Assignment 7

Loading Packages

library(XML)
library(jsonlite)
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

library(RCurl)

## Loading required package: bitops

Reading HTML

(HTML.Dataframe  <- readLines("https://raw.githubusercontent.com/Fyoun123/Data607/master/week%207/books.html") %>%  htmlParse() %>% readHTMLTable(which = 1))

##                    Book                               Author
## 1            Steve Jobs                      Walter Isaacson
## 2 Our Oreintal Heritage                          Will Durant
## 3      The Grand Design Stephen Hawking and Leonard Mlodinow
##             Genre
## 1       Biography
## 2         History
## 3 Popular science

Reading JSON

(JSON.Dataframe <- fromJSON("https://raw.githubusercontent.com/Fyoun123/Data607/master/week%207/books.json"))

##                       A                                    B
## 1                  Book                               Author
## 2            Steve Jobs                      Walter Isaacson
## 3 Our Oreintal Heritage                          Will Durant
## 4      The Grand Design Stephen Hawking and Leonard Mlodinow
##                 C
## 1           Genre
## 2       Biography
## 3         History
## 4 Popular science

Reading XML

xml_url<-getURL("https://raw.githubusercontent.com/Fyoun123/Data607/master/week%207/Books2.xml")
(XML.Dataframe<-xmlToDataFrame(xml_url, stringsAsFactors = FALSE))

##                   Books                               Author
## 1            Steve Jobs                      Walter Isaacson
## 2 Our Oreintal Heritage                          Will Durant
## 3      The Grand Design Stephen Hawking and Leonard Mlodinow
##             Genre
## 1       Biography
## 2         History
## 3 Popular science

XML and HTML are smilar where as JSON is different.