apple-jobs-scrape.R

library(tidyverse)
library(rvest)

# compile list of job listings urls
listing_urls = c()
for (i in 1:20) {
  base_url = paste('https://jobs.apple.com/en-us/search?location=united-states-USA&page=', i , sep = '')
  print(base_url)
  
  page = read_html(base_url)
  listings = page %>% html_nodes('.table-col-1')
  
  for (j in 1:length(listings)) {
    listing_url = listings[j] %>% html_node('a') %>% html_attr('href')
    print(listing_url)
    listing_urls = c(listing_urls, listing_url)
  }
}
listing_urls = paste('https://jobs.apple.com', listing_urls, sep = '')
length(listing_urls) = length(unique(listing_urls))

# scrape job details (title, location, team) from listing urls
datalist = list()
for (i in 1:length(listing_urls)) {
  Sys.sleep(1)
  page = read_html(listing_urls[i])
  print(listing_urls[i])
  
  job_title = page %>% html_node('#jdPostingTitle') %>% html_text()
  job_location = page %>% html_node('#job-location-name') %>% html_text()
  job_team = page %>% html_node('#job-team-name') %>% html_text()
  cat(paste(job_title, job_location, job_team, sep = '\n'))
  datalist[[i]] = tibble(job_title = job_title, job_location = job_location, 
                         job_team = job_team, job_url = listing_urls[i])
}
raw = do.call(rbind, datalist)

# clean, summarize
aapl_jobs = raw %>%
  mutate(scrape_date = Sys.Date())

aapl_jobs %>% group_by(job_location) %>% count(sort = T) # top locations
aapl_jobs %>% group_by(job_team) %>% count(sort = T) # top teams