Assignment 3 Owen Henderson

library(robotstxt)

is_allowed <- paths_allowed(url)

 www.imdb.com                      

if (is_allowed) {
  print("Scraping is allowed for this page.")
} else {
  print("Scraping is NOT allowed for this page.")
}

[1] "Scraping is allowed for this page."

library(rvest)
url <- "https://www.imdb.com/title/tt7235466/fullcredits?ref_=tt_cl_sm"
webpage <- read_html(url)

tables <- html_nodes(webpage, "table")

series_cast_table <- html_table(tables[3], fill = TRUE)

dim(series_cast_table)

NULL

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

url <- "https://www.imdb.com/title/tt7235466/fullcredits?ref_=tt_cl_sm"

webpage <- read_html(url)

tables <- html_nodes(webpage, "table")

cast_table <- html_table(tables[[3]], fill = TRUE)

clean_cast <- cast_table %>%
  select(2, 4) %>%  
  filter(!is.na(X2) & X2 != "", !is.na(X4) & X4 != "")  

clean_cast <- clean_cast %>% filter(X2 != "" & X4 != "")

Final:

num_rows <- nrow(clean_cast)
num_columns <- ncol(clean_cast)
cat("Final cleaned dataset contains:", num_rows, "observations and", num_columns, "columns.\n")

Final cleaned dataset contains: 1575 observations and 2 columns.

Clean Display:

head(clean_cast)