在循环中使用pdftools时的错误处理

Question

我试图从多个pdf文件中提取某些表，但并不是所有的文件都有该表。即使第一个文件不包含特定的表，我如何使用trycatch或类似命令跳过并继续下一个文件？

library(pdftools)
library(tidyverse)

url <- c("https://www.computershare.com/News/Annual%20Report%202019.pdf?2",
         "https://www.annualreports.com/HostedData/AnnualReportArchive/a/LSE_ASOS_2018.PDF")

raw_text <- map(url, pdf_text)

clean_table1 <- function(raw) {
  
  raw <- map(raw, ~ str_split(.x, "\\n") %>% unlist())
  raw <- reduce(raw, c)
  
  table_start <- stringr::str_which(tolower(raw), "twenty largest shareholders")
  table_end <- stringr::str_which(tolower(raw), "total")
  table_end <- table_end[min(which(table_end > table_start))]
  
  table <- raw[(table_start + 3 ):(table_start + 25)]
  table <- str_replace_all(table, "\\s{2,}", "|")
  text_con <- textConnection(table)
  data_table <- read.csv(text_con, sep = "|")
  #colnames(data_table) <- c("Name", "Number of Shares", "Percentage")
  data_table
}

shares <- map_df(raw_text, clean_table1) 

当我尝试运行时，我得到了以下错误。

Error in (table_start + 3):(table_start + 25) : argument of length 0
In addition: Warning message:
In min(which(table_end > table_start)) :
  no non-missing arguments to min; returning Inf

Answer 1

您可以检查table_start的length和return NULL，如果它为0，那么当使用map_df时，这些记录将自动折叠，您将拥有一个组合的数据帧。

library(tidyverse)

clean_table1 <- function(raw) {
  
  raw <- map(raw, ~ str_split(.x, "\\n") %>% unlist())
  raw <- reduce(raw, c)
  
  table_start <- stringr::str_which(tolower(raw), "twenty largest shareholders")
  if(!length(table_start)) return(NULL)
  table_end <- stringr::str_which(tolower(raw), "total")
  table_end <- table_end[min(which(table_end > table_start))]
  
  table <- raw[(table_start + 3 ):(table_start + 25)]
  table <- str_replace_all(table, "\\s{2,}", "|")
  text_con <- textConnection(table)
  data_table <- read.csv(text_con, sep = "|")
  #colnames(data_table) <- c("Name", "Number of Shares", "Percentage")
  data_table
}

shares <- map_df(raw_text, clean_table1)