Question

我试图从这个网页www.kinyo.es获取正文但它返回了这个问题：

Error in which(value == defs) : 
  argument "code" is missing, with no default
In addition: Warning messages:
1: XML content does not seem to be XML: 'Error displaying the error page: Application Instantiation Error: Could not connect to MySQL.' 
2: XML content does not seem to be XML: ''

我的代码是以下循环：

for(i in 1:n)
{

#get the URL
u <- webpage[i]

doc <- getURL(u)

#get the text from the body
html <- htmlTreeParse(doc, useInternal = TRUE)
txt <- xpathApply(html, "//body//text()[not(ancestor::script)][not(ancestor::style)][not(ancestor::noscript)]", xmlValue)
txt<-toString(txt)
txt

#clean
txt<-(str_replace_all(txt, "[\r\n\t,]" , ""))
txt<-tolower(txt)
txt
search <- c("wi-fi","router","switch","adsl","wireless")
search
stri_count_fixed(txt, search)

conta[i]<-sum(stri_count_fixed(txt, search))
#txt
}

Answer 1

这有点拉伸，因为我读了你的其他问题，我只能假设这就是你所追求的：

library(rvest)
library(stringr)

count_keywords <- function(url, keywords){
    read_html(url) %>% 
        html_nodes(xpath = '//body//text()[not(ancestor::script)][not(ancestor::style)][not(ancestor::noscript)]') %>% 
        html_text() %>% 
        toString() %>% 
        str_count(keywords) %>% 
        sum
}

urls <- c('http://www.dlink.com/it/it', 'http://www.kinyo.es')
search <- c("Wi-Fi","Router","Switch","ADSL")

res <- sapply(urls, count_keywords, search)

res
#> http://www.dlink.com/it/it        http://www.kinyo.es 
#>                         11                          0

R中的错误htmlTreeParse

1 个答案: