scrapeST.R

library(rvest)
st_tab <- read_html("https://en.wikipedia.org/wiki/List_of_Star_Trek_characters") %>%
  html_nodes(".wikitable td , .wikitable th") %>%
  html_text()

library(stringr)
titles <- st_tab %>%
  str_detect(regex("^\\n.*\\n$", perl = TRUE))

st_tab[titles]

which(titles)

st_tab_ds9 <- st_tab[seq(which(titles)[4]+1, to = which(titles)[5]-1)]


character_matrix <- matrix(st_tab_ds9, ncol = 7, byrow = TRUE)

library(dplyr)
ds9_char_df <- data.frame(character_matrix[-1,]) %>%
  setNames(character_matrix[1,]) %>%
  dplyr::tbl_df()

ds9_char_df %>% glimpse

library("gender")
library(tidyr)

ds9_char_df %>%
  select(Actor) %>%
  mutate(FirstName = str_match(Actor, "[A-Za-z]+"))

gender("Nana",years = c(1970,2011))


ds9_char_df %>% select(Actor) %>% .[[1]]