google scholar h-index scrape.R

library(tidyverse)
library(rvest)


google_scholar_urls <- tibble::tribble(
  ~name,                                                      ~url_path,
  "Tim Capon", "https://scholar.google.com/citations?user=mJeSBzAAAAAJ&hl=en",
  "Céline Nauges", "https://scholar.google.com/citations?hl=en&user=ehxgHeQAAAAJ",
  "Stéphane De Cara", "https://scholar.google.com/citations?hl=en&user=OjOkZwEAAAAJ",
  "Israel Finkelshtain", "https://scholar.google.com/citations?hl=en&user=ZBlt4VgAAAAJ",
  "Macario Rodríguez-Entrena", "https://scholar.google.com/citations?hl=en&user=pkagohUAAAAJ",
  "Carmen Almansa Sáez", "https://scholar.google.com/citations?hl=en&user=2L3U3doAAAAJ"
)


###################################################################

# test the process with an individual url

url <- google_scholar_urls %>% slice(1) %>% pull(url_path)

download <- read_html(url) %>% 
  html_nodes(".gsc_rsb_std")

download %>% 
  html_text() %>% 
  matrix(nrow = 3, byrow = TRUE) %>% 
  as_tibble() %>% 
  rename(All = 1, 
         `Since 2015` = 2) %>% 
  add_column(stat_name = c("Citations", "h-index", "i10-index"), .before = 1)

###################################################################

# run the process over all urls, with map

all_download <- google_scholar_urls %>% 
  mutate(stat_table = map(url_path, ~.x %>% 
                            read_html() %>% 
                            html_nodes(".gsc_rsb_std") %>% 
                            html_text() %>% 
                            matrix(nrow = 3, byrow = TRUE) %>% 
                            as_tibble() %>% 
                            rename(All = 1, 
                                   `Since 2015` = 2) %>% 
                            add_column(stat_name = c("Citations", "h-index", "i10-index"), .before = 1))) %>% 
  unnest(stat_table) %>% 
  print()


all_download %>% 
  openxlsx::write.xlsx(paste0("ggle_schlr_scp_", lubridate::today(), ".xlsx"), asTable = T)