Search code examples
rweb-scrapingrcurlrvestrselenium

Scrape website with R by navigating doPostBack


I want to extract a table periodicaly from below site.

price list changes when clicked building block names(BLOK 16 A, BLOK 16 B, BLOK 16 C, ...) . URL doesn't change, page changes by trigering

javascript:__doPostBack('ctl00$ContentPlaceHolder1$DataList2$ctl04$lnk_blok','')

I've tried 3 ways after searching google and starckoverflow.

what I've tried no 1: this doesn't triger doPostBack event.

postForm( "http://www.kentkonut.com.tr/tr/modul/projeler/daire_fiyatlari.aspx?id=44", ctl00_ContentPlaceHolder1_DataList2_ctl03_lnk_blok="ctl00$ContentPlaceHolder1$DataList2$ctl03$lnk_blok")

what I've tried no 2: selenium remote seem to works on (http://localhost:4444/) but remotedriver doesn't navigate. returns this error. (Error in checkError(res) : Undefined error in httr call. httr output: length(url) == 1 is not TRUE)

library(RSelenium)
startServer()
remDr <- remoteDriver()
remDr <- remoteDriver(remoteServerAddr = "localhost" 
                  , port = 4444L, browserName = "firefox")
remDr$open()
remDr$getStatus()
remDr$navigate("http://www.kentkonut.com.tr/tr/modul/projeler/daire_fiyatlari.aspx?id=44")

what I've tried no 3: this another way to triger dopostback event. it doesn't navigate.

base.url <- "http://www.kentkonut.com.tr/tr/modul/projeler/",
event.target <- 'ctl00$ContentPlaceHolder1$DataList2$ctl03$lnk_blok',
action <- "daire_fiyatlari.aspx?id=44"

ftarget <- paste0(base.url, action)
dum <- getURL(ftarget)
event.val <- unlist(strsplit(dum,"__EVENTVALIDATION\" value=\""))[2]
event.val <- unlist(strsplit(event.val,"\" />\r\n\r\n<script"))[1]
view.state <- unlist(strsplit(dum,"id=\"__VIEWSTATE\" value=\""))[2]
view.state <- unlist(strsplit(view.state,"\" />\r\n\r\n\r\n<script"))[1]
web.data <- postForm(ftarget, "form name" = "ctl00_ContentPlaceHolder1_DataList2_ctl03_lnk_blok", 
                   "method" = "POST", 
                   "action" = action, 
                   "id" = "ctl00_ContentPlaceHolder1_DataList2_ctl03_lnk_blok",
                   "__EVENTTARGET"=event.target,
                   "__EVENTVALIDATION"=event.val,
                   "__VIEWSTATE"=view.state)

thanks for your help.


Solution

  • library(rvest)    
    url<-"http://www.kentkonut.com.tr/tr/modul/projeler/daire_fiyatlari.aspx?id=44"
        pgsession<-html_session(url) 
        t<-html_table(html_nodes(read_html(pgsession), css = "#ctl00_ContentPlaceHolder1_DataList1"), fill= TRUE)[[1]]
        even_indices<-seq(2,length(t$X1),2)
        t<-t[even_indices,]
        t<-t[2:(length(t$X1)),]
    

    EDITED CODE:

    library(rvest)    
    url<-"http://www.kentkonut.com.tr/tr/modul/projeler/daire_fiyatlari.aspx?id=44"
    pgsession<-html_session(url)
    pgform<-html_form(pgsession)[[1]]
    page<-rvest:::request_POST(pgsession,"http://www.kentkonut.com.tr/tr/modul/projeler/daire_fiyatlari.aspx?id=44",
                               body=list(
                                 `__VIEWSTATE`=pgform$fields$`__VIEWSTATE`$value,
                                 `__EVENTTARGET`="ctl00$ContentPlaceHolder1$DataList2$ctl01$lnk_blok",
                                 `__EVENTARGUMENT`="",
                                 `__VIEWSTATEGENERATOR`=pgform$fields$`__VIEWSTATEGENERATOR`$value,
                                 `__VIEWSTATEENCRYPTED`=pgform$fields$`__VIEWSTATEENCRYPTED`$value,
                                 `__EVENTVALIDATION`=pgform$fields$`__EVENTVALIDATION`$value
                               ),
                               encode="form"
                               )
    # in the above example change eventtarget as "ctl00$ContentPlaceHolder1$DataList2$ctl02$lnk_blok" to get different table
    
    t<-html_table(html_nodes(read_html(page), css = "#ctl00_ContentPlaceHolder1_DataList1"), fill= TRUE)[[1]]
    even_indices<-seq(2,length(t$X1),2)
    t<-t[even_indices,]
    t<-t[2:(length(t$X1)),]