ArchiveTeam/CommonCrawl_URL_Processor
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Commented out URL Extractions (to be done post downloading of files)

Browse Source
This commit is contained in:
datechnoman 2024-01-12 04:02:06 +00:00
parent cba96e96e7
commit b881641c69
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
urlextractor_archiveteam.sh
View File

@ -26,10 +26,12 @@ export -f gzip_file
for file in "$directory"/*_urls.txt; do
filename=$(basename "$file")
grep -E "http(s)?://(www\.)?mediafire.com" "$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/" "$file" | sort -u >> "/opt/CommonCrawl_URL_Processor/export/discord_urls.txt"
# Commented out the lines that extract URLs
# grep -E "http(s)?://(www\.)?mediafire.com" "$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" &
@ -49,4 +51,4 @@ done
wait
# Move compressed files to /opt/CommonCrawl_URL_Processor
# mv "$directory"/*.gz /opt/CommonCrawl_URL_Processor/
# mv "$directory"/*.gz /opt/CommonCrawl_URL_Processor/