diff --git a/urlextractor_archiveteam.sh b/urlextractor_archiveteam.sh deleted file mode 100644 index b8289fb..0000000 --- a/urlextractor_archiveteam.sh +++ /dev/null @@ -1,54 +0,0 @@ -#!/bin/bash - -check_disk_space() { - while true; do - available_space=$(df -BG /dev/sda1 | awk 'NR==2 {print $4}' | tr -d 'G') - if [ "$available_space" -ge 20 ]; then - break - else - echo "Waiting for more than 20GB free space on /dev/sda1. Current available space: ${available_space}GB" - sleep 300 # Sleep for 5 minutes - fi - done -} - -# Check for free disk space before proceeding -check_disk_space - -directory=$(dirname "$0") - -gzip_file() { - file="$1" - gzip "$file" -} - -export -f gzip_file - -for file in "$directory"/*_urls.txt; do - filename=$(basename "$file") - - # Commented out the lines that extract URLs - # grep -E "http(s)?://(www\.)?mediafire.com" "$file" | sort -u >> "/opt/CommonCrawl_URL_Processor/export/mediafire_urls.txt" - # grep -E "http(s)?://(www\.)?i.imgur.com" "$file" | sort -u >> "/opt/CommonCrawl_URL_Processor/export/imgur_urls.txt" - # grep -E "http(s)?://(www\.)?pastebin.com" "$file" | sort -u >> "/opt/CommonCrawl_URL_Processor/export/pastebin_urls.txt" - # grep "https://cdn.discordapp.com/" "$file" | sort -u >> "/opt/CommonCrawl_URL_Processor/export/discord_urls.txt" - - if [[ $filename != "mediafire_urls.txt" && $filename != "t.me_urls.txt" && $filename != "telegram.me_urls.txt" && $filename != "sitemap_urls.txt" ]]; then - parallel gzip_file ::: "$file" & - - # Remove the line containing the filename (without "_urls.txt") from urls_to_download.txt - if sed -i "/$(echo "$filename" | sed 's/_urls.txt//')/d" "/opt/CommonCrawl_URL_Processor/urls_to_download.txt"; then - echo "File $(echo "$filename" | sed 's/_urls.txt//') has been successfully removed from urls_to_download.txt" - remaining_count=$(wc -l "/opt/CommonCrawl_URL_Processor/urls_to_download.txt" | awk '{print $1}') - echo "WAT files remaining to be processed $remaining_count" - else - echo "Failed to remove $filename from urls_to_download.txt" - fi - fi -done - -# Wait for all gzip processes to finish -wait - -# Move compressed files to /opt/CommonCrawl_URL_Processor -# mv "$directory"/*.gz /opt/CommonCrawl_URL_Processor/