Scraping data from pdf file in R - r

Question

I need to extract tables from a pdf. Here's the link
https://www.acea.be/uploads/statistic_documents/ACEA_Report_Vehicles_in_use-Europe_2018.pdf
I want first table from this pdf.
Here is my code
Sys.setenv(JAVA_HOME='C:\\Program Files\\Java\\jre1.8.0_201') # for 64-bit version
# install.packages("devtools")
library(tabulizer)
library(tabulizerjars)
library(tidyverse)
tab <- extract_tables("https://www.acea.be/uploads/statistic_documents/ACEA_Report_Vehicles_in_use-Europe_2018.pdf")
tab[[1]]
head(tab[[1]])
But in o/p column of year 2012,2013,2015,2016 are getting append into one column.
I want table as in pdf file .
o/p of my code.
[,1] [,2] [,3]
[1,] "Croatia" "1,445,0001,433,5631,458,1491,489,3381,540,2603.4" ""
[2,] "Czech Republic" "4,698,8004,787,8494,893,5625,115,3165,368,6605.0" ""
[3,] "Denmark" "2,225,1642,265,3492,320,9822,391,7552,477,4783.6" ""
[4,] "Estonia" "602,133628,562652,949676,592703,1513.9" ""
[5,] "Finland" "2,560,1902,575,9512,595,8672,612,9222,629,4320.6" ""
[6,] "France" "31,600,00031,650,00031,799,00031,915,49331,999,9530.3" ""

Answer 1

Here is an alternative solution :
library(RDCOMClient)
################################################
#### Step 1 : We convert the image to a PDF ####
################################################
path_PDF <- "C:\\ACEA_Report_Vehicles_in_use-Europe_2018.pdf"
path_Word <- "C:\\temp.docx"
####################################################################
#### Step 2 : We use the OCR of Word to convert the PDF in word ####
####################################################################
wordApp <- COMCreate("Word.Application")
wordApp[["Visible"]] <- TRUE
wordApp[["DisplayAlerts"]] <- FALSE
doc <- wordApp[["Documents"]]$Open(normalizePath(path_PDF),
ConfirmConversions = FALSE)
doc$SaveAs2(path_Word)
##############################################################
#### Step 3 : We extract the table from the word document ####
##############################################################
nb_Table <- doc$tables()$count()
list_Table <- list()
for(l in 1 : nb_Table)
{
nb_Row <- doc$tables(l)$Rows()$Count()
nb_Col <- doc$tables(l)$Columns()$Count()
mat_Temp <- matrix(NA, nrow = nb_Row, ncol = nb_Col)
for(i in 1 : nb_Row)
{
for(j in 1 : nb_Col)
{
mat_Temp[i, j] <- tryCatch(doc$tables(l)$cell(i, j)$range()$text(), error = function(e) NA)
}
}
list_Table[[l]] <- mat_Temp
}
list_Table[[1]]
[,1] [,2] [,3] [,4] [,5] [,6] [,7]
[1,] "Austria\r\a" "4,584,202\r\a" "4,641,308\r\a" "4,694,921\r\a" "4,748,048\r\a" "4,821,557\r\a" "1.5\r\a"
[2,] "Belgium\r\a" "5,392,909\r\a" "5,439,295\r\a" "5,511,080\r\a" "5,587,415\r\a" "5,669,764\r\a" "1.5\r\a"
[3,] "Croatia\r\a" "1,445,000\r\a" "1,433,563\r\a" "1,458,149\r\a" "1,489,338\r\a" "1,540,260\r\a" "3.4\r\a"
[4,] "Czech Republic\r\a" "4,698,800\r\a" "4,787,849\r\a" "4,893,562\r\a" "5,115,316\r\a" "5,368,660\r\a" "5.0\r\a"
[5,] "Denmark\r\a" "2,225,164\r\a" "2,265,349\r\a" "2,320,982\r\a" "2,391,755\r\a" "2,477,478\r\a" "3.6\r\a"
[6,] "Estonia\r\a" "602,133\r\a" "628,562\r\a" "652,949\r\a" "676,592\r\a" "703,151\r\a" "3.9\r\a"
[7,] "Finland\r\a" "2,560,190\r\a" "2,575,951\r\a" "2,595,867\r\a" "2,612,922\r\a" "2,629,432\r\a" "0.6\r\a"
[8,] "France\r\a" "31,600,000\r\a" "31,650,000\r\a" "31,799,000\r\a" "31,915,493\r\a" "31,999,953\r\a" "0.3\r\a"
[9,] "Germany\r\a" "43,431,124\r\a" "43,851,230\r\a" "44,403,124\r\a" "45,071,209\r\a" "45,803,560\r\a" "1.6\r\a"
[10,] "Greece\r\a" "5,138,745\r\a" "5,109,435\r\a" "5,102,203\r\a" "5,104,908\r\a" "5,126,024\r\a" "0.4\r\a"
[11,] "Hungary\r\a" "2,978,745\r\a" "3,035,764\r\a" "3,101,752\r\a" "3,192,132\r\a" "3,308,495\r\a" "3.6\r\a"
[12,] "Ireland\r\a" "1,882,550\r\a" "1,910,165\r\a" "1,943,868\r\a" "1,985,130\r\a" "2,026,977\r\a" "2.1\r\a"
[13,] "Italy\r\a" "37,078,274\r\a" "36,962,934\r\a" "37,080,753\r\a" "37,351,233\r\a" "37,876,138\r\a" "1.4\r\a"
[14,] "Latvia\r\a" "618,000\r\a" "634,214\r\a" "657,487\r\a" "677,561\r\a" "663,091\r\a" "-2.1\r\a"
[15,] "Lithuania\r\a" "1,753,000\r\a" "1,837,661\r\a" "1,113,445\r\a" "1,153,859\r\a" "1,190,146\r\a" "3.1\r\a"
[16,] "Luxembourg\r\a" "344,951\r\a" "355,358\r\a" "362,879\r\a" "372,538\r\a" "380,860\r\a" "2.2\r\a"
[17,] "Netherlands\r\a" "8,142,000\r\a" "8,154,000\r\a" "8,192,570\r\a" "8,336,414\r\a" "8,439,318\r\a" "1.2\r\a"
[18,] "Poland\r\a" "18,744,412\r\a" "19,389,446\r\a" "20,003,863\r\a" "20,723,423\r\a" "21,675,388\r\a" "4.6\r\a"
[19,] "Portugal\r\a" "4,497,000\r\a" "4,480,000\r\a" "4,496,000\r\a" "4,538,000\r\a" "4,600,000\r\a" "1.4\r\a"
[20,] "Romania\r\a" "4,485,148\r\a" "4,693,651\r\a" "4,905,630\r\a" "5,153,182\r\a" "5,470,578\r\a" "6.2\r\a"
[21,] "Slovakia\r\a" "1,826,393\r\a" "1,882,577\r\a" "1,952,002\r\a" "2,037,772\r\a" "2,124,972\r\a" "4.3\r\a"
[22,] "Slovenia\r\a" "1,080,001\r\a" "1,085,347\r\a" "1,096,920\r\a" "1,116,006\r\a" "1,143,218\r\a" "2.4\r\a"
[23,] "Spain\r\a" "22,247,528\r\a" "22,024,538\r\a" "22,029,512\r\a" "22,355,549\r\a" "22,876,247\r\a" "2.3\r\a"
[24,] "Sweden\r\a" "4,447,165\r\a" "4,495,473\r\a" "4,585,519\r\a" "4,669,063\r\a" "4,768,060\r\a" "2.1\r\a"
[25,] "United Kingdom\r\a" "31,481,823\r\a" "31,917,885\r\a" "32,612,782\r\a" "33,542,448\r\a" "34,378,386\r\a" "2.5\r\a"
[26,] "EUROPEAN UNION\r\a" "243,285,257\r\a" "245,241,555\r\a" "247,566,819\r\a" "251,917,306\r\a" "257,061,713\r\a" "2.0\r\a"
[27,] "Norway\r\a" "2,433,147\r\a" "2,487,254\r\a" "2,539,513\r\a" "2,592,324\r\a" "2,639,245\r\a" "1.8\r\a"
[28,] "Switzerland\r\a" "4,300,036\r\a" "4,366,895\r\a" "4,430,375\r\a" "4,503,865\r\a" "4,571,994\r\a" "1.5\r\a"
[29,] "EFTA\r\a" "6,733,183\r\a" "6,854,149\r\a" "6,969,888\r\a" "7,096,189\r\a" "7,211,239\r\a" "1.6\r\a"
[30,] "Russia\r\a" "38,482,000\r\a" "39,322,526\r\a" "40,844,535\r\a" "40,859,866\r\a" "41,614,430\r\a" "1.8\r\a"
[31,] "Turkey\r\a" "8,648,875\r\a" "9,283,923\r\a" "9,857,915\r\a" "10,589,337\r\a" "11,317,998\r\a" "6.9\r\a"
[32,] "Ukraine\r\a" "9,910,004\r\a" "9,958,943\r\a" "9,581,401\r\a" "9,602,581\r\a" "9,679,279\r\a" "0.8\r\a"