Assignment 3

Install Packages

library(rvest)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(readr)

## Warning: package 'readr' was built under R version 4.4.3

## 
## Attaching package: 'readr'

## The following object is masked from 'package:rvest':
## 
##     guess_encoding

Uploading Website

url <- "https://en.wikipedia.org/wiki/2024_in_film"
ua  <- "GriffinSchoolProjectBot/1.0 (+contact@example.com)"

Fetching the Page

pg <- read_html(httr::GET(url, httr::add_headers(`User-Agent` = ua)))

Recieving Table

tables <- pg |>
  html_elements("table.wikitable") |>
  html_table(fill = TRUE)

Inspecting Length of Table

length(tables)

## [1] 5

Finding Highest Grossing Film

pick_highest_grossing <- function(tbls) {
  idx <- which(vapply(tbls, function(t) any(grepl("Worldwide", names(t), ignore.case = TRUE)), logical(1)))
  if (length(idx)) tbls[[idx[1]]] else NULL
}
highest_grossing <- pick_highest_grossing(tables)
if (!is.null(highest_grossing)) head(highest_grossing)

## # A tibble: 6 × 4
##    Rank Title                 Distributor `Worldwide gross`
##   <int> <chr>                 <chr>       <chr>            
## 1     1 Inside Out 2          Disney      $1,698,863,816   
## 2     2 Deadpool & Wolverine  Disney      $1,338,073,645   
## 3     3 Moana 2               Disney      $1,059,242,164   
## 4     4 Despicable Me 4       Universal   $971,315,095     
## 5     5 Wicked                Universal   $756,535,681     
## 6     6 Mufasa: The Lion King Disney      $723,060,982