library(stringr)
library(RCurl)
## Loading required package: bitops
library(RJSONIO)
library(jsonlite)
## 
## Attaching package: 'jsonlite'
## The following objects are masked from 'package:RJSONIO':
## 
##     fromJSON, toJSON
library(XML)
library(knitr)
## Warning: package 'knitr' was built under R version 3.3.3
#library(RTidyHTML)

Parse HTML from Web and convert to Data Frame

booksContent <- getURL("https://raw.githubusercontent.com/jmehta753/MSDA_JM/master/DATA607/Week7/books.html")
books <- htmlParse(booksContent, useInternalNodes = TRUE)
child <- xmlChildren(xmlRoot(books))
child <- xmlChildren(child$body)
table <- xmlChildren(child$table)
HTMLDF <- readHTMLTable(child$table)
kable(HTMLDF)
V1 V2 V3 V4 V5 V6
Id Title Authors Year Genres Movie Adaptation
1 The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography Simon Singh 2000 Cryptography, Linguistics, History Â
2 Alan Turing: The Enigma Andrew Hodges, Douglas Hofstadter 1985 History, Mathematics, Technology The Imitation Game
3 Hidden Figures: The Story of the African-American Women Who Helped Win the Space Race Margot Lee Shetterly 2016 History, African-American, Technology Hidden Figures

Parse JSON from Web and convert to Data Frame

booksJson <- getURL("https://raw.githubusercontent.com/jmehta753/MSDA_JM/master/DATA607/Week7/books.json")
booksJsonDF<-fromJSON(booksJson)
kable(booksJsonDF)
Id Title Authors Year Genres Movie-Adaptation
1 The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography Simon Singh 2000 Cryptography, Linguistics, History NA
2 Alan Turing: The Enigma Andrew Hodges, Douglas Hofstadter 1985 History, Mathematics, Technology The Imitation Game
3 Hidden Figures: The Story of the African-American Women Who Helped Win the Space Race Margot Lee Shetterly 2016 History, African-American, Technology Hidden Figures

Parse XML from Web and convert to Data Frame

booksXml <- getURL("https://raw.githubusercontent.com/jmehta753/MSDA_JM/master/DATA607/Week7/books.xml")
booksXml1 <- xmlParse(booksXml)
booksXml1 <- xmlRoot(booksXml1)
booksXMLDF <- xmlSApply(booksXml1, function(x) xmlSApply(x, xmlValue))
booksXMLDF <- data.frame(t(booksXMLDF), row.names = NULL)
kable(booksXMLDF)
Id Title Authors Year Genres Movie.Adaptation
1 The Code Book: The Science of Secrecy from Ancient Egypt to Quantum Cryptography Simon Singh 2000 Cryptography, Linguistics, History
2 Alan Turing: The Enigma Andrew Hodges, Douglas Hofstadter 1985 History, Mathematics, Technology The Imitation Game
3 Hidden Figures: The Story of the African-American Women Who Helped Win the Space Race Margot Lee Shetterly 2016 History, African-American, Technology Hidden Figures