Question

我现在已经足够长时间困惑，似乎无法弄清楚如何绕过它。最容易提供虚拟代码：

require(RCurl)
require(XML)

#set a bunch of options for curl
options(RCurlOptions = list(cainfo = system.file("CurlSSL", "cacert.pem", package = "RCurl")))
agent="Firefox/23.0" 
curl = getCurlHandle()
curlSetOpt(
  cookiejar = 'cookies.txt' ,
  useragent = agent,
  followlocation = TRUE ,
  autoreferer = TRUE ,
  httpauth = 1L, # "basic" http authorization version -- this seems to make a difference for India servers
  curl = curl
)


list1 <- c('http://timesofindia.indiatimes.com//articleshow/2933112.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933131.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933209.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933277.cms')

#note list2 has a new link inserted in 2nd position; this is the link that kills the following getURL calls
list2 <- c('http://timesofindia.indiatimes.com//articleshow/2933112.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933019.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933131.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933209.cms',
           'http://timesofindia.indiatimes.com//articleshow/2933277.cms')



for ( i in seq( list1 ) ){
  print(list1[i])
  html <-
    try( getURL(
      list1[i],
      maxredirs = as.integer(20),
      followlocation = TRUE,
      curl = curl
    ),TRUE)
  if (class (html) == "try-error") {
    print(paste("error accessing",list1[i]))
    rm(html)
    gc()
    next
  } else {
    print('success')
  }
}


gc()

for ( i in seq( list2 ) ){
  print(list2[i])
  html <-
    try( getURL(
      list2[i],
      maxredirs = as.integer(20),
      followlocation = TRUE,
      curl = curl
    ),TRUE)
  if (class (html) == "try-error") {
    print(paste("error accessing",list2[i]))
    rm(html)
    gc()
    next
  } else {
    print('success')
  }
}

这应该可以在安装RCurl和XML库的情况下运行。关键是当我将http://timesofindia.indiatimes.com//articleshow/2933019.cms插入列表中的第二个位置时，它会杀死循环其余部分的成功（其他链接是相同的）。当链接包含PDF（检查以查看）时，会发生这种情况（在此情况和其他情况下一致）。

有关如何解决此问题的任何想法，以便获取包含PDF的链接不会杀死我的循环？正如你所看到的，我试图清除可能有问题的对象，gc()到处都是等等，但我无法弄清楚为什么PDF会杀死我的循环。

谢谢！

只是为了检查，这是我的两个for循环的输出：

    #[1] "http://timesofindia.indiatimes.com//articleshow/2933112.cms"
    #[1] "success"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933131.cms"
    #[1] "success"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933209.cms"
    #[1] "success"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933277.cms"
    #[1] "success"

和

    #[1] "http://timesofindia.indiatimes.com//articleshow/2933112.cms"
    #[1] "success"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933019.cms"
    #[1] "error accessing http://timesofindia.indiatimes.com//articleshow/2933019.cms"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933131.cms"
    #[1] "error accessing http://timesofindia.indiatimes.com//articleshow/2933131.cms"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933209.cms"
    #[1] "error accessing http://timesofindia.indiatimes.com//articleshow/2933209.cms"
    #[1] "http://timesofindia.indiatimes.com//articleshow/2933277.cms"
    #[1] "error accessing http://timesofindia.indiatimes.com//articleshow/2933277.cms"

Answer 1

您可能会发现使用httr更容易。它包装RCurl并默认设置您需要的选项。这是与httr：

的等效代码

require(httr)

urls <- c(
  'http://timesofindia.indiatimes.com//articleshow/2933112.cms',
  'http://timesofindia.indiatimes.com//articleshow/2933019.cms',
  'http://timesofindia.indiatimes.com//articleshow/2933131.cms',
  'http://timesofindia.indiatimes.com//articleshow/2933209.cms',
  'http://timesofindia.indiatimes.com//articleshow/2933277.cms'
)

responses <- lapply(urls, GET)
sapply(responses, http_status)

sapply(responses, function(x) headers(x)$`content-type`)

RCurl getURL with loop - 链接到PDF杀死循环

1 个答案: