Assignment 7

Load the three files using Github links to the file

#Loading Json
json_df <- fromJSON("https://raw.githubusercontent.com/Raharijao/Spring2024_Data_607_CUNYSPS/main/Week7/books_coldWar.json")

html_data <- read_html("https://raw.githubusercontent.com/Raharijao/Spring2024_Data_607_CUNYSPS/main/Week7/books_coldWar.html")
table_node <- html_data %>% html_node("table")
html_df <- table_node %>% html_table(fill = TRUE)

#Loading XML
x <- getURL("https://raw.githubusercontent.com/Raharijao/Spring2024_Data_607_CUNYSPS/main/Week7/books_coldWar.xml")
xml_data <- xmlParse(x)

# Extract book nodes
books <- getNodeSet(xml_data, "//book")

# Function to extract data from each book node
extract_book_info <- function(book) {
  # Extract title
  title <- xmlValue(book[["title"]])
  
  # Extract authors
  authors_nodes <- getNodeSet(book, "authors/author")
  authors <- sapply(authors_nodes, xmlValue)
  
  # Extract interesting attributes
  attributes_nodes <- getNodeSet(book, "interesting_attributes/attribute")
  interesting_attributes <- sapply(attributes_nodes, xmlValue)
  
  # Return as a list
  data.frame(
    Title = title,
    Authors = paste(authors, collapse = ", "),
    Interesting_Attributes = paste(interesting_attributes, collapse = "; ")
  )
}

# Apply the function to each book node and create a dataframe
xml_df <- do.call(rbind, lapply(books, extract_book_info))