scrape_emails.R

library('rvest')
library('stringr')


fachschaft = 'http://wiki.psyfako.org/index.php?title=Liste_der_Psychologie_Fachschaften'

emails = read_html(fachschaft) %>%
  html_nodes('p, a, span') %>% html_text(.) %>% 
  str_replace('\\[at\\]', '@') %>% str_replace('\\(at\\)', '@') %>%
  str_replace('\\[ät\\]', '@') %>% str_replace('\\[dot\\]', '.') %>% 
  str_subset(., '@') %>% str_trim(.) %>% 
  sapply(., function(text) {
    
    newline = regexpr('\n', text)[1]
    new = str_sub(text, 1, newline - 1)
    len = str_length(new)
    
    if (str_sub(new, len) == 'd') new = paste0(new, 'e')
    if (str_sub(new, len) == 'a') new = paste0(new, 't')
    new
    
  }) %>% str_subset(., '@') %>% unique(.)

write(emails, 'emails_fachschaften.txt')