通过导航 doPostBack 使用 R 抓取网站

Scrape website with R by navigating doPostBack

我想从以下站点定期提取 table。

单击积木名称(BLOK 16 A、BLOK 16 B、BLOK 16 C、...)时价格表会发生变化。 URL 不改变,通过触发改变页面

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

我在搜索 google 和 starckoverflow 后尝试了 3 种方法。

我试过没有 1: 这不会触发 doPostBack 事件。

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")

我试过的 2: selenium 遥控器似乎可以工作 (http://localhost:4444/) 但 remotedriver 无法导航。 returns 这个错误。 (checkError(res) 中的错误: httr 调用中出现未定义错误。 httr 输出: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")

我试过的没有 3: 这是触发 dopostback 事件的另一种方式。它不导航。

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)

感谢您的帮助。

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)),]

编辑代码:

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)),]