Google Scholar Search

Package

library(tidyverse)
library(rvest)
library(glue)

Function

### Function to get number of result by URL
get_number_by_URL <- function(URL){
  nbres <- read_html(URL) %>%
    html_nodes(".gs_ab_mdw") %>%
    html_text() %>% .[2] %>% 
    str_remove(",") %>% 
    str_extract("\\d+") %>% 
    as.numeric()
  
  return(nbres)
}

### Function to get result for one species
get_res_one_sp <- function(sp_name){
  print(sp_name)
  sp_name2 <- sp_name %>% str_replace_all(pattern = " ", "+")
  
  ### search in titre
  input <- glue("allintitle:+%22{sp_name2}%22")
  URL <- glue("https://scholar.google.com/scholar?as_vis=1&q={input}&hl=en")
  nbres_intitre <- get_number_by_URL(URL)
  
  ### search anywhere in artice
  URL <- glue("https://scholar.google.com/scholar?as_q=&as_epq={sp_name2}&hl=en&as_vis=1")
  nbres_anywhere <- get_number_by_URL(URL)
  
  ### output as df
  dfres <- data.frame(sp_name = sp_name, nb_intitre = nbres_intitre, nb_anywhere = nbres_anywhere)
  
  ##write.csv(dfres,"dfres.csv")
  
  return(dfres)
}

Run

For one species

get_res_one_sp("Cecropia sciadophylla")

## [1] "Cecropia sciadophylla"

##                 sp_name nb_intitre nb_anywhere
## 1 Cecropia sciadophylla         22        1130

For multi species

listsp <- c("Cecropia sciadophylla", "Cecropia obtusa", "Cecropia palmata")

do.call("rbind", lapply(listsp, get_res_one_sp))

## [1] "Cecropia sciadophylla"
## [1] "Cecropia obtusa"
## [1] "Cecropia palmata"

##                 sp_name nb_intitre nb_anywhere
## 1 Cecropia sciadophylla         22        1130
## 2       Cecropia obtusa         13         624
## 3      Cecropia palmata          8         610