Search for text and font

Question

I have an 800 page pdf document to index and so far I have a script that will search for a list of keywords. But the text has large sections of code in a different font, and I think we would like to generate an index of just code examples. Is there a way to search for text of a given font in applescript? Something like
set theSel to find text theText
if the font of theSel is "Times"
write to file, etc.

Answer 1

Please do send a page, I might be able to spot where the font problem is coming from - but no guarantee Address is in my profile.
You asked about the script formatter. red_menace of this forum wrote the script I use. To use it, you copy the script that you want to format to the clipboard and run the formatter. This then places the marked-up text in the clipboard so that you can paste it into the forum page.
<pre style="
font-family: Monaco, 'Courier New', Courier, monospace;
font-size: 10px;
margin: 0px;
padding: 5px;
border: 1px solid #000000;
width: 720px; height: 340px;
color: #000000;
background-color: #FFDDFF;
overflow: auto;">
script formatter - formats the clipboard text for forum posting
last reviewed January 19, 2009   red_menace[at]mac[dot]com
Input: text read from the clipboard
Output: formatted text copied to the clipboard
set AppleScript's text item delimiters to " "
-- some constants and switches
property TextColor : "#000000" -- black  (see http://www.w3schools.com/tags/ref&#95;colornames.asp)
property BackgroundColor : "#FFDDFF" -- a light plum/purple
property BorderColor : "#000000" -- black
property TheWidth : "width: 720px; " -- a width attribute  (deprecated in HTML 4.01)
property UseWidth : true -- use the width attribute?
property LineCount : 25 -- the number of lines before including the height attribute
property TheHeight : "height: " & ((LineCount * 13.6) as integer) & "px; " -- a maximum height for the <pre> box
property Emphasize : false -- emphasise (bold) the script text?
property UseURL : false -- include a Script Editor message link?
property AltURL : false -- use an alternate URL encoding?
property ToolTips : {¬
"this text can be pasted into the Script Editor", ¬
"this text can be pasted into an Automator 'Run AppleScript' action", ¬
"this text can be pasted into an Automator 'Run Shell Script' action", ¬
"this text can be pasted into a HTML editor", ¬
"this text can be pasted into a text editor", ¬
"- none -"}
property TooltipDefault : {item 1 of ToolTips} -- keep track of the last tooltip used
property TempFile : "Script_Formatter_TempFile" -- a temporary work file
try
-- write the clipboard to the temporary file
set TheClipboard to (the clipboard) as text
if TheClipboard is in {"", space, tab, return} then return -- clipboard is (basically) empty
set MyOpenFile to open for access ("/tmp/" & TempFile & ".txt" as POSIX file) with write permission
set eof of MyOpenFile to 0 -- empty any previous temp file
write TheClipboard to MyOpenFile
close access MyOpenFile
if UseURL then
-- encode URL  (see http://developer.apple.com/documentation/Darwin/Reference/Manpages/man1/pydoc.1. html)
do shell script "/usr/bin/python -c 'import sys, urllib; print urllib.quote(sys.argv[1])' " & quoted form of TheClipboard
-- add a link wrapper
set URLtext to "applescript://com.apple.scripteditor?action=new&script=" & the result
if AltURL then -- use an alternate URL encoding
set URLtext to "Click here to [url=" & URLtext & "]open this script in the Script Editor[/url]:<br />"
else -- use HTML anchor tag
set URLtext to "Click here to <a href=\"" & URLtext & "\">open this script in the Script Editor</a>:<br />"
end if
set PromptText to ((count URLtext) as text) & " URL and "
else
set {URLtext, PromptText} to {"", ""}
end if -- UseURL
-- convert to HTML  (see http://developer.apple.com/documentation/Darwin/Reference/ManPages/man1/textutil .1.html)
do shell script "cd /tmp/; /usr/bin/textutil -convert html -excludedelements '(html, head, title, body, p, span, font)' -encoding US-ASCII " & TempFile & ".txt"
-- fix up some formatting and add a pre wrapper  (see http://www.w3schools.com/tags/default.asp)
set HTMLtext to rest of paragraphs of (read ("/tmp/" & TempFile & ".html" as POSIX file))
if (count HTMLtext) is less than LineCount then -- skip the height attribute
set Height to ""
else
set Height to TheHeight
end if
set HTMLtext to FixCharacters from (HTMLtext as text) -- additional character encodings
if UseWidth then
set Width to TheWidth
else
set Width to ""
end if
if Emphasize then set HTMLtext to "<strong>" & HTMLtext & "</strong>"
set HTMLtext to "<pre style=\"
font-family: Monaco, 'Courier New', Courier, monospace;
font-size: 10px;
margin: 0px;
padding: 5px;
border: 1px solid " & BorderColor & ";
" & Width & Height & "
color: " & TextColor & ";
background-color: " & BackgroundColor & ";
overflow: auto;\"
title=\"\">
" & HTMLtext & "</pre>
-- assemble everything on the clipboard
set TheResult to choose from list ToolTips ¬
with title "Script Formatted" with prompt PromptText & ((count HTMLtext) as text) & " HTML characters will be placed on the clipboard (plus the following ToolTip):" default items TooltipDefault OK button name "OK" cancel button name "Cancel" with empty selection allowed without multiple selections allowed
if TheResult is false then -- cancel button
error number -128
else -- add the selected title attribute (tooltip), if any
set TooltipDefault to TheResult as text
set Here to (offset of " title=" in HTMLtext) - 1
set There to (offset of ">" in HTMLtext) - 1
if TheResult is in {{}, "- none -"} then -- no tooltip
set the clipboard to URLtext & (text 1 thru (Here - 1) of HTMLtext) & (text (There + 1) thru -1 of HTMLtext)
else
set the clipboard to URLtext & (text 1 thru (Here + 9) of HTMLtext) & TheResult & (text There thru -1 of HTMLtext)
end if
end if -- TheResult is false
on error ErrorMessage number ErrorNumber
log space & (ErrorNumber as text) & ":" & tab & ErrorMessage
try
close access MyOpenFile
end try
if (ErrorNumber is -128) or (ErrorNumber is -1711) then -- nothing (user cancelled)
else
activate me
display alert "Error " & (ErrorNumber as text) message ErrorMessage as warning buttons {"OK"} default button "OK"
end if
end try
to FixCharacters from TheText
fixes (converts) formatting characters used in some message forums  (see http://www.asciitable.com/)
parameters - TheText [text]: the text to fix
returns [text]: the fixed text
-- this list of lists contains the characters to encode - item 1 is the character, item 2 is the HTML encoding
set TheCharacters to {¬
{"!", "&#33;"}, ¬
{"*", "&#42;"}, ¬
{"+", "&#43;"}, ¬
{"-", "&#45;"}, ¬
{"[", "&#91;"}, ¬
{"\\", "&#92;"}, ¬
{"]", "&#93;"}, ¬
{"^", "&#94;"}, ¬
{"_", "&#95;"}, ¬
{"~", "&#126;"}}
set TempTID to AppleScript's text item delimiters
repeat with SomeCharacter in TheCharacters
if item 1 of SomeCharacter is in TheText then -- replace
set AppleScript's text item delimiters to item 1 of SomeCharacter
set the ItemList to text items of TheText
set AppleScript's text item delimiters to item 2 of SomeCharacter
set TheText to the ItemList as text
end if
end repeat
set AppleScript's text item delimiters to TempTID
return TheText
end FixCharacters
</pre>