Assignment_3

Question 5

library(robotstxt)
url <- "https://en.wikipedia.org/wiki/2026_in_film"
paths_allowed(url)

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

##  en.wikipedia.org

## [1] TRUE

Question 6

library(rvest)

url <- "https://en.wikipedia.org/wiki/2026_in_film"

table_data <- read_html(url) |>
  html_element("table.wikitable") |>
  html_table()

Question 8

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(purrr)

years <- 2020:2025

hg_films <- map_df(years, function(y) {

  url <- paste0("https://en.wikipedia.org/wiki/", y, "_in_film")

  read_html(url) |>
    html_element("table.wikitable") |>
    html_table() |>
    mutate(year = y)

})

hg_films

## # A tibble: 60 × 5
##     Rank Title                               Distributor `Worldwide gross`  year
##    <int> <chr>                               <chr>       <chr>             <int>
##  1     1 Demon Slayer: Kimetsu no Yaiba Mug… Toho / Ani… $507,127,293[4]    2020
##  2     2 The Eight Hundred                   CMC Pictur… $461,421,559       2020
##  3     3 My People, My Homeland              China Lion  $433,241,288[5]    2020
##  4     4 Bad Boys for Life                   Sony        $426,505,244       2020
##  5     5 Tenet                               Warner Bro… $365,309,519       2020
##  6     6 Sonic the Hedgehog                  Paramount   $319,715,683       2020
##  7     7 Dolittle                            Universal   $251,410,631       2020
##  8     8 Jiang Ziya                          Beijing En… $243,883,429       2020
##  9     9 A Little Red Flower                 HG Enterta… $238,600,000[6][…  2020
## 10    10 Shock Wave 2                        Universe F… $226,400,000       2020
## # ℹ 50 more rows