Visit “KoreaDaily Yelllowpage” using Firefox<\/p>\n\n\n\n
Choose {\uc2dc\uc560\ud2c0}<\/p>\n\n\n\n
\ub2e4\uc6b4\ub85c\ub4dc, “\uac00 \ub098 \ub2e4 \ub77c \ub9c8 \ubc14 \uc0ac \uc544 \uc790 \ucc28 \uce74 \ud0c0 \ud30c \ud558” as TEXT file using Firefox.<\/strong><\/p>\n\n\n\n US_Cities.txt<\/strong><\/p>\n\n\n\n US_Cities.pl<\/strong><\/p>\n\n\n\n KoreaDaily.pl (this code extracts each business type URL at KoreaDaily Yellowpage)<\/strong><\/p>\n\n\n\n KoreaDaily_URL.pl (this code removes < and > from KoreaDaily.txt)<\/strong><\/p>\n\n\n\n KoreaDaily_URL_biz.pl (removes none biz name URL)<\/strong><\/p>\n\n\n\n mecha.pl (this code mechanize each page)<\/strong><\/p>\n\n\n\n filename.pl (come up with mechanized file list file)<\/strong><\/p>\n\n\n\n page_extract.pl (extracts mechanizable file names on downloaded file)<\/strong><\/p>\n\n\n\n page6extract.pl <\/strong><\/p>\n\n\n\n page6unique.pl (come up with unique lines from extrated)<\/strong><\/p>\n\n\n\n onlypage6_modified.pl (update url)<\/strong><\/p>\n\n\n\n run above again for page=11, page=16, page=21, etc.<\/strong><\/p>\n\n\n\n and run mecha.pl accordingly again.<\/strong><\/p>\n","protected":false},"excerpt":{"rendered":" Visit “KoreaDaily Yelllowpage” using Firefox Choose {\uc2dc\uc560\ud2c0} \ub2e4\uc6b4\ub85c\ub4dc, “\uac00 \ub098 \ub2e4 \ub77c \ub9c8 \ubc14 \uc0ac \uc544 \uc790 \ucc28 \uce74 \ud0c0 \ud30c \ud558” as TEXT file using Firefox. US_Cities.txt US_Cities.pl KoreaDaily.pl (this code extracts each business type URL at KoreaDaily Yellowpage) KoreaDaily_URL.pl (this code removes < and > from KoreaDaily.txt) KoreaDaily_URL_biz.pl (removes none biz name URL) … <\/p>\nAtlanta\nChicago\nTexas\nWashington_DC\nDenver\nHawaii\nLos_Angeles\nNew_York\nSan_Diego\nSeattle\nSan_Francisco\nLas_Vegas<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Open US_Cities.txt for reading\nopen(my $input_fh, '<', 'US_Cities.txt') or die \"Could not open US_Cities.txt: $!\";\n# Open US_Cities_14.txt for writing\nopen(my $output_fh, '>', 'US_Cities_14.txt') or die \"Could not create US_Cities_14.txt: $!\";\n\n# Read each line from US_Cities.txt\nwhile (my $city = <$input_fh>) {\n chomp $city; # Remove newline character\n # Write the city name followed by numbers 01 to 14 to US_Cities_14.txt\n print $output_fh \"$city\\_01.txt\\n\";\n print $output_fh \"$city\\_02.txt\\n\";\n print $output_fh \"$city\\_03.txt\\n\";\n print $output_fh \"$city\\_04.txt\\n\";\n print $output_fh \"$city\\_05.txt\\n\";\n print $output_fh \"$city\\_06.txt\\n\";\n print $output_fh \"$city\\_07.txt\\n\";\n print $output_fh \"$city\\_08.txt\\n\";\n print $output_fh \"$city\\_09.txt\\n\";\n print $output_fh \"$city\\_10.txt\\n\";\n print $output_fh \"$city\\_11.txt\\n\";\n print $output_fh \"$city\\_12.txt\\n\";\n print $output_fh \"$city\\_13.txt\\n\";\n print $output_fh \"$city\\_14.txt\\n\";\n print $output_fh \"\\n\"; # Add a blank line between cities\n}\n\n# Close the file handles\nclose $input_fh;\nclose $output_fh;\n\nprint \"US_Cities_14.txt has been created.\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Define the output file name\nmy $output_file = 'KoreaDaily.txt';\n\n# Open the output file for writing\nopen(my $fh_out, '>', $output_file) or die \"Could not open file '$output_file' for writing: $!\";\n\n# Loop through files Atlanta_01.txt to Atlanta_13.txt\nfor my $file_number (1..14) {\n my $input_file = \"Seattle_\" . sprintf(\"%02d\", $file_number) . \".txt\";\n \n # Open the current input file for reading\n open(my $fh_in, '<', $input_file) or die \"Could not open file '$input_file': $!\";\n\n # Iterate through each line of the current input file\n while (my $line = <$fh_in>) {\n # Check if the line contains 'cat_code='\n if ($line =~ \/cat_code=\/) {\n # Write the line to the output file\n print $fh_out $line;\n }\n }\n\n # Close the current input file handle\n close($fh_in);\n}\n\n# Close the output file handle\nclose($fh_out);\n\nprint \"Extraction completed. Results saved in '$output_file'.\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\nuse strict;\nuse warnings;\n\n# Define the input and output file names\nmy $input_file = \"KoreaDaily.txt\";\nmy $output_file = \"KoreaDaily_URL.txt\";\n\n# Open the input file for reading\nopen my $input_fh, '<', $input_file or die \"Cannot open file $input_file: $!\";\n\n# Open the output file for writing\nopen my $output_fh, '>', $output_file or die \"Cannot open file $output_file: $!\";\n\n# Loop through each line of the input file\nwhile (my $line = <$input_fh>) {\n chomp $line; # Remove newline character\n my @matches = $line =~ \/<([^>]+)>\/g; # Extract content between < and > using regex\n\n # Write the extracted content to the output file\n foreach my $match (@matches) {\n print $output_fh \"$match\\n\";\n }\n}\n\n# Close the files\nclose $input_fh;\nclose $output_fh;\n\nprint \"Extraction completed. Extracted content saved in $output_file.\\n\";\n\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Input and output file names\nmy $input_file = 'KoreaDaily_URL.txt';\nmy $output_file = 'KoreaDaily_URL_biz.txt';\n\n# Open input and output files\nopen(my $input_fh, '<', $input_file) or die \"Could not open file '$input_file': $!\";\nopen(my $output_fh, '>', $output_file) or die \"Could not create file '$output_file': $!\";\n\n# Read input file line by line\nwhile (my $line = <$input_fh>) {\n # Check if the line does not end with 'sort=N'\n unless ($line =~ \/sort=N$\/) {\n # Write the line to the output file\n print $output_fh $line;\n }\n}\n\n# Close file handles\nclose($input_fh);\nclose($output_fh);\n\nprint \"Filtered URLs saved to '$output_file'.\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\nuse Encode; # To handle encoding issues\nuse WWW::Mechanize;\n\n# Read URLs from the text file\nmy $filename = 'onlypage6_modified.txt';\n\n# Create a new WWW::Mechanize object\nmy $mech = WWW::Mechanize->new();\n\n# Open the text file\nopen(my $fh, '<', $filename) or die \"Could not open file '$filename' $!\";\n\n# Initialize page number\nmy $page_num = 1;\n\n# Loop through each URL in the file\nwhile (my $url = <$fh>) {\n chomp $url; # Remove newline character\n\n # Check if the URL contains \/list\/list.asp\n next unless $url =~ m|\/list\/list\\.asp|;\n\n # Try to visit the URL, skip on failure\n eval {\n $mech->get($url);\n };\n if ($@) {\n warn \"Failed to get $url: $@\";\n next; # Skip to the next URL on failure\n }\n\n # Get the content of the current page\n my $content = $mech->content();\n\n # Save the content to a file with EUC-KR encoding\n my $filename = sprintf(\"%d.html\", $page_num);\n open(my $fh_out, '>:encoding(EUC-KR)', $filename) or die \"Could not open file '$filename' for writing: $!\";\n print $fh_out $content;\n close $fh_out;\n\n # Find pagination links and click on them to navigate through pages\n my @pagination_links = $mech->find_all_links(url_regex => qr\/page=\/i);\n for my $link (@pagination_links) {\n # Try to visit the pagination link, skip on failure\n eval {\n $mech->get($link->url);\n };\n if ($@) {\n warn \"Failed to get pagination link $link->url: $@\";\n next; # Skip to the next pagination link on failure\n }\n\n my $content = $mech->content();\n $page_num++;\n my $filename = sprintf(\"%d.html\", $page_num);\n open(my $fh_out, '>:encoding(EUC-KR)', $filename) or die \"Could not open file '$filename' for writing: $!\";\n print $fh_out $content;\n close $fh_out;\n }\n\n # Increment page number\n $page_num++;\n}\n\n# Close the file handle\nclose($fh);\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\nuse strict;\nuse warnings;\n\n# Open the output file for writing\nopen my $output_fh, '>', \"file_names.txt\" or die \"Cannot open file file_names.txt for writing: $!\";\n\n# Generate file names from 1.html to 481.html and write them to the output file\nfor my $i (1..300) {\n my $file_name = \"$i.html\";\n print $output_fh \"$file_name\\n\";\n}\n\n# Close the file\nclose $output_fh;\n\nprint \"File names generated and saved to file_names.txt\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Define the input and output filenames\nmy $input_filename = 'file_names.txt';\nmy $output_filename = 'ahrefextract.txt';\n\n# Open the output file for writing\nopen(my $fh_out, '>', $output_filename) or die \"Could not open file '$output_filename' $!\";\n\n# Open the input file containing the list of HTML files\nopen(my $fh_in, '<', $input_filename) or die \"Could not open file '$input_filename' $!\";\n\n# Loop through each HTML file in the input list\nwhile (my $html_file = <$fh_in>) {\n chomp $html_file; # Remove newline character\n\n # Open the HTML file for reading\n open(my $fh_html, '<', $html_file) or die \"Could not open file '$html_file' $!\";\n\n # Read the HTML content from the file\n my $html_content = do { local $\/; <$fh_html> };\n\n # Close the HTML file handle\n close($fh_html);\n\n # Extract URLs matching the specified pattern\n while ($html_content =~ m\/<a\\s+[^>]*?href=\"([^\"]*\\\/list\\\/list\\.asp[^\"]*)\"\/ig) {\n my $url = $1;\n print $fh_out \"URL: $url\\n\"; # Write the extracted URL to the output file\n }\n}\n\n# Close the file handles\nclose($fh_in);\nclose($fh_out);\n\nprint \"Extraction complete. Extracted URLs saved in $output_filename\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Input and output filenames\nmy $input_filename = 'ahrefextract.txt';\nmy $output_filename = 'page_6_extract.txt';\n\n# Open the input file for reading\nopen(my $fh_in, '<', $input_filename) or die \"Could not open file '$input_filename' $!\";\n\n# Open the output file for writing\nopen(my $fh_out, '>', $output_filename) or die \"Could not open file '$output_filename' $!\";\n\n# Loop through each line in the input file\nwhile (my $line = <$fh_in>) {\n # Check if the line contains 'page=6'\n if ($line =~ \/page=6\/) {\n # Write the line to the output file\n print $fh_out $line;\n }\n}\n\n# Close the file handles\nclose($fh_in);\nclose($fh_out);\n\nprint \"Extraction complete. Lines containing 'page=6' saved in $output_filename\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Input and output filenames\nmy $input_filename = 'page_6_extract.txt';\nmy $output_filename = 'onlypage6.txt';\n\n# Hash to store unique lines\nmy %unique_lines;\n\n# Open the input file for reading\nopen(my $fh_in, '<', $input_filename) or die \"Could not open file '$input_filename' $!\";\n\n# Loop through each line in the input file\nwhile (my $line = <$fh_in>) {\n # Remove leading and trailing whitespace\n $line =~ s\/^\\s+|\\s+$\/\/g;\n\n # Add the line to the hash (keys are unique)\n $unique_lines{$line} = 1;\n}\n\n# Close the input file handle\nclose($fh_in);\n\n# Open the output file for writing\nopen(my $fh_out, '>', $output_filename) or die \"Could not open file '$output_filename' $!\";\n\n# Write unique lines to the output file\nforeach my $unique_line (keys %unique_lines) {\n print $fh_out \"$unique_line\\n\";\n}\n\n# Close the output file handle\nclose($fh_out);\n\nprint \"Unique lines from $input_filename saved in $output_filename\\n\";\n<\/code><\/pre>\n\n\n\n#!\/usr\/bin\/perl\n\nuse strict;\nuse warnings;\n\n# Input and output file names\nmy $input_file = 'onlypage6.txt';\nmy $output_file = 'onlypage6_modified.txt';\n\n# Open input and output files\nopen(my $input_fh, '<', $input_file) or die \"Could not open file '$input_file': $!\";\nopen(my $output_fh, '>', $output_file) or die \"Could not create file '$output_file': $!\";\n\n# Read input file line by line\nwhile (my $line = <$input_fh>) {\n # Replace 'URL: \/list' with 'http:\/\/yp.koreadaily.com\/list'\n $line =~ s\/URL: \\\/list\/http:\\\/\\\/yp.koreadaily.com\\\/list\/;\n # Write the modified line to the output file\n print $output_fh $line;\n}\n\n# Close file handles\nclose($input_fh);\nclose($output_fh);\n\nprint \"URLs modified and saved to '$output_file'.\\n\";\n<\/code><\/pre>\n\n\n\n