library(tidyverse)
library(lubridate)
library(httr2)
#' Extract the title, description and views from an article
#'
#' Note that this function is generic enough to work with any named list that contains
#' a title, description and views. However, it is designed to work with the output of
#' the Wikimedia API, which is why the parameter is called `article`.
#'
#' @param article A list containing, amongst other things, the title, description and views of an article
#'
#' @return A tibble with three columns: title, description and views
#'
#' @examples
#' extract_article_info(list(title="Hello", description="World", views=1000))
#'
extract_article_info <- function(article){
tibble(title=article$title,
description=article$description,
views=article$views)
}
#' Get the most read articles from the English Wikipedia on a given day
#'
#' @param ymd_date A lubridate date object
#' @param access_token The access token to use to authenticate with the Wikimedia API.
#' To obtain an access token from Wikimedia, see the instructions
#' on https://api.wikimedia.org/wiki/Getting_started_with_Wikimedia_APIs
#'
#' @return A tibble with four columns: title, description, views and date
#'
#' @examples
#' get_most_read_en_articles(ymd("2023-07-16"), access_token)
#'
get_most_read_en_articles <- function(ymd_date, access_token){
# To get the most read articles of a given day, we need the URL to point to the following day
# It's awkward, but we can't control it, that's how the API works
url_date <- ymd_date + lubridate::days(1)
url <-
sprintf("https://api.wikimedia.org/feed/v1/wikipedia/en/featured/%04d/%02d/%02d",
year(url_date),
month(url_date),
day(url_date))
response <-
request(url) %>%
req_auth_bearer_token(access_token) %>%
req_perform()
json_response <- response %>% resp_body_json()
most_read <- json_response[['mostread']][['articles']]
# We use lapply to apply the extract_article_info function to each article
# This returns a list of tibbles
# We then use bind_rows to combine all the tibbles into one single tibble
df <- lapply(most_read, extract_article_info) %>% bind_rows()
# It's more efficient to add the date column after the lapply loop
df$date <- ymd_date
df
}
#### MAIN SCRIPT ####
access_token <- readr::read_file("my_secret_access_token.txt")
df_most_read <- get_most_read_en_articles(ymd("2023-07-16"), access_token)
