0

我正在尝试从多个 pdf 文件中提取某些表格，但并非所有文件都有该表格。即使第一个文件不包含某个表，我如何使用 trycatch 或类似方法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)

尝试运行时出现以下错误。

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
4

1 回答 1

2

您可以检查是否length为0 table_start，return NULL因此在使用map_df这些记录时会自动折叠，并且您将拥有一个组合数据框。

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)
于 2020-10-15T01:20:44.727 回答