Gettingdata_allegro_pl

Scraping allegro.pl website

library(tidyr, warn.conflicts=F, quietly=T)
library(stringr, warn.conflicts=F, quietly=T)
library(RSelenium, warn.conflicts = F, quietly = T)
library(netstat)

tap_data=data.frame()   #Create empty data frame
driver <- rsDriver(browser = c("chrome"), chromever = "107.0.5304.62",port=free_port())

## checking Selenium Server versions:

## BEGIN: PREDOWNLOAD

## BEGIN: DOWNLOAD

## BEGIN: POSTDOWNLOAD

## checking chromedriver versions:

## BEGIN: PREDOWNLOAD

## BEGIN: DOWNLOAD

## BEGIN: POSTDOWNLOAD

## checking geckodriver versions:

## BEGIN: PREDOWNLOAD

## BEGIN: DOWNLOAD

## BEGIN: POSTDOWNLOAD

## checking phantomjs versions:

## BEGIN: PREDOWNLOAD

## BEGIN: DOWNLOAD

## BEGIN: POSTDOWNLOAD

## [1] "Connecting to remote server"
## $acceptInsecureCerts
## [1] FALSE
## 
## $browserName
## [1] "chrome"
## 
## $browserVersion
## [1] "107.0.5304.110"
## 
## $chrome
## $chrome$chromedriverVersion
## [1] "107.0.5304.62 (1eec40d3a5764881c92085aaee66d25075c159aa-refs/branch-heads/5304@{#942})"
## 
## $chrome$userDataDir
## [1] "/tmp/.com.google.Chrome.UE41IC"
## 
## 
## $`goog:chromeOptions`
## $`goog:chromeOptions`$debuggerAddress
## [1] "localhost:46675"
## 
## 
## $networkConnectionEnabled
## [1] FALSE
## 
## $pageLoadStrategy
## [1] "normal"
## 
## $platformName
## [1] "linux"
## 
## $proxy
## named list()
## 
## $setWindowRect
## [1] TRUE
## 
## $strictFileInteractability
## [1] FALSE
## 
## $timeouts
## $timeouts$implicit
## [1] 0
## 
## $timeouts$pageLoad
## [1] 300000
## 
## $timeouts$script
## [1] 30000
## 
## 
## $unhandledPromptBehavior
## [1] "dismiss and notify"
## 
## $`webauthn:extension:credBlob`
## [1] TRUE
## 
## $`webauthn:extension:largeBlob`
## [1] TRUE
## 
## $`webauthn:virtualAuthenticators`
## [1] TRUE
## 
## $webdriver.remote.sessionid
## [1] "28bceca4d8c2f453dd8fb13706e0cfbc"
## 
## $id
## [1] "28bceca4d8c2f453dd8fb13706e0cfbc"

remote_driver <- driver[["client"]]

tryCatch(
  {
    remote_driver$maxWindowSize()
    remote_driver$navigate("https://allegro.pl/kategoria/galanteria-i-dodatki-parasole-11068?string=umbrella")
    
    button<-remote_driver$findElements("xpath", '/html/body/div[2]/div[1]/div/div[2]/div/div[2]/button[1]')
    button[[1]]$clickElement()
    
    elements<-remote_driver$findElements("css", "article")
    
    for (el in elements){
      text<-el$getElementText()
      list<-str_split(text, "\n")
      
      zloty=gregexpr(text = text, pattern = fixed('zł\n'))
      separators=gregexpr(text = text, pattern = '\\n')
      
      num<-0
      for (i in separators[[1]]){
        num<-num+1
        if(zloty[[1]][1]<i){
          break
        }
      }
      if(zloty[[1]][1]==-1){
        num<-num+1
      }
      num
      
      if(list[[1]][num-1]=='Black Week'){
        name<-list[[1]][num-2]
        price<-list[[1]][num+1]
      }else{
        name<-list[[1]][num-1]
        price<-list[[1]][num]
      }
      
      tap_data=rbind(tap_data, data.frame(name,price,stringsAsFactors = FALSE))
    }
    
    print(paste(nrow(tap_data)))
  },
  error=function(e) {
    message('An Error Occurred')
    print(e)
  },
  warning=function(w) {
    message('A Warning Occurred')
    print(w)
    return(NA)
  }
)

## An Error Occurred

## <subscriptOutOfBoundsError in button[[1]]: subscript out of bounds>

head(tap_data)

## data frame with 0 columns and 0 rows