Created
September 6, 2024 04:25
-
-
Save iangow/17d0177444437e055a22194d716daba7 to your computer and use it in GitHub Desktop.
Code to get player lists from AFL tables
This file contains 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(httr2) # request(), req_*(), resp_body_html() | |
| library(rvest) # html_elements(), html_table() | |
| library(tidyverse) | |
| extract_team_ids <- function(link_text) { | |
| matches <- str_match(link_text, '<a href="teams/(.*)_idx.html">(.*)</a>') | |
| team_id <- matches[, 2] | |
| team_name <- matches[, 3] | |
| tibble(team_id, team_name) | |
| } | |
| all_teams_url <- "https://afltables.com/afl/afl_index.html" | |
| teams <- | |
| map_dfr(team_urls, extract_team_ids) |> | |
| filter(team_id != "allteams") | |
| get_team_list <- function(team_id) { | |
| url <- str_c("https://afltables.com/afl/stats/alltime/", | |
| team_id, ".html") | |
| resp <- | |
| request(url) |> | |
| req_user_agent(getOption("HTTPUserAgent")) |> | |
| req_perform() |> | |
| resp_body_html() |> | |
| html_elements("body") | |
| make_range <- function(start, end) { | |
| start | |
| } | |
| df <- | |
| resp[[1]] |> | |
| html_table() |> | |
| mutate(DOB = as.Date(DOB)) |> | |
| filter(!is.na(DOB)) |> | |
| separate_wider_regex(cols = c(Debut, Last), | |
| patterns = c(years = "^[0-9]+", "y ", days = "[0-9]+", "d$"), | |
| names_sep = "_", | |
| too_few = "align_start") |> | |
| mutate(debut = if_else(is.na(Debut_days), | |
| DOB + years(Debut_years), | |
| DOB + years(Debut_years) + days(Debut_days)), | |
| last = if_else(is.na(Debut_days), | |
| DOB + years(Last_years), | |
| DOB + years(Last_years) + days(Last_days))) |> | |
| arrange(desc(last)) |> | |
| select(-matches("^(Debut|Last)", ignore.case = FALSE)) |> | |
| mutate(team_id = team_id, .before = 1) | |
| df | |
| } | |
| team_lists <- | |
| map(teams$team_id, get_team_list) |> | |
| list_rbind() | |
| seasons <- | |
| team_lists |> | |
| select(team_id, Player, DOB, Seasons) |> | |
| separate_longer_delim(Seasons, ",") |> | |
| mutate(Seasons = str_trim(Seasons)) |> | |
| separate_wider_regex(Seasons, | |
| patterns = c(first_season = "^[0-9]+", "-", last_season = "[0-9]+$"), | |
| too_few = "align_start") |> | |
| mutate(last_season = coalesce(last_season, first_season)) |> | |
| rowwise() |> | |
| mutate(seasons = list(first_season:last_season)) |> | |
| unnest(seasons) |> | |
| select(-first_season, -last_season) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment