Question

我使用textread包中的read_doc函数编写了一个简单的r脚本来导入doc文件。但是，当它尝试加载中型文件时，会花费很长时间，并且会强制关闭。该如何处理？


dir <- setwd("Data")
url <- "https://www.pjf.mg.gov.br/e_atos/e_atos.php"

pjf.dados <- function(filtro1, dataArea0, dataArea1) {

  dados <- list(filtro1 = "24",
                filtro2 = " ",
                dataArea0 = "01/01/2010",
                dataArea1 = "31/12/2017",
                sb_psq2 = "Pesquisar")

}

form <- pjf.dados(filtro1, dataArea0, dataArea1)

# requisicao de busca
res <- POST(url, body = form)

nit <- res %>%
  xml2::read_html() %>% 
  html_nodes('a') %>%
  html_attr('href') 

nit <- nit[grepl("nit", nit, ignore.case = TRUE)]
atos <- sub("/([^/]*)$", "/", url)
anexos <- sapply(strsplit(nit, split='./', fixed=TRUE), function(x) (x[2]))
links <- gsub(" ", "%20", (paste0(atos, anexos)))

    for (i in 1:length(links)) {

  if(!file.exists(basename(links[i])))
    try(download.file((links[i]), destfile = basename(links[i]),  mode="wb"))
}

doc_files <- list.files(".", pattern = "doc", full.names = TRUE)

  list_doc <- tryCatch ({

    lapply(doc_files, function (i) {
    read_doc(i) %>%
    str_split(pattern = "\n") %>%
      unlist() %>%
     str_trim() %>%
      str_subset(pattern = ":(\\d+)")

})

如何使用TextRead R包读取mediu大小的doc文件

0 个答案: