Hi guys, i have this C++ program (actually it's just a snippet) :
#include <iostream>
#include <pcre.h>
#include <string>
using namespace std;
int main(){
string pattern = "<a\\s+href\\s*=\\s*\"([^\"]+)\"",
html = "<html>\n"
"<body>\n"
"<a href=\"example_link_1\"/>\n"
"<a href=\"example_link_2\"/>\n"
"<a href=\"example_link_3\"/>\n"
"</body>\n"
"</html>";
int i, ccount, rc,
*offsets,
eoffset;
const char *error;
pcre *compiled;
compiled = pcre_compile( pattern.c_str(), PCRE_CASELESS | PCRE_MULTILINE, &error, &eoffset, 0 );
if( !compiled ){
cerr << "Error compiling the regexp!!" << endl;
return 0;
}
rc = pcre_fullinfo( compiled, 0, PCRE_INFO_CAPTURECOUNT, &ccount );
offsets = new int[ 3 * (ccount + 1) ];
rc = pcre_exec( compiled, 0,
html.c_str(),
html.length(), 0, 0, offsets, 3 * (ccount + 1) );
if( rc >= 0 ){
for( i = 1; i < rc; ++i ){
cout << "Match : " <<
html.substr( offsets[2*i], offsets[2*i+1] - offsets[2*i] ) << endl;
}
}
else{
cout << "Sorry, no matches!" << endl;
}
delete [] offsets;
return 0;
}
As you can see, i'm trying to match
html links inside a buffer with the given regular expression (the \\s is \s escaped
for C/C++ strings).
But, even if in the buffer there are 3 links and the regexp is compiled with the PCRE_CASELESS and PCRE_MULTILINE flags, i match only one element :
Match : example_link_1
Note: I start the loop fro index 1 because the pcre library returns the string that matched (not the match itself) as the first element, and the matches follows.
What's wrong with this code? The regexp itself i think it's correct (tried in PHP
for instance).
