607 Week 7 Assignment

library(XML)

## Warning: package 'XML' was built under R version 3.5.2

library(RCurl)

## Warning: package 'RCurl' was built under R version 3.5.2

## Loading required package: bitops

library(jsonlite)

Parsing HTML

books_html_url <- 
  getURL("https://raw.githubusercontent.com/Chris-Ayre/DATA607-ASSIGN7/master/books.html")

books_html <- readHTMLTable(books_html_url, header = TRUE)
books_html

## $`NULL`
##         ISBN        TITLE           Author 1        Author 2
## 1 0062748203    Barracoon Zora Neale Hurston                
## 2 1501135945 Indianapolis       Lynn Vincent     Sara Vladic
## 3 1101871849    Our Towns      James Fallows Deborah Fallows
##          PUBLISHER
## 1          Amistad
## 2 Simon & Schuster
## 3          Amistad

Parsing XML

books_xml_url <- 
  getURL("https://raw.githubusercontent.com/Chris-Ayre/DATA607-ASSIGN7/master/books.xml")

books_xml1 <- xmlParse(books_xml_url, ignoreBlanks=TRUE)
books_xml <- xmlToDataFrame(books_xml1)
books_xml

##          title             author      publisher       ISBN
## 1    Barracoon Zora Neale Hurston        Amistad 0062748203
## 2 Indianopolis       Lynn Vincent Simon Schuster 1501135945
## 3    Our Towns      James Fallows        Amistad 1101871849
##           author2
## 1            <NA>
## 2     Sara Vladic
## 3 Deborah Fallows

Parsing JSON

books_json_URL <- 
  getURL("https://raw.githubusercontent.com/Chris-Ayre/DATA607-ASSIGN7/master/books.json")
books_json <- fromJSON(books_json_URL)
books_json

## $books
##         ISBN        Title                         Author        Publisher
## 1 0062748203    Barracoon             Zora Neale Hurston          Amistad
## 2 1501135945 Indianopolis      Lynn Vincent, Sara Vladic Simon & Schuster
## 3 1101871849    Our Towns James Fallows, Deborah Fallows          Amistad

THE DATA FRAMES ARE NOT IDENTICAL - EACH PROTOCOL HAS DIFFERENT DEFAULTS THAT ORDER THE COLUMNS DIFFERENTLY