library(rvest) cislo <- seq(1,861,by=1) linky <- paste("https://forum.pirati.cz/viewforum.php?f=822&start=", cislo, sep="") linky_ok <- NA odpovedi <- NA zobrazeni <- NA datum <- NA zalozil <- NA tema<- NA pro <- NA proti <- NA zdrzelse <- NA celkem <- NA for (i in 1:861){ URL <- linky[i] stranka <- read_html(URL) linky_ok[i] <- paste("https://forum.pirati.cz", (stranka %>% html_nodes(xpath = '//*[@id="page-body"]/div[3]/div/ul[2]/li[1]/dl/dt/div/a') %>% html_attr("href")), sep="") odpovedi[i] <- stranka %>% html_nodes(xpath = '//*[@id="page-body"]/div[3]/div/ul[2]/li[1]/dl/dd[2]') %>% html_text() zobrazeni[i] <- stranka %>% html_nodes(xpath = '//*[@id="page-body"]/div[3]/div/ul[2]/li[1]/dl/dd[1]') %>% html_text() datum[i] <- stranka %>% html_nodes(xpath = '//*[@id="page-body"]/div[3]/div/ul[2]/li[1]/dl/dt/div/div[2]/time') %>% html_text() zalozil[i] <- stranka %>% html_nodes(xpath = '//*[@id="page-body"]/div[3]/div/ul[2]/li[1]/dl/dt/div/div[2]/a') %>% html_text() tema[i]<- stranka %>% html_nodes(xpath = '//*[@id="page-body"]/div[3]/div/ul[2]/li[1]/dl/dt/div/a') %>% html_text() URL2 <- linky_ok[i] stranka2 <- read_html(URL2) skip_to_next <- FALSE tryCatch(pro[i] <- stranka2 %>% html_nodes(xpath = '//*[@id="page-body"]/form/div/div/div/fieldset/dl[1]/dd[1]/div') %>% html_text(), error = function(e) { skip_to_next <<- TRUE}) if(skip_to_next) { pro[i] ==0} tryCatch(proti[i] <- stranka2 %>% html_nodes(xpath = '//*[@id="page-body"]/form/div/div/div/fieldset/dl[2]/dd[1]/div') %>% html_text(), error = function(e) { skip_to_next <<- TRUE}) if(skip_to_next) { proti[i] ==0} tryCatch(zdrzelse[i] <- stranka2 %>% html_nodes(xpath = '//*[@id="page-body"]/form/div/div/div/fieldset/dl[3]/dd[1]/div') %>% html_text(), error = function(e) { skip_to_next <<- TRUE}) if(skip_to_next) { zdrzelse[i] ==0} tryCatch(celkem[i] <- stranka2 %>% html_nodes(xpath = '//*[@id="page-body"]/form/div/div/div/fieldset/dl[4]/dd') %>% html_text(), error = function(e) { skip_to_next <<- TRUE}) if(skip_to_next) { celkem[i] ==0} } tabulka <- as.data.frame(cbind(linky_ok, odpovedi, zobrazeni, datum, zalozil, tema, pro, proti, zdrzelse , celkem))