genderdata.R

# i used these linses of code to scrap african gendernames from the internet for one of my projects, it may not help you
library(rvest)
library(mbanalytics)
url = "https://www.momjunction.com/baby-names/african/page/%s/"
Allnames = 1:20%>% 
  map_df(~sprintf(url,.) %>% 
           read_html() %>% html_table(fill = T) %>% as.data.frame()  %>% 
           select(NAMES,GENDER) %>%  filter(!grepl("googletag.cmd.",NAMES),GENDER != "Unisex") %>% 
           mutate(GENDER = ifelse(GENDER == "Boy","M","F"),  NAMES = tolower(NAMES))) %>% 
  rename_all(tolower)
url2 = "https://www.behindthename.com/submit/names/usage/eastern-african/%s"
Allnames2 = 1:3 %>% 
  map(~sprintf(url2,.) %>% read_html()) %>% 
  map_df(~tibble(names = html_nodes(., ".listname") %>% html_text() %>% tolower(),
              gender =  html_nodes(., ".listgender") %>% html_text()%>% tolower() )) %>% filter(gender != "f & m")
url3 = 'http://www.firstnamesbaby.com/Baby-Boy-Names-Popular/Kenyan/%s/Boy/'
url4 = 'http://www.firstnamesbaby.com/Names-By-Country/Kenyan/Girl/page%s'
malenames = LETTERS %>% 
  map_df(~ sprintf(url3,.) %>%
        read_html() %>% 
        html_table(fill = T)  %>% enframe() %>% filter(name == 1) %>% unnest(value) %>% 
        separate(X1,into = c("names",'gender'),sep = "[|]") %>% select(names,gender) %>% 
        mutate_all(.funs = trimws) %>% mutate(gender = ifelse(gender == "Boy","M","F")))
femalenames = 1:11 %>% 
  map_df(~sprintf(url4,.) %>% 
           read_html() %>% 
           html_table(fill = T)  %>% enframe() %>% filter(name == 1) %>% unnest(value) %>% 
           separate(X1,into = c("names",'gender'),sep = "[|]") %>% select(names,gender) %>% 
           mutate_all(.funs = trimws) %>% mutate(gender = ifelse(gender == "Boy","M","F")))
Allnames3 = malenames %>% rbind(femalenames) %>% 
  mutate(names = tolower(names))

allnames = rbind(Allnames,Allnames2,Allnames3)
full_list = list(genderdata::ipums_usa,genderdata::napp,genderdata::ssa_national) %>% 
  map(~mutate(.,gender = ifelse(male > female ,"M","F"))) %>% 
  bind_rows(genderdata::ssa_state %>% mutate(.,gender = ifelse(M > `F` ,"M","F")),
            genderdata::kantrowitz,allnames) %>% 
  select(name,gender)