library(jsonlite)## Warning: package 'jsonlite' was built under R version 3.3.3library(xml2)## Warning: package 'xml2' was built under R version 3.3.3library(rvest)## Warning: package 'rvest' was built under R version 3.3.3library(XML)## Warning: package 'XML' was built under R version 3.3.3##
## Attaching package: 'XML'## The following object is masked from 'package:rvest':
##
## xmllibrary(RCurl)## Warning: package 'RCurl' was built under R version 3.3.3## Loading required package: bitopslibrary(tidyverse)## Warning: package 'tidyverse' was built under R version 3.3.3## -- Attaching packages ---------------------------------- tidyverse 1.2.1 --## v ggplot2 3.0.0 v purrr 0.2.4
## v tibble 1.4.2 v dplyr 0.7.4
## v tidyr 0.8.0 v stringr 1.3.1
## v readr 1.1.1 v forcats 0.3.0## Warning: package 'tibble' was built under R version 3.3.3## Warning: package 'tidyr' was built under R version 3.3.3## Warning: package 'readr' was built under R version 3.3.3## Warning: package 'purrr' was built under R version 3.3.3## Warning: package 'dplyr' was built under R version 3.3.3## Warning: package 'forcats' was built under R version 3.3.3## -- Conflicts ------------------------------------- tidyverse_conflicts() --
## x tidyr::complete() masks RCurl::complete()
## x dplyr::filter() masks stats::filter()
## x purrr::flatten() masks jsonlite::flatten()
## x readr::guess_encoding() masks rvest::guess_encoding()
## x dplyr::lag() masks stats::lag()
## x purrr::pluck() masks rvest::pluck()
## x XML::xml() masks rvest::xml()Read the JSON FILE
json_books <- fromJSON(txt = "https://raw.githubusercontent.com/ghh2001/607Assignment7-/master/booksGH3.json")
class (json_books)## [1] "list"json_books## $books
## Title
## 1 Start with Why: How Great Leaders Inspire Everyone to Take Action
## 2 The Four: The Hidden DNA of Amazon, Apple, Facebook, and Google
## 3 Change or Die The Three Keys to Change at Work and in Life
## 4 Crushing it! How Great Entrepreneurs Build
## 5 Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking
## Authors Type Length
## 1 Simon Sinek Audible Audiobook 288
## 2 Scott Galloway Paperpack 320
## 3 Alan Deutschman Paperpack 256
## 4 Gary Vaynerchuk Audible Audiobook 420
## 5 Foster Provost, Karen Dillon, Tom Fawcett Paperpack 414
## AmazonRating
## 1 4.5
## 2 4.5
## 3 4.5
## 4 4.5
## 5 4.5# the list of author did not work (currently a list, Chr1, chr2 etc), otherwise all workedAlternative method of reading the Json File, using getURL function
raw_JSON = getURL("https://raw.githubusercontent.com/ghh2001/607Assignment7-/master/booksGH3.json", ssl.verifypeer = FALSE)
booksGH_JSON = fromJSON(txt = raw_JSON)
str(booksGH_JSON)## List of 1
## $ books:'data.frame': 5 obs. of 5 variables:
## ..$ Title : chr [1:5] "Start with Why: How Great Leaders Inspire Everyone to Take Action" "The Four: The Hidden DNA of Amazon, Apple, Facebook, and Google" "Change or Die The Three Keys to Change at Work and in Life" "Crushing it! How Great Entrepreneurs Build" ...
## ..$ Authors :List of 5
## .. ..$ : chr "Simon Sinek"
## .. ..$ : chr "Scott Galloway"
## .. ..$ : chr "Alan Deutschman"
## .. ..$ : chr "Gary Vaynerchuk"
## .. ..$ : chr [1:3] "Foster Provost" "Karen Dillon" "Tom Fawcett"
## ..$ Type : chr [1:5] "Audible Audiobook" "Paperpack" "Paperpack" "Audible Audiobook" ...
## ..$ Length : chr [1:5] "288" "320" "256" "420" ...
## ..$ AmazonRating: chr [1:5] "4.5" "4.5" "4.5" "4.5" ...class (booksGH_JSON)## [1] "list"Create a dataframe from the Json Files just read
booksGH_JSON_df = as.data.frame(booksGH_JSON)
class (booksGH_JSON_df)## [1] "data.frame"#kable (booksGH_JSON_df)
# but, the aurthors showd as C ("author1, author2") format,try the 3rd way below to read JSON file
json.url <- "https://raw.githubusercontent.com/ghh2001/607Assignment7-/master/booksGH3.json"
json.file <- getURLContent(json.url)
json.df <- as.data.frame(fromJSON(json.file[[1]]))
colnames(json.df) <- str_replace(colnames(json.df),"books\\.", "")
colnames(json.df) <- str_replace(colnames(json.df),"\\.", " ")
dim(json.df)## [1] 5 5#kable(json.df)
# it works, but it appears 3 times, which does not make senseRead in Xml File
data2 <- getURL("https://raw.githubusercontent.com/ghh2001/607Assignment7-/master/booksGH3.xml")
xbooks <- xmlParse(data2)
class (xbooks)## [1] "XMLInternalDocument" "XMLAbstractDocument"root <- xmlRoot(xbooks)
class (root)## [1] "XMLInternalElementNode" "XMLInternalNode"
## [3] "XMLAbstractNode"books_xml <- xmlToDataFrame(root)
class (books_xml)## [1] "data.frame"books_xml## Title
## 1 Start with Why: How Great Leaders Inspire Everyone to Take Action
## 2 The Four: The Hidden DNA of Amazon, Apple, Facebook, and Google
## 3 Change or Die The Three Keys to Change at Work and in Life
## 4 Crushing it! How Great Entrepreneurs Build
## 5 Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking
## Author Type Length
## 1 Simon Sinek Audible Audiobook 288
## 2 Scott Galloway Kindle 320
## 3 Alan Deutschman Paperpack 256
## 4 Gary Vaynerchuk Audible Audiobook 420
## 5 Foster Provost; Karen Dillon; Tom Fawcett Paperpack 414
## AmazonRating
## 1 4.5
## 2 4.5
## 3 4.5
## 4 4.5
## 5 4.5Read in HtML file
books_html <- "https://raw.githubusercontent.com/ghh2001/TestAug28GH/master/booksGH3.html" %>%
read_html () %>%
html_nodes("table") %>%
html_table(fill = T)
books_html <- as.data.frame(books_html)
books_html## Title
## 1 Start with Why: How Great Leaders Inspire Everyone to Take Action
## 2 The Four: The Hidden DNA of Amazon, Apple, Facebook, and Google
## 3 Change or Die: The Three Keys to Change at Work and in Life
## 4 Crushing it! How Great Entrepreneurs Build
## 5 Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking
## 6 <NA>
## Authors Type Length
## 1 SImon Sinek Audible Audiobook 288
## 2 Scott Galloway Kindle 320
## 3 Alan Deutschman Paperpack 256
## 4 Gary Vaynerchuk Audible AUdiobook 420
## 5 Foster Provost; Karen Dillon; Tom Fawcett Paperpack 414
## 6 <NA> <NA> NA
## AmazonRating
## 1 4.5
## 2 4.5
## 3 4.5
## 4 4.5
## 5 4.5
## 6 NA