Extract only the main textual content from an HTML page

extractMainContent.R

#autoinstall packages
packages <- c("rJava", "boilerpipeR", "httr")
if (length(setdiff(packages, rownames(installed.packages()))) > 0) {
  install.packages(setdiff(packages, rownames(installed.packages())))  
}

# Enjoy learning ? https://dataseolabs.com

# configure your jre
Sys.setenv(JAVA_HOME='C:\\Program Files\\Java\\jre1.8.0_181') # for 64-bit version

# load your libraries
library(rJava)
library(boilerpipeR)
library(httr)

# your url
url <- "https://en.wikipedia.org/wiki/Application_programming_interface"

# use GET method
req <- GET(url)

# extract html
html <- content(req, as = "text", encoding = "UTF-8")

# extract main content
txt <- ArticleSentencesExtractor(html)
print(txt)

# write the result into txt file
write.table(txt,"result.txt",sep="",row.names=FALSE,col.names=FALSE,quote=FALSE)