$email, "pass" => $pass);
curl_setopt($ch, CURLOPT_POSTFIELDS,$post);
curl_exec($ch);
spider_notes($ch);
curl_close($ch);
}
function spider_notes($ch) {
//This finds the note links and feeds them to the parser
curl_setopt($ch, CURLOPT_URL,"http://m.facebook.com/notes.php");
$data = curl_exec($ch);
$html = str_get_html($data);
//count posts so we can travese all pages
foreach($html->find('small') as $element) {
if ($buffer = strstr($element->innertext,"Notes 1 - 5 of ")) {
$posts = substr($buffer,15);
}
}
$count = 0;
//the while loop CURL's through the multiple pages of your notes section
while ($count < $posts) {
foreach($html->find('a') as $element) {
if (strstr($element->href,"/note.php")) {
if (strstr($element->href,"#anchor_fbid_")) {
if ($element->innertext != "Read More")
find_comments($ch,html_entity_decode($element->href)); //go to and parse the note
}
}
}
$count = $count + 5;
curl_setopt($ch, CURLOPT_URL,sprintf("http://m.facebook.com/notes.php?p=%s",$count));
$data = curl_exec($ch);
$html = str_get_html($data);
}
}
function find_comments($ch,$url) {
//This function takes the notes page tags the data we want and strips the html then parses it
//curl_setopt($ch, CURLOPT_REFERER,"http://m.facebook.com/notes.php");
curl_setopt($ch, CURLOPT_URL, sprintf("http://m.facebook.com%s",$url));
$data = curl_exec($ch);
$data = charset_decode_utf_8($data);
$html = str_get_html($data);
$title = $html->find("div.note",0)->find("a",0)->innertext;
echo "Note: " . $title . "
";
foreach ($html->find("div[id*=comments_note_]") as $element) {
foreach ($element->find("div") as $scrape) {
if($scrape->class == "note") {
if($title != $scrape->find("a",0)->plaintext) {
echo "Author: " . $scrape->find("a",0)->plaintext . "
";
}
}
if(!$scrape->class) {
echo "Comment: " . substr($scrape->plaintext,0,-6) . "
";
}
}
}
?>