Created
October 28, 2025 16:18
-
-
Save MichaelChirico/6132deadc98882303efbbdc8dc18fcd3 to your computer and use it in GitHub Desktop.
Get NFL game durations
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| library(rvest) | |
| library(xml2) | |
| PFR_URL = 'https://www.pro-football-reference.com' | |
| read_with_backoff = function(url, sleep = 0.1) { | |
| tryCatch(read_html(url), error = function(.) { | |
| Sys.sleep(sleep) | |
| sleep = 2 * sleep | |
| message(sprintf("Failed, retrying in %.2fs", sleep)) | |
| read_with_backoff(url, sleep = sleep) | |
| }) | |
| } | |
| game_data = data.frame( | |
| summary = character(), | |
| start_time = character(), | |
| duration = character() | |
| ) | |
| for (year in 2024:2025) { | |
| games = file.path(PFR_URL, 'years', year, 'games.htm') |> | |
| read_html() |> | |
| xml_find_all("//a[text() = 'boxscore']") |> | |
| xml_attr("href") | |
| for (game in games) { | |
| boxscore = read_with_backoff(paste0(PFR_URL, game)) | |
| game_data = rbind(game_data, data.frame( | |
| summary = xml_text(xml_find_first(boxscore, "//h1")), | |
| start_time = xml_text(xml_find_first(boxscore, "//strong[text() = 'Start Time']/parent::*")), | |
| duration = xml_text(xml_find_first(boxscore, "//strong[text() = 'Time of Game']/parent::*")) | |
| )) | |
| Sys.sleep(1) | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment