quick and dirty code to extraplate text from html file with custom tag

text_from_html.R

      
      
    library(rio)
    library(dplyr)
    
    
    read_file = function(file_path) {
      file_connection <- file(file_path, "r")
      read_data       <-  c()
      while ( TRUE ) {
        line <- readLines(file_connection, n = 1)
        if ( length(line) == 0 ) {
          break
        }
        read_data <- c(read_data,line)
      }
      close(file_connection)
      return(read_data)
    }
    
    text_from_html <- function(html_file_path ,txt_file_destination){
      data_vector  <- (read_file(html_file_path)) #vector of all lines within rmd file
      patterns_vector <- c(
        '<p class="ti-section-1"',
        '<p class="ti-section-2"',
        '<span class="bold">',
          '<p class="ti-art"', 
        '<p class="sti-art">',
          '<span class="italic">'
      )
      complete <- c()
      for (i in 1:length(patterns_vector)){
      extremes     <- grep(patterns_vector[i],data_vector ) 
      print(extremes)
      complete <- c(complete, extremes)
      }
      complete %>% unique() %>% sort() -> index_vector

      text       <- data_vector[index_vector] #filter read file for line of r codes
      patterns_vector <- c(
        '<p class="ti-section-1"',
        '<p class="ti-section-2"',
        '<span class="bold">',
        '<p class="ti-art"', 
        '<p class="sti-art">',
        '<span class="italic">',
        '</p>',
        '-1-1',
        'id="d1e',
        '"L_2013176IT.01000101-d-',
        '">',
        '</span>',
        '<p class="tbl-txt'
      )
      for (i in 1:length(patterns_vector)){
      text <- gsub(patterns_vector[i],"",text)
      }
      print(text)
      write(text,txt_file_destination)
       }
    
    text_from_html("L_2013176IT.01000101.xml.html",txt_file_destination = "report.txt")