsetStart offsetEnd
## 1     Achnatherum eminens     Achnatherum eminens           0        18
## 2   Achnatherum inebrians   Achnatherum inebrians          20        40
## 3 Achnatherum lettermanii Achnatherum lettermanii          42        64
## 4     Achnatherum lobatum     Achnatherum lobatum          66        84
## 5    Achnatherum nelsonii    Achnatherum nelsonii          86       105
## 6   Achnatherum pinetorum   Achnatherum pinetorum         107       127
##            identifiedName
## 1     Achnatherum eminens
## 2   Achnatherum inebrians
## 3 Achnatherum lettermanii
## 4     Achnatherum lobatum
## 5    Achnatherum nelsonii
## 6   Achnatherum pinetorum

From a text string

res4 <- scrapenames(text = 'A spider named Pardosa moesta Banks, 1892')
head(res4$data)

##         verbatim scientificName offsetStart offsetEnd identifiedName
## 1 Pardosa moesta Pardosa moesta          15        28 Pardosa moesta