Shell Programming and Scripting

(name of the script you save it as, i like to call it threaddl) http://boards.4chan.org/tg/res/20218467 1

# removes a script tag
-e '1 s/.\{1,31\}$//' -e '2,10 d'

# remove rss link tag and more script tags
-e '/^<meta / s_<link[^>]\{1,100\}xml"/>\(<title>[^>]\+</title>\).\+_\1_'

# make favicon source a relative link
# ST="static.4chan.org"
# LOC=the input thread's number
-e '/^<meta / s_//'$ST'/image/\(favicon-\?[a-z]\{0,10\}\.ico\)_'$LOC'/misc/\1_'

# remove alternative style sheets
-e '/^<meta / s_<link rel="alternate style.\+\(<link rel="apple-touch-icon" h\)_\1_'

# make default style sheet's source associated to the board a relative link
-e '/^<meta / s_//'$ST'/css/\([a-z0-9\.]\{1,25\}\.css\)_'$LOC'/misc/\1_'

# remove some more script tag(s)
-e '3,16 d'

# remove name, tripcode and post number nodes that are only for mobile view
-e '$ s_\(<div id="\)pim\([0-9]\{1,25\}\).\{1,1000\}\(\1\(pi\|f\)\2\)_\3_g'

# give thumbnails, full sized pictures, logo, spoiler images, country flags relative source link
-e '$ s_//.\.thumbs\.4chan\.org/[a-z0-9]\{1,10\}/thumb/\([0-9]\{1,25\}s\.jpg\)_'$LOC'/misc/\1_g' -e '$ s_//images\.4chan\.org/[a-z0-9]\{1,10\}/src/\([0-9]\{1,25\}\.\)\(jpg\|gif\|png\)_'$LOC'/\1\2_g' -e '$ s_//'$ST'/image/title/[a-z]\{1,10\}/[a-z0-9]\{1,100\}\.\(jpg\|gif\|png\)_'$LOC'/misc/logo.\1_g' -e '$ s_//'$ST'/image/\(spoiler-\?[a-z0-9]\{0,10\}\....\)_'$LOC'/misc/\1_g' -e '$ s_//'$ST'/image/country/\(\([a-z]\{0,25\}/\)\?[a-z0-9]\{1,25\}\....\)_'$LOC'/misc/\1_g'

# point quote links to relative target and mark the ones with a target of OP or a cross thread post
-e '$ s_\(<a href="\)'$LOC'\(#p\{1,100\}"\)_\1\2_g' -e '$ s_<a href="#p'$LOC'" class="quotelink">&gt;&gt;'$LOC'_& (OP)_g' -e '$ s_\(<a href="[0-9]\{1,100\}\)\(#p[0-9]\{1,100\}" class="quotelink">&gt;&gt;[0-9]\{1,100\}\)_\1.html\2 (Cross-thread)_g'

# remove board link list, report/delete form, theme selector from the bottom of the html page, correct the Return and Top links and inject script
# S1=a script tag
-e '$ s_\(</div></div></div><hr>\)<div class="mobile".\+</div><hr>\(<div class="navLinks navLinksBot">\[<a href="\)\.\./\(\./"[^>]\{0,100\}>Return</a>\] \[<a href="\)#top\(">Top</a>\]\).\+</body>_\1</form>\2\3javascript:scroll(0,0);\4<div id=bottom></div>'$S1'</body>_'

# remove board link list, settings, posting form, correct Return and Bottom links, preserve the logo image and text and announcement, inject a script and a style tag to add image expansion feature
# S2= a script and a style tag
-e '$ s_^\(.\{1,39\}\)<div id="boardNavDesktop" class="desktop">.\{0,7800\}\(<div class="boardBanner"\{0,250\}\)<hr class="abovePostForm"/\?>.\{0,400\}\(<div class="navLinks">.<a href="\)\.\./\(\./.\{0,100\}\)#bottom\(">Bottom</a>]\).\{0,4000\}alt=""/></a>\(</div><hr><a href="ja\)_'$S2'\1\2\3\4javascript:scroll(0,d.documentElement.scrollHeight)\5\6_'

# add the http protocol to links in a tags
-e '$ s_<a\(.\{1,1000\}\)href="//_<a\1href="http://_g'

# removes a script tag
-e '2,10 d'
...
# remove some more script tag(s)
-e '3,16 d'

s_'$ST'_'$LOC'_

# ST="static.4chan.org"

s_'"$ST"'_'"$LOC"'_

# echo a | sed 's/a/[nope]/' 
[nope] 
#