sliderule_scraper.R

## Scraper One
library(rvest)
url = "http://nuforc.org/webreports/ndxe201507.html"
pg <- html(url)
nodes <- html_nodes(pg, "table")
table <- html_table(nodes)
str(table)
View(table)

# Alternate pipe function 
# table <- pg %>% html_nodes("table") %>% html_table()

## Scraper Two 
url2 <- "http://carzoom.in/car-specification/"
pg2 <- html(url2)
nodes2 <- html_nodes(pg2, ".car-model li a")
title2 <- html_text(nodes2)
links2 <- html_attr(nodes2, "href")
links2

## Scraper Three
url3 <- "http://nhrdf.org/en-us/AreaAndProductiionReport"
pg3.session <- html_session(url3)
pg3.form <- html_form(pg3.session)[[1]]
pg3.form.filled <- set_values(pg3.form, 
                        "dnn$dnnLANG$selectCulture" = "en-US",
                        "dnn$ctr961$AreaAndProductiionReport$Year" = 2014,
                        "dnn$ctr961$AreaAndProductiionReport$State" = "All",
                        "dnn$ctr961$AreaAndProductiionReport$ddlCrop" = 1)

pg3.submit <- submit_form(pg3.session, pg3.form.filled,
          submit = 'dnn$ctr961$AreaAndProductiionReport$BtnGetMnthWiseData')

pg3.out <- html(pg3.submit)
pg3.table <-  pg3.out %>% 
  html_node("#dnn_ctr961_AreaAndProductiionReport_GridView1")  %>%
  html_table()

str(pg3.table)


# For Generalised Scraping (with parameters)
url4 = "http://nhrdf.org/en-us/AreaAndProductiionReport?year="
years <- 2014
urlGen <- paste0(url4, years)
urlGen