/* remove HTTP headers from multiple gzip or single zip from stdin */
    
     int fileno (FILE *);
     int setenv (const char *, const char *, int);
     #define jmp (yy_start) = 1 + 2 *
     int x;
    %option nounput noinput noyywrap
    %%
    HTTP\/[\40-\176]+\x0d\x0a x++;
    [\40-\176]+:[\40-\176]+\r\n if(!x)fwrite(yytext,1,yyleng,yyout);
    \x0D\x0A if(!x)fwrite(yytext,1,yyleng,yyout);x=0;
    %%
    int main()
    { 
    yylex();
    exit(0);
    }

Retrieve hostnames, IP addresses and (if available) sitemap URLs from latest Common Crawl.

     ftp -4 https://data.commoncrawl.org/crawl-data/CC-MAIN-2023-50/robotstxt.paths.gz # <-- 180K
     gzip -dc robotstxt.paths.gz \
     |head -5 \
     |sed 's>.*>GET /& HTTP/1.1[]Host: data.commoncrawl.org[]Connection: >;
           $!s/$/keep-alive[]/;$s/$/close[]/' \
     |tr [] '\r\n' \
     |openssl s_client -quiet -connect data.commoncrawl.org:443 \
     |yy054 \
     |zegrep -a '(^Sitemap:)|(^Host:)|(^WARC-Target-URI:)|(^WARC-IP-Address:)' > 1.txt
     exec cat 1.txt

Download NetBSD 1.0 in a single TCP connection.

    y="GET /pub/NetBSD-archive/NetBSD-1.0/source/src10/"
    z="Host: archive.netbsd.org"
    sed '$!s>.*>'"$y"'& HTTP/1.1[]'"$z"'[]Connection: keep-alive[]>;
         $s>.*>'"$y"'& HTTP/1.0[]'"$z"'[]>' << eof \
    |tr '[]' '\r\n' \
    |openssl s_client -quiet -connect 151.101.129.6:443 -servername archive.netbsd.org > http+gzip
    src10.aa
    src10.ab
    src10.ac
    src10.ad
    src10.ae
    src10.af
    src10.ag
    src10.ah
    src10.ai
    src10.aj
    src10.ak
    src10.al
    src10.am
    src10.an
    src10.ao
    src10.ap
    src10.aq
    src10.ar
    src10.as
    src10.at
    src10.au
    src10.av
    src10.aw
    src10.ax
    src10.ay
    src10.az
    src10.ba
    src10.bb
    src10.bc
    src10.bd
    src10.be
    src10.bf
    eof

    yy054 < http+gzip|tar tvzf /dev/stdin

Include an argv[1] will print HTTP headers only

    yy054 print < http+gzip
    yy054 x < http+gzip