Scraping NFL data with purrr and tidyr goodness

scrape_nfl.R

# Replicating https://t.co/Jq1QfFGpjA

library(rvest)
library(stringr)
library(dplyr)
library(tidyr)
library(purrr)
library(lubridate)

get_and_clean_table <- function(url) {
  paste0("http://www.pro-football-reference.com", url) %>%
  read_html() %>%
  html_nodes("table#game_logs") %>%
  html_table() %>%
  first() %>%
  set_names(tolower(names(.))) %>%
  filter(year != "Year") %>%
  mutate(game = str_replace(game, "\\*", "")) %>%
  separate(game, c("away", "home"), sep = " @ ") %>%
  mutate_each(funs(as.integer), vpts:hpyds) %>%
  mutate(year = ymd(year))
}

## IO
officials <- read_html("http://www.pro-football-reference.com/officials/") %>%
  html_nodes("table a") %>%
  {data_frame(name = html_text(.), url = html_attr(., "href"))} %>%
  mutate(data = url %>% map(get_and_clean_table)) %>%
  unnest()

write_csv(officials, "officials_data.csv")