Blog

#!/usr/bin/perl

use strict;
use warnings;
use HTML::TokeParser;

# Output file for saving extracted content
my $output_file = 'moving_seoul_extracted.txt';

# Open the output file for writing
open my $output_fh, '>', $output_file or die "Cannot open output file '$output_file': $!";

# Iterate through each file from 1.mhtml to 25.mhtml
for my $file_number (1..25) {
    my $input_file = "${file_number}.mhtml";

    # Open the current input file for reading
    open my $input_fh, '<', $input_file or warn "Cannot open input file '$input_file': $!";

    # Create an HTML::TokeParser object for the current input file
    my $parser = HTML::TokeParser->new($input_fh);

    my $extract = 0;  # Flag to indicate whether to extract content between span and div tags

    # Iterate through the tokens in the current input file
    while (my $token = $parser->get_token) {
        if ($token->[0] eq 'S') {
            my $tag = $token->[1];

            # Check if the tag is "span" or "div" with class attribute containing "UsdlK" or "W4Efsd"
            my $class = $token->[2]->{class} || '';
            if (($tag eq 'span' && $class =~ /UsdlK/) || ($tag eq 'div' && $class =~ /W4Efsd/)) {
                $extract = 1;  # Set the extract flag to start extracting
                next;  # Skip the current token
            }
        }

        if ($extract && $token->[0] eq 'T') {
            # Extract and write the text content along with the file name to the output file
            my $content = $token->[1];
            print $output_fh "$input_file: $content\n";
        }

        if ($extract && $token->[0] eq 'E') {
            my $tag = $token->[1];

            # Reset the extract flag when the closing span or div tag is encountered
            if ($tag eq 'span' || $tag eq 'div') {
                $extract = 0;
            }
        }
    }

    # Close the current input file
    close $input_fh;
}

# Close the output file
close $output_fh;

# Print a completion message
print "Extraction complete. Extracted content with file names is saved in '$output_file'\n";

import re
import PyPDF2
import importlib
import subprocess
import csv
import os

def install_missing_package(package):
    try:
        importlib.import_module(package)
    except ImportError:
        subprocess.check_call(['pip', 'install', package])

def extract_phone_numbers_from_pdf(file_path):
    phone_numbers = []
    
    # Open the PDF file
    with open(file_path, 'rb') as file:
        # Create a PDF reader object
        reader = PyPDF2.PdfReader(file)
        
        # Iterate over each page in the PDF
        for page in reader.pages:
            # Extract the text from the page
            text = page.extract_text()
            
            # Use regular expressions to find phone numbers
            # This pattern matches US phone numbers in various formats
            pattern = r'(\+\d{1,2}\s?)?(\()?(\d{3})(?(2)\))[-.\s]?(\d{3})[-.\s]?(\d{4})'
            matches = re.findall(pattern, text)
            
            # Format the phone numbers as (###) ###-####
            formatted_numbers = ['({}) {}-{}'.format(*match[2:]) for match in matches]
            
            # Add the matched phone numbers to the list
            phone_numbers.extend(formatted_numbers)
    
    return phone_numbers

# Check if PyPDF2 is installed, and install it if necessary
install_missing_package('PyPDF2')

# Read the text file with a list of PDF file names
pdf_list_file = 'pdf_files.txt'
with open(pdf_list_file, 'r') as file:
    pdf_files = file.read().splitlines()

# Extract phone numbers from each PDF and store them in a list
phone_number_list = []
for pdf_file in pdf_files:
    phone_numbers = extract_phone_numbers_from_pdf(pdf_file)
    phone_number_list.extend([(pdf_file, number) for number in phone_numbers])

# Write the extracted phone numbers to a CSV file
csv_file = 'phone_extracts.csv'
with open(csv_file, 'w', newline='') as file:
    writer = csv.writer(file)
    writer.writerow(['PDF Name', 'Phone Number'])
    writer.writerows(phone_number_list)

# Print the success message
print(f"Phone numbers extracted from {len(pdf_files)} PDF files and saved to {csv_file}.")

import re
import PyPDF2
import importlib
import subprocess

def install_missing_package(package):
    try:
        importlib.import_module(package)
    except ImportError:
        subprocess.check_call(['pip', 'install', package])

def extract_phone_numbers_from_pdf(file_path):
    phone_numbers = []
    
    # Open the PDF file
    with open(file_path, 'rb') as file:
        # Create a PDF reader object
        reader = PyPDF2.PdfReader(file)
        
        # Iterate over each page in the PDF
        for page in reader.pages:
            # Extract the text from the page
            text = page.extract_text()
            
            # Use regular expressions to find phone numbers
            # This pattern matches US phone numbers in various formats
            pattern = r'(\+\d{1,2}\s?)?(\()?(\d{3})(?(2)\))[-.\s]?(\d{3})[-.\s]?(\d{4})'
            matches = re.findall(pattern, text)
            
            # Format the phone numbers as (###) ###-####
            formatted_numbers = ['({}) {}-{}'.format(*match[2:]) for match in matches]
            
            # Add the matched phone numbers to the list
            phone_numbers.extend(formatted_numbers)
    
    return phone_numbers

# Check if PyPDF2 is installed, and install it if necessary
install_missing_package('PyPDF2')

# Specify the path to your PDF file
pdf_file_path = 'sample.pdf'

# Extract phone numbers from the PDF file
phone_numbers = extract_phone_numbers_from_pdf(pdf_file_path)

# Print the extracted phone numbers
for number in phone_numbers:
    print(number)