r - 基于并发请求的 RCurl 爬虫问题

Question

以下是一个脚本，用于重现我在使用执行并发请求的 RCurl 构建爬虫时所面临的问题。
目标是下载数千个网站的内容以进行统计分析。因此，解决方案应该扩展。

library(RCurl)
library(httr)

uris = c("inforapido.com.ar", "lm.facebook.com", "promoswap.enterfactory.com", 
         "p.brilig.com", "wap.renxo.com", "alamaula.com", "syndication.exoclick.com", 
         "mcp-latam.zed.com", "startappexchange.com", "fonts.googleapis.com", 
         "xnxx.com", "wv.inner-active.mobi", "canchallena.lanacion.com.ar", 
         "android.ole.com.ar", "livefyre.com", "fbapp://256002347743983/thread")

### RCurl Concurrent requests 

getURIs <- function(uris, ..., multiHandle = getCurlMultiHandle(), .perform = TRUE){
  content = list()
  curls = list()
  for(i in uris) {
    curl = getCurlHandle()
    content[[i]] = basicTextGatherer()
    opts = curlOptions(URL = i, writefunction = content[[i]]$update,
                       timeout = 2, maxredirs = 3, verbose = TRUE,
                       followLocation = TRUE,...)
    curlSetOpt(.opts = opts, curl = curl)
    multiHandle = push(multiHandle, curl)
  }
  if(.perform) {
    complete(multiHandle)
    lapply(content, function(x) x$value())
  } else {
    return(list(multiHandle = multiHandle, content = content))
  }
}

### Split uris in 3
uris_ls = split(uris, 1:3)

### retrieve content 
uris_content <- list()
for(i in seq_along(uris_ls)){
  uris_content[[i]] <- getURIs(uris_ls[[i]])
}

library(plyr)
a = lapply(uris_content, function(x) ldply(x, rbind))
result = ldply(a, rbind)
names(result) <- c('url', 'content')
result$number_char <- nchar(as.character(result$content))

### Here are examples of url that aren't working
url_not_working = result[result$number_char == 0, 1]

# url_not_working
# [1] "inforapido.com.ar"              "canchallena.lanacion.com.ar"    "fbapp://256002347743983/thread"
# [4] "xnxx.com"                       "startappexchange.com"           "wv.inner-active.mobi"          
# [7] "livefyre.com"   

### Using httr GET it works fine

get_httr = GET(url_not_working[2])
content(g, 'text')

# The result is the same when using a single call
get_rcurl = getURL(url_not_working[2], encoding='UTF-8', timeout = 2, 
                   maxredirs = 3, verbose = TRUE,
                   followLocation = TRUE)
get_rcurl

问题:

鉴于我需要抓取的网页数量，我宁愿为此使用 RCurl，因为它支持并发请求。
我想知道是否可以改进 getURLs() 调用以使其工作
在 getURL/getURLs 版本失败的情况下作为 GET() 版本。

更新:

我添加了一个包含更多数据(990 uris)的要点以更好地重现问题。

uris_ls <- dput() # dput() output found here: https://gist.github.com/martinbel/b4cc730b32914475ef0b

运行后:

uris_content <- list()
for(i in seq_along(uris_ls)){
  uris_content[[i]] <- getURIs(uris_ls[[i]])
}

我收到以下错误:

Error in curlMultiPerform(obj) : embedded nul in string: 'GIF89a\001'
In addition: Warning message:
In strsplit(str, "\\\r\\\n") : input string 1 is invalid in this locale

使用 getURIAsynchronous:

  uris_content <- list()
  for(i in seq_along(uris_ls)){
    uris_content[[i]] <- getURIAsynchronous(uris_ls[[i]], 
         .opts=list(timeout = 2, maxredirs = 3, verbose = TRUE,
         followLocation = TRUE))
  }

我收到类似的错误:
nchar(str) 中的错误:无效的多字节字符串 1

更新 2

library(RCurl)
uris_ls <- dput() # dput() output found here: https://gist.github.com/martinbel/b4cc730b32914475ef0b

尝试以下操作后:

Sys.setlocale(locale="C")
uris_content <- list()
for(i in seq_along(uris_ls)){
    uris_content[[i]] <- getURIAsynchronous(uris_ls[[i]], 
       .opts=list(timeout = 2, maxredirs = 3, verbose = TRUE,
       followLocation = TRUE))
}

结果是它对前 225 个 URL 运行良好，然后它只从网站返回 cero 内容。这是空错误问题吗？

# This is a quick way to inspect the output:
nc = lapply(uris_content, nchar)
nc[[5]]
 [1]  51422      0     16  19165 111763      6  14041    202   2485      0
[11]  78538      0      0      0 133253  42978      0      0   7880  33336
[21]   6762    194     93      0      0      0      0      0      9      0
[31] 165974  13222  22605   1392      0  42932   1421      0      0      0
[41]      0  13760    289      0   2674

nc[[6]]
[1] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[39] 0 0 0 0 0 0 0

Answer 1

由于没有人回答，我提出了一个临时解决方案。如果 getURIAsynchronous 不起作用，只需使用 httr::GET 按顺序下载和 httr::content没有空字符串问题。

library(RCurl)
library(httr)

Sys.setlocale(locale="C")

opts = list(timeout = 2, maxredirs = 3, 
            verbose = TRUE, followLocation = TRUE)

try_asynch <- function(uris, .opts=opts){
  getURIAsynchronous(uris, .opts=opts)
}

get_content <- function(uris){
  cont <- try_asynch(uris)
  nc <- lapply(content, nchar)
  nc <- sapply(nc, function(x) ifelse(sum(x > 0), 1, 0))
  if(sum(nc) < 10){
    r <- lapply(uris, function(x) GET(x))
    cont <- lapply(r, function(x) content(x, 'text'))
  }
  cont
}

docs <- lapply(uris_ls, get_content)