Schriftliche Anfragen Berlin pardok (lpd-abodienst@parlament-berlin.de)

pardok.R

# see also https://www.brodrigues.co/blog/2018-06-10-scraping_pdfs/

library(pdftools)
library(tidyverse)

( txt <- pdf_text(pdf = 'http://pardok.parlament-berlin.de/starweb/adis/citat/VT/18/SchrAnfr/S18-20899.pdf') %>% 
         readr::read_lines() ) 
    
fin <- txt[133:145]

fin <- fin %>% 
       str_replace_all('%', '') %>% 
       str_replace_all('\\.', '') %>% 
       str_replace_all('\\,', '.') %>% 
       stringr::str_squish()

( fin <- readr::read_delim(fin, delim = ' ', col_names = FALSE) )