Question

我想应用一个循环从R中的多个网页中抓取数据。我能够抓取一个网页的数据，但是当我尝试使用多个页面的循环时，我得到一个令人沮丧的错误。我花了几个小时修补，但没有用。任何帮助将不胜感激!!!

这有效：

###########################
# GET COUNTRY DATA
###########################

library("rvest")

site <- paste("http://www.countryreports.org/country/","Norway",".htm", sep="")
site <- html(site)

stats<-
    data.frame(names =site %>% html_nodes(xpath="//*/td[1]") %>% html_text() ,
         facts =site %>% html_nodes(xpath="//*/td[2]") %>% html_text() ,
         stringsAsFactors=FALSE)

stats$country <- "Norway"
stats$names   <- gsub('[\r\n\t]', '', stats$names)
stats$facts   <- gsub('[\r\n\t]', '', stats$facts)
View(stats)

但是，当我尝试在循环中写入时，我收到错误

###########################
# ATTEMPT IN A LOOP
###########################

country<-c("Norway","Sweden","Finland","France","Greece","Italy","Spain")

for(i in country){

site <- paste("http://www.countryreports.org/country/",country,".htm", sep="")
site <- html(site)

stats<-
data.frame(names =site %>% html_nodes(xpath="//*/td[1]") %>% html_text() ,
         facts =site %>% html_nodes(xpath="//*/td[2]") %>% html_text() ,
       stringsAsFactors=FALSE)

stats$country <- country
stats$names   <- gsub('[\r\n\t]', '', stats$names)
stats$facts   <- gsub('[\r\n\t]', '', stats$facts)

stats<-rbind(stats,stats)
stats<-stats[!duplicated(stats),]
}

错误：

Error: length(url) == 1 is not TRUE
In addition: Warning message:
In if (grepl("^http", x)) { :
  the condition has length > 1 and only the first element will be used

Answer 1

最终工作代码：

###########################
# THIS WORKS!!!!
###########################

country<-c("Norway","Sweden","Finland","France","Greece","Italy","Spain")

for(i in country){

site <- paste("http://www.countryreports.org/country/",i,".htm", sep="")
site <- html(site)

stats<-
data.frame(names =site %>% html_nodes(xpath="//*/td[1]") %>% html_text() ,
     facts =site %>% html_nodes(xpath="//*/td[2]") %>% html_text() ,
       stringsAsFactors=FALSE)

stats$nm <- i
stats$names   <- gsub('[\r\n\t]', '', stats$names)
stats$facts   <- gsub('[\r\n\t]', '', stats$facts)
#stats<-stats[!duplicated(stats),]
all<-rbind(all,stats)

}
 View(all)

Answer 2

在循环之前初始化空数据帧。我已经完成了这个问题，以下代码对我来说很好。

country<-c("Norway","Sweden","Finland","France","Greece","Italy","Spain")
df <- data.frame(names = character(0),facts = character(0),nm = character(0))

for(i in country){

  site <- paste("http://www.countryreports.org/country/",i,".htm", sep="")
  site <- html(site)

  stats<-
    data.frame(names =site %>% html_nodes(xpath="//*/td[1]") %>% html_text() ,
               facts =site %>% html_nodes(xpath="//*/td[2]") %>% html_text() ,
               stringsAsFactors=FALSE)

  stats$nm <- i
  stats$names   <- gsub('[\r\n\t]', '', stats$names)
  stats$facts   <- gsub('[\r\n\t]', '', stats$facts)
  #stats<-stats[!duplicated(stats),]
  #all<-rbind(all,stats)
  df <- rbind(df, stats)
  #all <- merge(Output,stats)

}
View(df)

Answer 3

这就是我所做的。它不是最好的解决方案，但你会得到一个输出。这也只是一种解决方法。我不建议您在运行循环时将表输出写入文件。干得好。从stats生成输出后，

output<-rbind(stats,i)

然后将表写入，

write.table(output, file = "D:\\Documents\\HTML\\Test of loop.csv", row.names = FALSE, append = TRUE, sep = ",")

#then close the loop
}

祝你好运

如何使用循环来抓取R中多个网页的网站数据？

3 个答案: