通过导航doPostBack来抓取R网站

时间:2017-01-10 17:27:21

标签: r web-scraping rcurl rvest rselenium

我想从下面的网站中定期提取表格。

单击构建块名称时,

价格表会发生变化(BLOK 16 A,BLOK 16 B,BLOK 16 C,...)。网址不会更改,页面更改会被更改

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

我搜索了google和starckoverflow后尝试了3种方法。

我尝试过的不是1:这不会导致doPostBack事件失败。

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")

我尝试过的没有2: selenium remote似乎适用于(http://localhost:4444/),但是remotedriver无法导航。返回此错误。 (checkError(res)出错:   httr调用中的未定义错误。 httr输出:length(url)== 1不为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:这是另一种方式来解决dopostback事件。它无法导航。

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。

1 个答案:

答案 0 :(得分:2)

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)),]

已编辑代码:

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)),]