Assignment 3

Question 5, true or false

library(robotstxt)

paths_allowed("https://en.wikipedia.org/wiki/2026_in_film")

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

##  en.wikipedia.org

## [1] TRUE

Question 6

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(purrr)

url <- "https://en.wikipedia.org/wiki/2026_in_film"
webpage <- read_html(url)

# Extract the first table with the "Highest-grossing films" (usually the first table)
highest_grossing_table <- webpage %>%
  html_node("table.wikitable") %>%  # selects the first table with class 'wikitable'
  html_table(fill = TRUE)