R function: email address ➜ institution name, quick and dirty (just the 1st hit in Bing)

emailAddressToInstitutionName.R

# Usage example (disclaimer: fictitious email addresses, any resemblance to real ones is coincidental):
## emailAddressToInstitutionName(c('[email protected]',
##                                 '[email protected]'))
##> "Ministère du Travail, du Plein emploi et de l'Insertion"
##> "Ministerie van Sociale Zaken en Werkgelegenheid | Rijksoverheid.nl"
# Required packages: `magrittr`, `rvest`

library(magrittr) # for the %>% operator

emailAddressToInstitutionName <- function(charvec_of_email_addresses,
                                          wait_time_before_retry=3) { # in seconds
    stopifnot(is.character(charvec_of_email_addresses),
              length(charvec_of_email_addresses)>0,
              all(grepl('^\\S+@\\S+$',charvec_of_email_addresses)),
              is.numeric(wait_time_before_retry),
              length(wait_time_before_retry)==1,
              wait_time_before_retry>0)
    query <- function(x)
        x %>% 
        rvest::read_html() %>% 
        rvest::html_nodes('#b_results > li.b_algo.b_vtl_deeplinks > h2 > a') %>% 
        rvest::html_text() %>% 
        ifelse(length(.)!=0, .,
               {Sys.sleep(wait_time_before_retry); query(x)}) # retry
    charvec_of_email_addresses %>% 
        sub('.+@(.+)','\\1',.) %>% # extract domain
        paste0('https://www.bing.com/search?q=',.) %>% 
        sapply(query, USE.NAMES=FALSE)
}