Now I feel bad I opened that
"can of worms"...
//
// Ignore These - So you don't need to process any of these in any way. Just leave them as is.
//
// Yes - Ignoring these embedded URL might not be so simple...
< img src="http://photo_link" height=xxx width=xxx border=2 >
< a href="http://photo_link" target="_blank">Photo Title or Name< /a >
< a href="_link_" target="_blank">_link_< /a >
< object width="425" height="355"><param name="movie" value="http://www.youtube.com/v/__video__code"></param><param name="wmode" value="transparent"></param>< embed > < /embed ></object>
< embed> ___whatever__ </embed>
[ url ]__Link__[ /url ]
[ img ]__Link__[ /img ]
... etc., etc.,...
//
// Only Process These (Independent String Tokens) - & Ignore Everything Else
//
"http://__any__length__string__token___" ==> [ url ]http://__any__length__string__token___[ /url ]
"https://__any__length__string__token___" ==> [ url ]http://__any__length__string__token___[ /url ]
"www.__any__length__string__token___" ==> [ url ]www.__any__length__string__token___[ /url ]
//
// Summary - Simplified "C" Code Algorithm (Other Details & Complexities Omitted)
//
// NOTEs:
// 1) Tokens here are delimited by "white blank spaces" (space, newline, tabs, etc.)
// \n - newline
// \t - horizontal tab
// \v - vertical tab
// \b - backspace
// \r - carriage return
// \f - formfeed
//
// 2) URLs will become a string token as delimited by "
white blank spaces".
//
// The entire single entity "token" will be the URL.
//
// This assumes that a URL will start w/ either (
http://, https://, www., or other known header), &
// it will end w/ a "
white blank space".
Code:
char string_token[1025], p[2025];
string_token[0] = '\0';
p[0] = '\0';
while(get_next_string_token(string_token)) { // get next token - pseudo code
strncpy(p,string_token,1024); // make a copy
if(strncmp(string_token,"http://",7) == 0) { // if "http" URL
tag_untagged_URL(p); // tag that animal
output(p); // output fixed URL
} else if(strncmp(string_token,"https://",8) == 0) { // else if "https" URL
tag_untagged_URL(p); // tag that animal
output(p); // output fixed URL
} else if(strncmp(string_token,"www.",4) == 0) { // else if "www." URL
tag_untagged_URL(p); // tag that animal
output(p); // output fixed URL
} else {
output(string_token); // output unprocessed string token - pseudo code
}
} Reference: strncmp http://www.cplusplus.com/reference/c...g/strncmp.html Reference: strtok http://www.cplusplus.com/reference/c...ng/strtok.html 