pacman::p_load(robotstxt, rvest)
Question 5
library(robotstxt)
paths_allowed("https://en.wikipedia.org/wiki/2026_in_film")
## Warning: package 'future' was built under R version 4.5.2
## en.wikipedia.org
## [1] TRUE
Question 6
library(rvest)
my_html <- read_html("https://en.wikipedia.org/wiki/2026_in_film")
my_table <- my_html %>% html_element("table") %>% html_table()
my_table
## # A tibble: 3 × 1
## `List of years in film`
## <chr>
## 1 "… 2016\n2017\n2018\n2019\n2020\n2021\n2022\n2023\n2024\n2025\n2026\n2027\n20…
## 2 "Art\nArchaeology\nArchitecture\n\nLiterature\nMusic\nPhilosophy\nScience+..."
## 3 ".mw-parser-output .navbar{display:inline;font-size:88%;font-weight:normal}.m…