$ echo "a" > tmp.txt
$ la tmp.txt
-rw-r--r-- 1 alexk alexk     2 Jun  2 17:48 tmp.txt
$ chmod 0700 tmp.txt
$ la tmp.txt
-rwx------ 1 alexk alexk 2 Jun  2 17:48 tmp.txt
$ sudo chown root.root tmp.txt
[sudo] password for alexk: 
$ la tmp.txt
-rwx------ 1 root root 2 Jun  2 17:48 tmp.txt
$ rm tmp.txt
rm: remove write-protected regular file 'tmp.txt'? y
$ la tmp.txt
ls: cannot access 'tmp.txt': No such file or directory

$ apt search libdvd-pkg
Sorting... Done
Full Text Search... Done
libdvd-pkg/stable,now 1.4.2-1-1 all [installed]
  DVD-Video playing library - installer

$ apt search libdvdcss
Sorting... Done
Full Text Search... Done
…
libdvdcss-dev/now 1.4.2-1~local amd64 [installed,local]
  library for accessing encrypted DVDs - development files

libdvdcss2/now 1.4.2-1~local amd64 [installed,local]
  library for accessing encrypted DVDs

libdvdcss2-dbgsym/now 1.4.2-1~local amd64 [installed,local]
  debug symbols for libdvdcss2

libdvdread4/now 6.0.1-1 amd64 [installed,local]
  library for reading DVDs

libdvdread8/stable,now 6.1.1-2 amd64 [installed,automatic]
  library for reading DVDs

$ apt search libbluray
Sorting... Done
Full Text Search... Done
libbluray-bdj/stable,now 1:1.2.1-4+deb11u2 all [installed]
  Blu-ray Disc Java support library (BD-J library)

libbluray-bin/stable 1:1.2.1-4+deb11u2 amd64
  Blu-ray disc playback support library (tools)

libbluray-dev/stable 1:1.2.1-4+deb11u2 amd64
  Blu-ray disc playback support library (development files)

libbluray-doc/stable 1:1.2.1-4+deb11u2 all
  Blu-ray disc playback support library (documentation)

libbluray2/stable,now 1:1.2.1-4+deb11u2 amd64 [installed]
  Blu-ray disc playback support library (shared library)

$ hd /usr/lib/firefox-esr/fonts/TwemojiMozilla.ttf | head
00000000  00 01 00 00 00 11 01 00  00 04 00 10 43 4f 4c 52  |............COLR|
00000010  9b 59 1b ad 00 13 22 f8  00 02 51 6c 43 50 41 4c  |.Y...."...QlCPAL|
00000020  99 fd 98 85 00 15 74 64  00 00 0f ea 46 46 54 4d  |......td....FFTM|
00000030  94 98 f7 41 00 15 84 50  00 00 00 1c 47 44 45 46  |...A...P....GDEF|
00000040  00 27 34 59 00 15 84 6c  00 00 00 1e 47 53 55 42  |.'4Y...l....GSUB|
00000050  71 92 ee f7 00 15 84 8c  00 00 6c 80 4f 53 2f 32  |q.........l.OS/2|
00000060  34 c3 0a 83 00 00 01 98  00 00 00 60 63 6d 61 70  |4..........`cmap|
00000070  25 3d b7 6c 00 00 6a a8  00 00 0b fa 63 76 74 20  |%=.l..j.....cvt |
00000080  00 11 01 44 00 00 76 a4  00 00 00 04 67 61 73 70  |...D..v.....gasp|
00000090  ff ff 00 03 00 13 22 f0  00 00 00 08 67 6c 79 66  |......".....glyf|

$ file /usr/lib/firefox-esr/fonts/TwemojiMozilla.ttf
/usr/lib/firefox-esr/fonts/TwemojiMozilla.ttf: TrueType Font data, 17 tables, 1st "COLR", 12 names, Macintosh, type 1 string

$ apt search fonts-liberation
Sorting... Done
Full Text Search... Done
fonts-liberation/stable,now 1:1.07.4-11 all [installed]
  Fonts with the same metrics as Times, Arial and Courier

fonts-liberation2/stable,now 2.1.3-1 all [installed]
  Fonts with the same metrics as Times, Arial and Courier (v2)

ttf-mscorefonts-installer/stable,now 3.8 all [installed]
  Installer for Microsoft TrueType core fonts

$ file /usr/share/fonts/truetype/msttcorefonts/Arial.ttf
/usr/share/fonts/truetype/msttcorefonts/Arial.ttf: TrueType Font data, digitally signed, 23 tables, 1st "DSIG", 70 names, Unicode, Typeface \251 The Monotype Corporation plc. Data \251 The Monotype Corporation plc/Type Solution

$ uname -a
Linux ng3 6.1.0-0.deb11.5-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.1.12-1~bpo11+1 (2023-03-05) x86_64 GNU/Linux
$ la /boot/initrd* /boot/vmlinuz*
-rw-r--r-- 1 root root 68062772 Mar 28 22:35 /boot/initrd.img-6.0.0-0.deb11.6-amd64
-rw-r--r-- 1 root root 68913767 Mar 31 17:35 /boot/initrd.img-6.1.0-0.deb11.5-amd64
-rw-r--r-- 1 root root  7730784 Dec 19 14:14 /boot/vmlinuz-6.0.0-0.deb11.6-amd64
-rw-r--r-- 1 root root  7866720 Mar  5 18:27 /boot/vmlinuz-6.1.0-0.deb11.5-amd64

$ la -clt /boot/initrd* /boot/vmlinuz*
-rw-r--r-- 1 root root 68913767 Mar 31 17:35 /boot/initrd.img-6.1.0-0.deb11.5-amd64
-rw-r--r-- 1 root root  7866720 Mar 31 17:35 /boot/vmlinuz-6.1.0-0.deb11.5-amd64
-rw-r--r-- 1 root root 68062772 Mar 28 22:35 /boot/initrd.img-6.0.0-0.deb11.6-amd64
-rw-r--r-- 1 root root  7730784 Jan  4 10:14 /boot/vmlinuz-6.0.0-0.deb11.6-amd64

#!/usr/bin/perl
   # get Chrome Cache
   # suggestion: save as ~/.getCC; chmod +x; chmod 700

   #  A PERL script to iterate through Chromium/Chrome 'Cache_Data/' dir
   #+ & extract all http-delivered files stored within those data-files

   # 2023-03-21:         Finally found location of URL-length
   #                     (& thus how to find start of content for all files)
   # 2023-03-16: bugfix: Account for Content-Encoding invalidating file-magic
   # 2023-03-12:         Account for multiple http version + 200|203 status
   # 2023-03-08: bugfix: COUNT removed; LEN used instead
   #           +        (FOFF used for BEG, not COUNT)
   #           +         brotli now works
   #           +        (no magic for brotli (a mistake imo))
   # 2023-03-07: bugfix: corrected miss on most magic files (my bad)
   #           +         excluded compound header fields to eliminate wrong values
   #             added $FOFF (diff between HTTP-begin ($END - $LEN) & magic-begin ($BEG))
   #           + (*every* file with both $BEG & $LEN has diff == x34) (h-begin is bigger)
   #           + thus if no magic but LEN then BEG = END - LEN - 52
   #           +      if magic but no LEN then LEN = END - BEG - 52 (yes, this *does* happen)
   # 2023-03-05: bugfix: coded to exclude 711 zero-length files
   #           +         account for multiple-same-value $mime (fixes ~1000 gif + jpg files)
   #           +         added 'Content-Encoding:br' Brotli compression
   #           +        (you may need 'sudo apt install brotli' to view those files)

   use strict;
   use warnings;
   use autodie;
   use experimental qw( switch );

   # Global CONSTANTS
   my $UNBROT= "/usr/bin/brotli -d";                                   # change to your location
   my $DD    = "/bin/dd";                                              # - ditto -
   my $GUNZIP= "/bin/gunzip";                                          # - ditto -
   my $TOUCH = "/usr/bin/touch";                                       # - ditto -
   my $IN    = "/home/alexk/.cache/chromium/Default/Cache/Cache_Data"; # Chromium cache folder
   my $OUT   = "/home/alexk/Personal/ChromeCache/Files/";              # Place to extract files to
   my $FOFF  = 52;                                                     # Offset of HTTP-begin from magic-eof (BEG) + LEN
   my $HTTP  = "HTTP/1.1 200";                                         # '200 OK' not in all files
   my $MEOF  = "\x{d8}\x{41}\x{0d}\x{97}\x{45}\x{6f}\x{fa}\x{f4}";     # Magic End bits (last 8 bytes of every simple cache Entry file data record)
   my $MENT  = "\x{30}\x{5c}\x{72}\x{a7}\x{1b}\x{6d}\x{fb}\x{fc}";     # Magic Start bits (1st 8 bytes of every simple cache Entry file data record)
   my $MURL  = "_dk_";                                                 # Magic Start for URL (url follows within cache Entry file data record)

   # save algorithm:
   # 1) $URL/@URL: find $key_length from header
   # 2) $BEG;$END;$LEN: obtain data start+end (from $key_length + $MEOF)
   # 3) only save HTTP 200 files ($HTTP)
   # 4) $HTTP;$BROTLI;$GZIP;$MIME;$MOD;$TLS: obtain http header fields (from $MEOF + $FOFF)
   # 5) extract section $BEG to $END from $IN file into $OUT dir
   # 6) $MOD: touch file to conform with http header date
   # 7) $BROTLI;$GZIP: decompress gzip/brotli files

   # Stats 2023-03-06:
   # 10978 HTTP 200 from 23594 files in Cache_Data
   #     6 do NOT contain a MIME field
   # 10979 files saved to disk (real	1m23.219s)

   # chromium cache in 2023 is a "simple cache"
   # see https://www.chromium.org/developers/design-documents/network-stack/disk-cache/very-simple-backend/
   # see https://chromium.googlesource.com/chromium/src/+/HEAD/net/disk_cache/simple/simple_entry_format.h
   # see https://github.com/JimmXinu/FanFicFare/blob/main/fanficfare/browsercache/browsercache_simple.py
   # start-of-record magic-marker == 30 5c 72 a7 1b 6d fb fc
   #   end-of-record magic-marker == d8 41 0d 97 45 6f fa f4
   # (data ends immediately before eor)
   # (http header starts 44 bytes after eor, and thus 44+8=52 bytes (\x34) after end-of-data)
   # (eor also ends file; 16 bytes then follow to actual end-of-file)
   # from FFF: (finally found url-length location)
   # cache Entry-file header = struct.Struct('<QLLLL') [little-endian | 8-byte | 4-byte | 4-byte | 4-byte | 4-byte)
   # (magic, version, key_length, key_hash, padding) = shformat.unpack(data)
   # Parse Chrome Cache File; see https://github.com/JimmXinu/FanFicFare/blob/main/fanficfare/browsercache/chromagnon/cacheParse.py

   opendir( my $d, "$IN") or die "Cannot open directory $IN";          # Open cache dir
   my @list 
      = grep { 
         !/^\.\.?$/                                                    # miss /. + /.. files
         && -f "$IN/$_"                                                # is a file (not dir, etc)
	} readdir( $d );
   closedir( $d );
   foreach my $f (@list) {                                             # Iterate through each cached data-file
#     my $f    = "be75a13d44e548da_0";
      # section variables
      my $BEG  = -1;                                                   # Extract begins (bytes)
      my $BROTLI = 0;                                                  # brotli encoding (0/1)
      my $END  = -1;                                                   # Extract ends   (bytes)
      my $GZIP = 0;                                                    # gzip encoding (0/1)
      my $HPOS = -1;                                                   # 'HTTP' string begins (bytes)
      my $HSTA = -1;                                                   # 'HTTP' status string (only interested in '200' or '203')
      my $HVER = '';                                                   # 'HTTP' version string (eg '1.1')
      my $LEN  = -1;                                                   # content-length
      my $MAGIC = '';
      my $MIME = "";                                                   # content-type
      my $MOD  = "";                                                   # last-modified
      my $OFF  = -1;                                                   # Offset of magic from file beginning
      my $TLS  = "";                                                   # TLS==Three Letter Suffix
      my $URL  = "";                                                   # url within cache Entry file
      my @URL  = "";                                                   # same url as an array
      my $UPOS = "";                                                   # position of url start in Entry file
      open my $fh, '<:raw', "$IN/$f" or die "Cannot open file $IN/$f";

      # 1 Obtain url length then url
      # $key_length starts from byte 24 (\x18), normally begins with an 8-byte string '1/0/_dk_', then stretches to the end of the URL sequence
      # the std 8-byte string indicates that two streams (1 + 0) are included within the file
      # the request-url sequence is 2 x (normally-identical) base urls then the full request url, each separated by a single space
      # data supplied to request url begins immediately after the url, and ends immediately before the $MEOF magic-marker
      # http response headers begin 44 bytes after the end of $MEOF, starting with HTTP Status string at $HPOS
      # none of the "std" response headers can be *expected* to exist, though most do
      # all sorts of stuff exists after initial response header bundle, many of which I do not understand
      #+ including content-servers such as amazon, certificates, proxy-servers, others
      # this second stream (for std 2-stream files) ends with another $MEOF 16 bytes (\x10) before eof
      # eg1: "1/0/_dk_https://bbc.co.uk https://bbc.co.uk https://static.files.bbci.co.uk/core/bundle-service-bar.003e5ecd332a5558802c.js"
      #  \x18 ^       ^ $UPOS (=32 =\x20)                ($key_length =123 =\x7b; note: 24+123 =147 =\x93)                         \x93 ^
      # eg2: "d8410d97 456ffaf4 01000000 24be2bf3 8d010000000000005814000003654702 acd8b17d9a552f00b8a4b27d9a552f00 40040000 HTTP/1.1 200"
      # \x220 ^           \x228 ^           \x230 ^                          \x240 ^                          \x250 ^        ^ $HPOS (=596 =\x254)
      my $bytes_read = read $fh, my $bytes, 24;
      die "Got $bytes_read but expected 24" unless $bytes_read == 24;
      my ($magic, $version, $key_length, $key_hash, $padding) = unpack 'a8 a4 a4 a4 a4', $bytes;
      if( unpack('Q', $magic ) ne unpack('Q', $MENT )) {
         $magic = unpack('H16', $magic );
         $MENT = unpack('H16', $MENT );
         die "'$IN/$f' is not a cache entry file, wrong magic number\n (got '$magic' not '$MENT')";
      }
      seek( $fh, 0, 0 );                                               # return to start of file
      read( $fh, my $cache_buffer, -s "$IN/$f" );                      # put whole file in $cache_buffer
      close( $fh ) or die "could not close $IN/$f";
      # Obtain url
      if( $cache_buffer =~ /$MURL/ ) {
         $UPOS = $-[0] + 4;                                            # url begins immediately *after* marker string
         $key_length=unpack('L', $key_length );
         $key_hash  =unpack('H16', $key_hash );
         $URL  = substr( $cache_buffer, $UPOS, $key_length - ($UPOS - 24));
         @URL  = split(' ', $URL );
      }

      # 2 Obtain data start+end
      $BEG = $key_length + 24;
      $END = index( $cache_buffer, "$MEOF", $BEG);
      if( $END < 1 ) {
         print STDERR "'$IN/$f': error finding end of data at $0 line:". __LINE__ ."\n";
         next;                                                         # immediately skips up to foreach() + increments $f
      } else {
         if( $BEG == $END ) {                                          # yes, some pages have Content-Length:0
            $LEN = -1;
         } else {
            $LEN = $END - $BEG;
         }
      }

      # 3 Only extract from HTTP 200|203
      if( $cache_buffer =~ /\x{00}\x{00}HTTP\/(\d.\d*)\s(200|203)/i ) {
         $HPOS = $-[0] + 2;
         if( $HPOS != $END + $FOFF) {
            print STDERR "'$IN/$f':  error finding start of http at $0 line:". __LINE__ ."\n";
            next;                                                      # immediately skips up to foreach() + increments $f
         }
         $HVER = "$1";                                                 # http version; always HTTP/1.1 for me
         $HSTA = "$2";                                                 # http status; we are only interested in 200 or 203
         $HTTP = "HTTP/$HVER $HSTA";
         # 4 Obtain http header fields
         if( $LEN > 0 ) {                                              # yes, some pages have Content-Length:0
            if( $cache_buffer =~ /\x00Content-Encoding:\s*br/i )   { $BROTLI = 1; }
            if( $cache_buffer =~ /\x00Content-Encoding:\s*gzip/i ) { $GZIP   = 1; }
            if( $cache_buffer =~ /\x00Content-Length:\s*(\d+)/i )  {
               if( $1 != $LEN ) {
                  print STDERR "'$IN/$f': data-length \$LEN=$LEN differs from http Content-Length=$1 at $0 line:". __LINE__ ."\n";
               }
               if( !$1 ) { print STDERR "'$IN/$f': len=0 at $0 line:". __LINE__ ."\n"; }
            }
            if( $cache_buffer =~ /\x00Last-Modified:\s*([ A-Za-z0-9,:]+)/i ) {
               $MOD = $1;                                              # some web servers ignore case + introduce spaces!
            } else {
               if( $cache_buffer =~ /\x00Date:\s*([ A-Za-z0-9,:]+)/i ) {# did page did not want to be cached? (Chromium did it anyway!)
                  $MOD = $1;                                           # (all pages should have a date (or a Date))
               }
            }
            if( $cache_buffer =~ /\x00Content-Type:\s*([a-z-]+\/[a-z0-9.+-]+)/i ) {
               $MIME = $1;
            } # variable $1 NOT reset on failed match (v stupid)
         } else { next; } # if( $LEN > 0 )

         # easy to mixup mime/media-types & encoding (compression schemes) here
         # Content-Type     == mime-type          refers to the type of file that is being transferred
         # Content-Encoding == compression scheme refers to the type of compression used during transfer
         # so, a text file (js txt xml, etc) with gzip magic will be a gzipped-textfile (eg file.xml.gz)
         # gzip encoding (+ brotli) are only support; deflate no support, compress not even mentioned
         # see https://httpd.apache.org/docs/current/mod/mod_deflate.html
         # see https://www.iana.org/assignments/media-types/media-types.xhtml
         given( $MIME ) {
            when ('application/font-woff' )  { $MAGIC = 'wOFF';                           $OFF = 0; $TLS = 'woff'; }
            when ('application/font-woff2')  { $MAGIC = 'wOF2';                           $OFF = 0; $TLS = 'woff2'; }
            when ('application/javascript')  { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }   # magic for gzip encoding
            when ('application/json')        { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'json'; } # magic for gzip encoding
            when ('application/manifest+json'){ $MAGIC = "\x{1f}\x{8b}\x{08}";            $OFF = 0; $TLS = 'json'; } # magic for gzip encoding
            when ('application/x-javascript'){ $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }   # magic for gzip encoding
            when ('application/xml')         { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'xml'; }  # magic for gzip encoding
            when ('binary/octet-stream')     { $MAGIC = "GIF89a";                         $OFF = 0; $TLS = 'gif'; }
            when ('font/ttf')                { $MAGIC = "\x{00}\x{01}\x{00}\x{00}\x{00}"; $OFF = 0; $TLS = 'ttf'; }
            when ('font/woff')               { $MAGIC = 'wOFF';                           $OFF = 0; $TLS = 'woff'; }
            when ('font/woff2')              { $MAGIC = 'wOF2';                           $OFF = 0; $TLS = 'woff2'; }
            when ('image/gif')               { $MAGIC = 'GIF87a';                         $OFF = 0; $TLS = 'gif'; }
#           when ('image/gif')               { $MAGIC = 'GIF89a';                         $OFF = 0; $TLS = 'gif'; }
            when ('image/jpeg')              { $MAGIC = 'JFIF';                           $OFF = 6; $TLS = 'jpg'; }
#           when ('image/jpeg')              { $MAGIC = 'Exif';                           $OFF = 6; $TLS = 'jpeg'; }
#           when ('image/jpeg')              { $MAGIC = "\x{ff}\x{d8}\x{ff}\x{e0}";       $OFF = 6; $TLS = 'jpg'; }
            when ('image/png')               { $MAGIC = "\x{89}PNG";                      $OFF = 0; $TLS = 'png'; }
            when ('image/svg+xml')           { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'svg'; }  # magic for gzip encoding
            when ('image/vnd.microsoft.icon'){ $MAGIC = "\x{00}\x{00}\x{01}\x{00}";       $OFF = 0; $TLS = 'ico'; }
            when ('image/webp')              { $MAGIC = 'RIFF';                           $OFF = 0; $TLS = 'webp'; }
            when ('image/x-icon')            { $MAGIC = "\x{00}\x{00}\x{01}\x{00}";       $OFF = 0; $TLS = 'ico'; }
            when ('text/css')                { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'css'; }  # magic for gzip encoding
            when ('text/fragment+html')      { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'htm'; }  # magic for gzip encoding
            when ('text/html')               { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'html'; } # magic for gzip encoding
            when ('text/javascript')         { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }   # magic for gzip encoding
            when ('text/plain')              { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'txt'; }  # magic for gzip encoding
            when ('text/xml')                { $MAGIC = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'xml'; }  # magic for gzip encoding
            when ('video/mp4')               { $MAGIC = 'ftypisom';                       $OFF = 4; $TLS = 'mp4'; }  # most unlikely
            default                          { $MAGIC = '';                               $OFF = 0; $TLS = ''; }
         }
         # gzip encoding overrides file magic (is earlier in file-stream)
         # brotli encoding overrides file magic (there is none)
         if( $GZIP ) { $MAGIC = "\x{1f}\x{8b}\x{08}"; $OFF = 0; } elsif( $BROTLI ) { $MAGIC = ""; $OFF = 0; }
         if( $MAGIC ) {
            if( $MAGIC eq 'GIF87a') {                                  # account for gif + jpeg multiple $MAGIC
               if( ! index( $cache_buffer, "$MAGIC" )) {
                  $MAGIC = 'GIF89a';
               }
            } elsif( $MAGIC eq 'JFIF') {
               if( ! index( $cache_buffer, "$MAGIC" )) {
                  $MAGIC = 'Exif';
                  $TLS   = 'jpeg';
                  if( ! index( $cache_buffer, "$MAGIC" )) {
                     $MAGIC = "\x{ff}\x{d8}\x{ff}\x{e0}";
                     $TLS   = 'jpg';
                  }
               }
            }
         }
         # suffixes (holy m$)
         if( $TLS ) {
            $TLS = ".$TLS";
            if( $GZIP || $BROTLI ) {                                   # compression-encoding
               if( $GZIP ) { $TLS = "$TLS.gz"; } else { $TLS = "$TLS.br"; }
            }
         }
         # 5 print the files out
         if( $BEG > -1 && $LEN > -1 ) {
            `$DD if="$IN/$f" of="$OUT/$f$TLS" skip=$BEG count=$LEN iflag=skip_bytes,count_bytes status=none`;
            # 6 set the date to last-modified
            if( $MOD ) { `$TOUCH "$OUT/$f$TLS" -d "$MOD"`; }
            # 7 decompress if necessary
            if( $GZIP || $BROTLI ) {                                   # compression-encoding
               if( $GZIP ) {                                           # decompressed; .gz/.br suffix removed
                  `$GUNZIP "$OUT/$f$TLS"`;                             # original file removed; date retained
               } else {
                  `$UNBROT -j "$OUT/$f$TLS"`;
               }
            }
         } # lots of Content-Length:0 files
#         print "$MIME; $URL[0]; $f; \$key_length=$key_length; \$key_hash=$key_hash; \$BEG=$BEG; \$END=$END; \$LEN=$LEN; \$TLS=$TLS \n";
      } # if( $cache_buffer =~ /\x{00}\x{00}HTTP\/(\d.\d*)\s(200|203)/i ) # other pages mostly HTTP 204 No Content
   }

$ ~/Personal/.getCC
image/webp: 000420fedcafe6ff_0; $TLS=.webp; $HPOS=5185; $END=5185; $HVER=1.1; $HSTA=200; $HTTP=HTTP/1.1 200; $MOD=Fri, 03 Mar 2023 20:27:56 GMT; 
$ cd ~/Personal/ChromeCache/Files
$ time ~/Personal/.getCC

real	1m28.431s
user	0m53.738s
sys	0m34.723s

00001430  fc 9b 54 2f 00 a4 ec 1b  fc 9b 54 2f 00 57 02 00  |..T/......T/.W..|
00001440  00 48 54 54 50 2f 31 2e  31 20 32 30 30 00 61 63  |.HTTP/1.1 200.ac|

00002800  02 72 ab 33 c9 16 55 2f  00 8d 9c 35 c9 16 55 2f  |.r.3..U/...5..U/|
00002810  00 56 02 00 00 48 54 54  50 2f 31 2e 31 20 32 30  |.V...HTTP/1.1 20|

00003740  ea 4c 55 2f 00 48 7c d5  ea 4c 55 2f 00 55 02 00  |.LU/.H|..LU/.U..|
00003750  00 48 54 54 50 2f 31 2e  31 20 32 30 30 00 61 63  |.HTTP/1.1 200.ac|

#!/usr/bin/perl
   # get Chrome Cache
   # suggestion: save as ~/.getCC; chmod +x; chmod 700

   #  A PERL script to iterate through Chromium/Chrome 'Cache_Data/' dir
   #+ & extract all http-delivered files stored within those data-files

   # 2023-03-12:         Account for multiple http version + 200|203 status
   # 2023-03-08: bugfix: COUNT removed; LEN used instead
   #           +        (F_OFF used for BEG, not COUNT)
   #           +         brotli now works
   #           +        (no magic for brotli (a mistake imo))
   # 2023-03-07: bugfix: corrected miss on most magic files (my bad)
   #           +         excluded compound header fields to eliminate wrong values
   #             added $F_OFF (diff between HTTP-begin ($END - $LEN) & magic-begin ($BEG))
   #           + (*every* file with both $BEG & $LEN has diff == x34) (h-begin is bigger)
   #           + thus if no magic but LEN then BEG = END - LEN - 52
   #           +      if magic but no LEN then LEN = END - BEG - 52 (yes, this *does* happen)
   # 2023-03-05: bugfix: coded to exclude 711 zero-length files
   #           +         account for multiple-same-value $mime (fixes ~1000 gif + jpg files)
   #           +         added 'Content-Encoding:br' Brotli compression
   #           +        (you may need 'sudo apt install brotli' to view those files)

   use strict;
   use warnings;
   use autodie;
   use experimental qw( switch );

   # save algorithm:
   # 1) only save HTTP 200 files ($END)
   # 2) try first to set file beginning ($BEG) from magic bytes
   # 3) if (2) fails, set $BEG from $LEN; if no length, then ignore file
   # 4) extract section $BEG to $END from $IN file into $OUT dir
   # 5) touch file to conform with http header date

   # Stats 2023-03-06:
   # 10978 HTTP 200 from 23594 files in Cache_Data
   #     6 do NOT contain a MIME field
   # 10979 files saved to disk (real	1m23.219s)

   # Global CONSTANTS
   my $IN   = "/home/alexk/.cache/chromium/Default/Cache/Cache_Data/"; # Chromium cache folder.
   my $OUT  = "/home/alexk/Personal/ChromeCache/Files/";               # Place for extracted files
   my $HTTP = "HTTP/1.1 200";                                          # '200 OK' not in all files
   my $F_OFF= 52;                                                      # Offset of HTTP-begin from magic-begin (BEG) + LEN

   opendir( my $d, "$IN") or die "Cannot open directory $IN: $!\n";    # Open cache dir
   my @list 
      = grep { 
         !/^\.\.?$/                                                    # miss /. + /.. files
         && -f "$IN/$_"                                                # is a file (not dir, etc)
	} readdir( $d );
   closedir( $d );
   foreach my $f (@list) {                                             # Iterate through each cached data-file
#     my $f    = "000420fedcafe6ff_0";
      # section variables
      my $BEG  = -1;                                                   # Extract begins (bytes)
      my $BROTLI = 0;                                                  # brotli encoding (0/1)
      my $END  = -1;                                                   # Extract ends   (bytes)
      my $GZIP = 0;                                                    # gzip encoding (0/1)
      my $HPOS = -1;                                                   # 'HTTP' string begins (bytes)
      my $HSTA = -1;                                                   # 'HTTP' status string (only interested in '200' or '203')
      my $HVER = '';                                                   # 'HTTP' version string (eg '1.1')
      my $magic = '';
      my $MIME = "";                                                   # content-type
      my $MOD  = "";                                                   # last-modified
      my $OFF  = -1;                                                   # Offset of magic from file beginning
      my $TLS  = "";                                                   # TLS==Three Letter Suffix
      my $LEN  = -1;                                                   # content-length
      open my $fhi, '<:raw', "$IN/$f" or die $!;
      read( $fhi, my $cache_buffer, -s "$IN/$f" );
      close( $fhi ) or die "could not close $IN/$f: $!";
      if( $cache_buffer =~ /\x{00}\x{00}HTTP\/(\d.\d*)\s(200|203)/i ) {
         $HPOS = $-[0] + 2;
         $HVER = "$1";
         $HSTA = "$2";
         $HTTP = "HTTP/$HVER $HSTA";
      }
      $END     = index( $cache_buffer, "$HTTP", $HPOS);                # Check for presence of HTTP 200|203 header (paranoia coding)
      if( $END > -1 ) {                                                #+(and therefore std header fields for successful access)
         if( $cache_buffer =~ /\x00Content-Encoding:\s*br/i )   { $BROTLI = 1; }
         if( $cache_buffer =~ /\x00Content-Encoding:\s*gzip/i ) { $GZIP   = 1; }
         if( $cache_buffer =~ /\x00Content-Length:\s*(\d+)/i )  {
            $LEN  = $1;
            if( !$LEN ) { $LEN  = -1; }                                # yes, some pages have Content-Length:0
         }
         if( $cache_buffer =~ /\x00Last-Modified:\s*([ A-Za-z0-9,:]+)/i ) {
            $MOD = $1;                                                 # some web servers ignore case + introduce spaces!
         } else {
            if( $cache_buffer =~ /\x00Date:\s*([ A-Za-z0-9,:]+)/i ) {  # did page did not want to be cached? (Chromium did it anyway!)
               $MOD = $1;                                              # (all pages should have a date (or a Date))
            }
         }
         if( $cache_buffer =~ /\x00Content-Type:\s*([a-z-]+\/[a-z0-9.+-]+)/i ) {
            $MIME = $1;
         } # variable $1 NOT reset on failed match (v stupid)
         given( $MIME ) {
            when ('application/font-woff' )  { $magic = 'wOFF';                           $OFF = 0; $TLS = 'woff'; }
            when ('application/font-woff2')  { $magic = 'wOF2';                           $OFF = 0; $TLS = 'woff2'; }
            when ('application/javascript')  { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }    # magic for gzip encoding
            when ('application/json')        { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'json'; }
            when ('application/x-javascript'){ $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }
            when ('application/xml')         { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }
            when ('binary/octet-stream')     { $magic = "GIF89a";                         $OFF = 0; $TLS = 'gif'; }
            when ('font/ttf')                { $magic = "\x{00}\x{01}\x{00}\x{00}\x{00}"; $OFF = 0; $TLS = 'ttf'; }
            when ('font/woff')               { $magic = 'wOFF';                           $OFF = 0; $TLS = 'woff'; }
            when ('font/woff2')              { $magic = 'wOF2';                           $OFF = 0; $TLS = 'woff2'; }
            when ('image/gif')               { $magic = 'GIF87a';                         $OFF = 0; $TLS = 'gif'; }
#           when ('image/gif')               { $magic = 'GIF89a';                         $OFF = 0; $TLS = 'gif'; }
            when ('image/jpeg')              { $magic = 'JFIF';                           $OFF = 6; $TLS = 'jpg'; }
#           when ('image/jpeg')              { $magic = 'Exif';                           $OFF = 6; $TLS = 'jpeg'; }
#           when ('image/jpeg')              { $magic = "\x{ff}\x{d8}\x{ff}\x{e0}";       $OFF = 6; $TLS = 'jpg'; }
            when ('image/png')               { $magic = "\x{89}PNG";                      $OFF = 0; $TLS = 'png'; }
            when ('image/svg+xml')           { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'svg'; }
            when ('image/vnd.microsoft.icon'){ $magic = "\x{00}\x{00}\x{01}\x{00}";       $OFF = 0; $TLS = 'ico'; }
            when ('image/webp')              { $magic = 'RIFF';                           $OFF = 0; $TLS = 'webp'; }
            when ('text/css')                { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'css'; }
            when ('text/fragment+html')      { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'htm'; }
            when ('text/html')               { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'html'; }
            when ('text/javascript')         { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }
            when ('text/plain')              { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'txt'; }
            when ('video/mp4')               { $magic = 'ftypisom';                       $OFF = 4; $TLS = 'mp4'; }   # most unlikely
            default                          { $magic = '';                               $OFF = 0; $TLS = ''; }
         }
         if( $magic ) {
            if( $magic eq 'GIF87a') {                                  # account for gif + jpeg multiple $magic
               $BEG = index( $cache_buffer, "$magic" );
               if( $BEG < 0 ) {
                  $magic = 'GIF89a';
                  $BEG   = index( $cache_buffer, "$magic" );
               }
            } elsif( $magic eq 'JFIF') {
               $BEG = index( $cache_buffer, "$magic" );
               if( $BEG < 0 ) {
                  $magic = 'Exif';
                  $TLS   = 'jpeg';
                  $BEG   = index( $cache_buffer, "$magic" );
                  if( $BEG < 0 ) {
                     $magic = "\x{ff}\x{d8}\x{ff}\x{e0}";
                     $TLS   = 'jpg';
                     $BEG   = index( $cache_buffer, "$magic" );
                  }
               }
            }
            $BEG   = index( $cache_buffer, "$magic" );
         }
#         # trying to decode where each file begins (determine common offsets)
#         if( $LEN < 1  &&  $BEG > -1 )  { }
#         if( $BEG > -1  &&  $LEN > -1 ) {
#            # at this point $BEG - $OFF == start of magic
#            #               $END        == start of $HTTP
#            #               $LEN        == length of content from header
#            my $mbeg = $BEG - $OFF;  my $mhex = sprintf("0x%X", $mbeg);
#            my $hbeg = $END - $LEN;  my $hhex = sprintf("0x%X", $hbeg);
#            my $diff = $hbeg - $mbeg;
#            my $dhex = sprintf("0x%X", $diff);
#            print "$MIME: $f; \$END/\$LEN=$END / $LEN; \$mbeg=$mbeg / $mhex; \$hbeg=$hbeg / $hhex; \$diff=$diff / $dhex; \n";
#        }
         if( $BEG > -1 ) {
            $BEG  -= $OFF;
            if( $LEN < 1 ) { $LEN = $END - $BEG - $F_OFF; }            # v rare, but happens
         } elsif( $LEN > -1 ) { $BEG = $END - $LEN - $F_OFF; }         # no magic (text, xml + brotli files)
         # suffixes (holy m$)
         if( $TLS ) {
            $TLS = ".$TLS";
            if( $GZIP || $BROTLI ) {                                   # account for different compression-encodings
               if( $GZIP ) { $TLS = "$TLS.gz"; } else { $TLS = "$TLS.br"; }
            }
         }
         # print the files out
         if( $BEG > -1 && $LEN > -1 ) {
            `dd if="$IN/$f" of="$OUT/$f$TLS" skip=$BEG count=$LEN iflag=skip_bytes,count_bytes status=none`;
            if( $MOD ) { `touch "$OUT/$f$TLS" -d "$MOD"`; }
#           print "$MIME: $f; \$TLS=$TLS; \$HPOS=$HPOS; \$END=$END; \$HVER=$HVER; \$HSTA=$HSTA; \$HTTP=$HTTP; \$MOD=$MOD; \n";
         }
      } # if( $END > -1 )                                              # other pages are most likely to be HTTP 204 No Content
   }

$ la ~/.cache/chromium/Default/Cache/Cache_Data/fff822c2bb27d828_0
-rw------- 1 alexk alexk 4389 Feb 24 02:31 /home/alexk/.cache/chromium/Default/Cache/Cache_Data/fff822c2bb27d828_0
$ la ~/Personal/ChromeCache/Files/fff822c2bb27d828_0.gif
-rw-r--r-- 1 alexk alexk 43 Feb 24 02:31 /home/alexk/Personal/ChromeCache/Files/fff822c2bb27d828_0.gif
$ hexdump ~/.cache/chromium/Default/Cache/Cache_Data/fff822c2bb27d828_0 -C | head -31
00000000  30 5c 72 a7 1b 6d fb fc  05 00 00 00 b2 00 00 00  |0\r..m..........|
00000010  23 84 68 3b 00 00 00 00  31 2f 30 2f 5f 64 6b 5f  |#.h;....1/0/_dk_|
00000020  68 74 74 70 73 3a 2f 2f  61 6d 61 7a 6f 6e 2e 63  |https://amazon.c|
00000030  6f 2e 75 6b 20 68 74 74  70 73 3a 2f 2f 61 6d 61  |o.uk https://ama|
00000040  7a 6f 6e 2e 63 6f 2e 75  6b 20 68 74 74 70 73 3a  |zon.co.uk https:|
00000050  2f 2f 61 61 78 2d 65 75  2e 61 6d 61 7a 6f 6e 2e  |//aax-eu.amazon.|
00000060  63 6f 2e 75 6b 2f 65 2f  6c 6f 69 2f 69 6d 70 3f  |co.uk/e/loi/imp?|
00000070  62 3d 4a 48 4f 6b 41 4c  63 55 4e 66 59 35 4f 61  |b=JHOkALcUNfY5Oa|
00000080  54 5f 5a 31 61 39 4c 32  67 41 41 41 47 47 67 55  |T_Z1a9L2gAAAGGgU|
00000090  4b 4d 77 67 4d 41 41 41  48 32 41 51 42 4f 4c 30  |KMwgMAAAH2AQBOL0|
000000a0  45 67 49 43 41 67 49 43  41 67 49 43 41 67 49 43  |EgICAgICAgICAgIC|
000000b0  42 4f 4c 30 45 67 49 43  41 67 49 43 41 67 49 43  |BOL0EgICAgICAgIC|
000000c0  41 67 49 43 41 2d 55 71  38 45 47 49 46 38 39 61  |AgICA-Uq8EGIF89a|
000000d0  01 00 01 00 f0 00 00 00  00 00 00 00 00 21 f9 04  |.............!..|
000000e0  01 00 00 00 00 2c 00 00  00 00 01 00 01 00 00 02  |.....,..........|
000000f0  02 44 01 00 3b d8 41 0d  97 45 6f fa f4 01 00 00  |.D..;.A..Eo.....|
00000100  00 ab bd 8a cb 2b 00 00  00 00 00 00 00 dc 0f 00  |.....+..........|
00000110  00 03 0d 45 02 86 fc 8d  34 ff 53 2f 00 e7 d9 8e  |...E....4.S/....|
00000120  34 ff 53 2f 00 bd 00 00  00 48 54 54 50 2f 31 2e  |4.S/.....HTTP/1.|
00000130  31 20 32 30 30 20 4f 4b  00 53 65 72 76 65 72 3a  |1 200 OK.Server:|
00000140  20 53 65 72 76 65 72 00  44 61 74 65 3a 20 46 72  | Server.Date: Fr|
00000150  69 2c 20 32 34 20 46 65  62 20 32 30 32 33 20 30  |i, 24 Feb 2023 0|
00000160  32 3a 33 31 3a 30 38 20  47 4d 54 00 43 6f 6e 74  |2:31:08 GMT.Cont|
00000170  65 6e 74 2d 54 79 70 65  3a 20 69 6d 61 67 65 2f  |ent-Type: image/|
00000180  67 69 66 00 43 6f 6e 74  65 6e 74 2d 4c 65 6e 67  |gif.Content-Leng|
00000190  74 68 3a 20 34 33 00 78  2d 61 6d 7a 2d 72 69 64  |th: 43.x-amz-rid|
000001a0  3a 20 42 37 35 4d 32 37  57 4e 38 38 32 54 59 4d  |: B75M27WN882TYM|
000001b0  45 56 32 4e 46 48 00 56  61 72 79 3a 20 43 6f 6e  |EV2NFH.Vary: Con|
000001c0  74 65 6e 74 2d 54 79 70  65 2c 41 63 63 65 70 74  |tent-Type,Accept|
000001d0  2d 45 6e 63 6f 64 69 6e  67 2c 55 73 65 72 2d 41  |-Encoding,User-A|
000001e0  67 65 6e 74 00 00 00 00  00 03 00 00 00 0d 07 00  |gent............|
$ hexdump fff822c2bb27d828_0.gif -C
00000000  47 49 46 38 39 61 01 00  01 00 f0 00 00 00 00 00  |GIF89a..........|
00000010  00 00 00 21 f9 04 01 00  00 00 00 2c 00 00 00 00  |...!.......,....|
00000020  01 00 01 00 00 02 02 44  01 00 3b                 |.......D..;|
0000002b

# make less more friendly for non-text input files, see lesspipe(1)
[ -x /usr/bin/lesspipe ] && eval "$(SHELL=/bin/sh lesspipe)"

#!/bin/sh
# ~/.lessfilter
# 2023-03-11 add brotli to all other encodings for less

case "$1" in
   *.br)
      brotli -dc "$1"
      ;;
   *)
      # We don't handle this format.
      exit 1
esac

# No further processing by lesspipe necessary
exit 0

#!/usr/bin/perl
   # get Chrome Cache
   # suggestion: save as ~/.getCC; chmod +x; chmod 700

   # A PERL script to iterate through the Chromium/Chrome 'Cache_Data/'
   #+extract all http-delivered files stored within those data-files

   # 2023-03-08: bugfix: COUNT removed; LEN used instead
   #           +        (F_OFF used for BEG, not COUNT)
   #           +         brotli now works
   #           +        (no magic for brotli (a mistake imo))
   # 2023-03-07: bugfix: corrected miss on most magic files (my bad)
   #           +         excluded compound header fields to eliminate wrong values
   #             added $F_OFF (diff between HTTP-begin ($END - $LEN) & magic-begin ($BEG))
   #           + (*every* file with both $BEG & $LEN has diff == x34) (h-begin is bigger)
   #           + thus if no magic but LEN then BEG = END - LEN - 52
   #           +      if magic but no LEN then LEN = END - BEG - 52 (yes, this *does* happen)
   # 2023-03-05: bugfix: coded to exclude 711 zero-length files
   #           +         account for multiple-same-value $mime (fixes ~1000 gif + jpg files)
   #           +         added 'Content-Encoding:br' Brotli compression
   #           +        (you may need 'sudo apt install brotli' to view those files)

   use strict;
   use warnings;
   use autodie;
   use experimental qw( switch );

   # save algorithm:
   # 1) only save HTTP 200 files ($END)
   # 2) try first to set file beginning ($BEG) from magic bytes
   # 3) if (2) fails, set $BEG from $LEN; if no length, then ignore file
   # 4) extract section $BEG to $END from $IN file into $OUT dir
   # 5) touch file to conform with http header date

   # Stats 2023-03-06:
   # 10978 HTTP 200 from 23594 files in Cache_Data
   #     6 do NOT contain a MIME field
   # 10979 files saved to disk (real	1m23.219s)

   # Global CONSTANTS
   my $IN   = "/home/alexk/.cache/chromium/Default/Cache/Cache_Data/"; # Chromium cache folder.
   my $OUT  = "/home/alexk/Personal/ChromeCache/Files/";               # Place for extracted files
   my $HTTP = "HTTP/1.1 200";                                          # '200 OK' not in all files
   my $F_OFF= 52;                                                      # Offset of HTTP-begin from magic-begin (BEG) + LEN

   opendir( my $d, "$IN") or die "Cannot open directory $IN: $!\n";    # Open cache dir
   my @list 
      = grep { 
         !/^\.\.?$/                                                    # miss /. + /.. files
         && -f "$IN/$_"                                                # is a file (not dir, etc)
	} readdir( $d );
   closedir( $d );
   foreach my $f (@list) {                                             # Iterate through each cached data-file
#     my $f    = "0f0ce6df8548452e_0";
      # section variables
      my $BEG  = -1;                                                   # Extract begins (bytes)
      my $BROTLI = 0;                                                  # brotli encoding (0/1)
      my $END  = -1;                                                   # Extract ends   (bytes)
      my $GZIP = 0;                                                    # gzip encoding (0/1)
      my $magic = '';
      my $MIME = "";                                                   # content-type
      my $MOD  = "";                                                   # last-modified
      my $OFF  = -1;                                                   # Offset of magic from file beginning
      my $TLS  = "";                                                   # TLS==Three Letter Suffix
      my $LEN  = -1;                                                   # content-length
      open my $fhi, '<:raw', "$IN/$f" or die $!;
      read( $fhi, my $cache_buffer, -s "$IN/$f" );
      close( $fhi ) or die "could not close $IN/$f: $!";
      $END     = index( $cache_buffer, "$HTTP");                       # Check for presence of HTTP 200 OK header
      if( $END > -1 ) {                                                #+(and therefore std header fields)
         if( $cache_buffer =~ /\x00Content-Encoding:\s*br/i )   { $BROTLI = 1; }
         if( $cache_buffer =~ /\x00Content-Encoding:\s*gzip/i ) { $GZIP   = 1; }
         if( $cache_buffer =~ /\x00Content-Length:\s*(\d+)/i )  {
            $LEN  = $1;
            if( !$LEN ) { $LEN  = -1; }                                # yes, some pages have Content-Length:0
         }
         if( $cache_buffer =~ /\x00Last-Modified:\s*([ A-Za-z0-9,:]+)/i ) {
            $MOD = $1;                                                 # some web servers ignore case + introduce spaces!
         } else {
            if( $cache_buffer =~ /\x00Date:\s*([ A-Za-z0-9,:]+)/i ) {  # did page did not want to be cached? (Chromium did it anyway!)
               $MOD = $1;                                              # (all pages should have a date (or a Date))
            }
         }
         if( $cache_buffer =~ /\x00Content-Type:\s*([a-z-]+\/[a-z0-9.+-]+)/i ) {
            $MIME = $1;
         } # variable $1 NOT reset on failed match (v stupid)
         given( $MIME ) {
            when ('application/font-woff' )  { $magic = 'wOFF';                           $OFF = 0; $TLS = 'woff'; }
            when ('application/font-woff2')  { $magic = 'wOF2';                           $OFF = 0; $TLS = 'woff2'; }
            when ('application/javascript')  { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }    # magic for gzip encoding
            when ('application/json')        { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'json'; }
            when ('application/x-javascript'){ $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }
            when ('application/xml')         { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }
            when ('binary/octet-stream')     { $magic = "GIF89a";                         $OFF = 0; $TLS = 'gif'; }
            when ('font/ttf')                { $magic = "\x{00}\x{01}\x{00}\x{00}\x{00}"; $OFF = 0; $TLS = 'ttf'; }
            when ('font/woff')               { $magic = 'wOFF';                           $OFF = 0; $TLS = 'woff'; }
            when ('font/woff2')              { $magic = 'wOF2';                           $OFF = 0; $TLS = 'woff2'; }
            when ('image/gif')               { $magic = 'GIF87a';                         $OFF = 0; $TLS = 'gif'; }
#           when ('image/gif')               { $magic = 'GIF89a';                         $OFF = 0; $TLS = 'gif'; }
            when ('image/jpeg')              { $magic = 'JFIF';                           $OFF = 6; $TLS = 'jpg'; }
#           when ('image/jpeg')              { $magic = 'Exif';                           $OFF = 6; $TLS = 'jpeg'; }
#           when ('image/jpeg')              { $magic = "\x{ff}\x{d8}\x{ff}\x{e0}";       $OFF = 6; $TLS = 'jpg'; }
            when ('image/png')               { $magic = "\x{89}PNG";                      $OFF = 0; $TLS = 'png'; }
            when ('image/svg+xml')           { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'svg'; }
            when ('image/vnd.microsoft.icon'){ $magic = "\x{00}\x{00}\x{01}\x{00}";       $OFF = 0; $TLS = 'ico'; }
            when ('image/webp')              { $magic = 'RIFF';                           $OFF = 0; $TLS = 'webp'; }
            when ('text/css')                { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'css'; }
            when ('text/fragment+html')      { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'htm'; }
            when ('text/html')               { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'html'; }
            when ('text/javascript')         { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'js'; }
            when ('text/plain')              { $magic = "\x{1f}\x{8b}\x{08}";             $OFF = 0; $TLS = 'txt'; }
            when ('video/mp4')               { $magic = 'ftypisom';                       $OFF = 4; $TLS = 'mp4'; }   # most unlikely
            default                          { $magic = '';                               $OFF = 0; $TLS = ''; }
         }
         if( $magic ) {
            if( $magic eq 'GIF87a') {                                  # account for gif + jpeg multiple $magic
               $BEG = index( $cache_buffer, "$magic" );
               if( $BEG < 0 ) {
                  $magic = 'GIF89a';
                  $BEG   = index( $cache_buffer, "$magic" );
               }
            } elsif( $magic eq 'JFIF') {
               $BEG = index( $cache_buffer, "$magic" );
               if( $BEG < 0 ) {
                  $magic = 'Exif';
                  $TLS   = 'jpeg';
                  $BEG   = index( $cache_buffer, "$magic" );
                  if( $BEG < 0 ) {
                     $magic = "\x{ff}\x{d8}\x{ff}\x{e0}";
                     $TLS   = 'jpg';
                     $BEG   = index( $cache_buffer, "$magic" );
                  }
               }
            }
            $BEG   = index( $cache_buffer, "$magic" );
         }
#         # trying to decode where each file begins (determine common offsets)
#         if( $LEN < 1  &&  $BEG > -1 )  { }
#         if( $BEG > -1  &&  $LEN > -1 ) {
#            # at this point $BEG - $OFF == start of magic
#            #               $END        == start of $HTTP
#            #               $LEN        == length of content from header
#            my $mbeg = $BEG - $OFF;  my $mhex = sprintf("0x%X", $mbeg);
#            my $hbeg = $END - $LEN;  my $hhex = sprintf("0x%X", $hbeg);
#            my $diff = $hbeg - $mbeg;
#            my $dhex = sprintf("0x%X", $diff);
#            print "$MIME: $f; \$END/\$LEN=$END / $LEN; \$mbeg=$mbeg / $mhex; \$hbeg=$hbeg / $hhex; \$diff=$diff / $dhex; \n";
#        }
         if( $BEG > -1 ) {
            $BEG  -= $OFF;
            if( $LEN < 1 ) { $LEN = $END - $BEG - $F_OFF; }            # v rare, but happens
         } elsif( $LEN > -1 ) { $BEG = $END - $LEN - $F_OFF; }         # no magic (text, xml + brotli files)
         # suffixes (holy m$)
         if( $TLS ) {
            $TLS = ".$TLS";
            if( $GZIP || $BROTLI ) {                                   # account for different compression-encodings
               if( $GZIP ) { $TLS = "$TLS.gz"; } else { $TLS = "$TLS.br"; }
            }
         }
         # print the files out
         if( $BEG > -1 && $LEN > -1 ) {
            `dd if="$IN/$f" of="$OUT/$f$TLS" skip=$BEG count=$LEN iflag=skip_bytes,count_bytes status=none`;
            if( $MOD ) { `touch "$OUT/$f$TLS" -d "$MOD"`; }
#          print "$MIME: $f; \$TLS=$TLS; \$END=$END; \$BEG=$BEG; \$LEN=$LEN; \$MOD=$MOD; \n";
         }
      } # if( $END > -1 )                                              # other pages are most likely to be HTTP 204 No Content
   }

#!/usr/bin/php
<?php
   // getCC (get Chrome Cache)
   // suggestion: save as ~/.getCC; chmod +x; chmod 700

   $dir  = "/home/alexk/.cache/chromium/Default/Cache/Cache_Data/"; // Chromium cache folder.
   $ppl  = "/home/alexk/Personal/ChromeCache/Files/";               // Place for extracted files
// $END  = "HTTP/1.1 200 OK";                                       // Search in cache-file (works, yet not in some files)
   $END  = "HTTP/1.1 200";                                          // Search in cache-file (works, and IS in all files)
   $FTL  = "";                                                      // Filetype lowercase
   $FTU  = "";                                                      // Filetype uppercase
   $MOFF = 0;                                                       // Offset of magic from file beginning

   $list = scandir( $dir );
   foreach( $list as $filename ) {

      if( is_file( $dir.$filename )) {
         $content = file_get_contents( $dir.$filename );
         if( strstr( $content, 'JFIF')) {
            $FTL  = "jpg";
            $FTU  = "JPEG";
            $MOFF    = 6;
            echo( $filename."  $FTU \n");
            $start   = ( strpos( $content, "JFIF", 0 ) - $MOFF );
            $end     =   strpos( $content, $END, 0 );
            $content =   substr( $content, $start, $end - $MOFF );
            $length =   strlen( $content );
            $wholenm =   $ppl.$filename.".$FTL";
            file_put_contents( $wholenm, $content );
//          echo( "Saving :".$wholenm." \n");
            echo( "start : $start \n");
            echo( "end   : $end \n");
            $diff = $end - $start;
            echo( "length: $length (s/b $diff)\n");
         }
         elseif( strstr( $content, "\211PNG")) {
            $FTL  = "png";
            $FTU  = "PNG";
            $MOFF    = 1;
            echo( $filename."  $FTU \n");
            $start   = ( strpos( $content, "$FTU", 0 ) - $MOFF );
            $end     =   strpos( $content, $END, 0 );
            $content =   substr( $content, $start, $end - $MOFF );
            $length =   strlen( $content );
            $wholenm = $ppl.$filename.".$FTL";
            file_put_contents( $wholenm, $content );
//          echo( "Saving :".$wholenm." \n");
            echo( "start : $start \n");
            echo( "end   : $end \n");
            $diff = $end - $start;
            echo( "length: $length (s/b $diff)\n");
         }
         elseif( strstr( $content, "GIF89a")) {
            $FTL  = "gif";
            $FTU  = "GIF";
            $MOFF    = 0;
            echo( $filename."  $FTU \n");
            $start  = ( strpos( $content, "GIF89a", 0 ) - $MOFF );
            $end    =   strpos( $content, $END, 0 );
            $newc   =   substr( $content, $start, $end );
            $length =   strlen( $newc );
            $wholenm = $ppl.$filename.".$FTL";
            file_put_contents( $wholenm, $newc );
            echo( "Saving :".$wholenm." \n");
            echo( "start : $start \n");
            echo( "end   : $end \n");
            $diff = $end - $start;
            echo( "length: $length (s/b $diff)\n");
         }
         else {
            echo( $filename."  UNKNOWN \n");
         }
      }
   }
?>

ffa41e3d8b4e0cf9_0  PNG 
start : 150 
end   : 14212 
length: 14211 (s/b 14062)
ffa78518232ea9f2_0  PNG 
start : 170 
end   : 1417 
length: 1416 (s/b 1247)
ffad48f3aefb6cd7_0  GIF 
Saving :/home/alexk/Personal/ChromeCache/Files/ffad48f3aefb6cd7_0.gif 
start : 1089 
end   : 1183 
length: 1183 (s/b 94)
ffba1f5387a04a08_0  JPEG 
start : 166 
end   : 972 
length: 966 (s/b 806)
ffbf8448256da635_0  UNKNOWN 
ffc1ebd8d62551b6_0  GIF 
Saving :/home/alexk/Personal/ChromeCache/Files/ffc1ebd8d62551b6_0.gif 
start : 193 
end   : 288 
length: 288 (s/b 95)
ffc2019c23af2000_0  UNKNOWN 
ffc239239bc4e4a9_0  JPEG 
start : 195 
end   : 1920 
length: 1914 (s/b 1725)
ffc57d9b41cebadd_0  UNKNOWN 
ffcbd7258d6a0aea_0  UNKNOWN 
ffda4d6b8e2937fd_0  UNKNOWN 
ffdac4bf770719a1_0  UNKNOWN 
ffde560cb8ad0eaf_0  UNKNOWN 
fff42f6de6d58540_0  UNKNOWN 
fff530252c03d813_0  UNKNOWN 
fff55afc8b58e35f_0  UNKNOWN 
fff822c2bb27d828_0  GIF 
Saving :/home/alexk/Personal/ChromeCache/Files/fff822c2bb27d828_0.gif 
start : 202 
end   : 297 
length: 297 (s/b 95)
index  UNKNOWN