function harvest_links($url)
{
# Initialize
global $DELAY;
$link_array = array();
# Get page base for $url
$page_base = get_base_page_address($url);
# Download webpage
sleep($DELAY);
$downloaded_page = http_get($url, "");
$anchor_tags = parse_array($downloaded_page['FILE'], "<a", "</a>", EXCL);
# Put http attributes for each tag into an array
for ($xx = 0; $xx < count($anchor_tags); $xx++) {
$href = get_attribute($anchor_tags[$xx], "href");
$resolved_addres = resolve_address($href, $page_base);
$link_array[] = $resolved_addres;
echo "Harvested: " . $resolved_addres . " \n";
}
return $link_array;
}
}
$strSQL .= " WHERE iPageID={$pageID}";
db_run_query($strSQL);
}
//die("Preparation done.\n");
}
$seed = db_get_next_to_harvest();
while ($seed != NULL) {
$SEED_URL = $seed["strURL"];
// First URL spider downloads
#$START_PENETRATION = seed['iLevel'];
# Get links from $SEED_URL
echo "Harvesting Seed " . $seed["iPageID"] . "; URL " . $seed["strURL"] . "\n";
#$link_array = array();
# Get page base for $url
$page_base = get_base_page_address($seed["strURL"]);
# Download webpage
//global $DELAY;
//sleep($DELAY);
$strHTML = "";
if ($seed["strHTML"] == NULL) {
//die("No page: " . $seed["iPageID"]);
echo "Downloading....\n";
try {
$strURL = $seed["strURL"];
if (exclude_link($seed["strURL"])) {
throw new Exception("Page in excluded list: {$strURL}\n");
}
$downloaded_page = http_get_withheader($seed["strURL"], "");
# Catch fetch errors, oversize files, non-text extensions etc.
if ($downloaded_page['ERROR'] !== '') {
function download_images_for_page($target)
{
echo "target = {$target}\n";
# Download the web page
$web_page = http_get($target, $referer = "");
# Update the target in case there was a redirection
$target = $web_page['STATUS']['url'];
# Strip file name off target for use as page base
$page_base = get_base_page_address($target);
# Identify the directory where iamges are to be saved
$save_image_directory = "saved_images_" . str_replace("http://", "", $page_base);
# Parse the image tags
$img_tag_array = parse_array($web_page['FILE'], "<img", ">");
if (count($img_tag_array) == 0) {
echo "No images found at {$target}\n";
exit;
}
# Echo the image source attribute from each image tag
for ($xx = 0; $xx < count($img_tag_array); $xx++) {
$image_path = get_attribute($img_tag_array[$xx], $attribute = "src");
echo " image: " . $image_path;
$image_url = resolve_address($image_path, $page_base);
if (get_base_domain_address($page_base) == get_base_domain_address($image_url)) {
# Make image storage directory for image, if one doesn't exist
$directory = substr($image_path, 0, strrpos($image_path, "/"));
$directory = str_replace(":", "-", $directory);
$image_path = str_replace(":", "-", $image_path);
clearstatcache();
// clear cache to get accurate directory status
if (!is_dir($save_image_directory . "/" . $directory)) {
mkpath($save_image_directory . "/" . $directory);
}
# Download the image, report image size
$this_image_file = download_binary_file($image_url, $ref = "");
echo " size: " . strlen($this_image_file);
# Save the image
if (stristr($image_url, ".jpg") || stristr($image_url, ".gif") || stristr($image_url, ".png")) {
$fp = fopen($save_image_directory . "/" . $image_path, "w");
fputs($fp, $this_image_file);
fclose($fp);
echo "\n";
}
} else {
echo "\nSkipping off-domain image.\n";
}
}
}
/*
LIB_resolve_addresses.php 函数测试
*/
include "../util/LIB_resolve_addresses.php";
$url_1 = "http://www.bruceyoo.com/";
$url_2 = "http://www.bruceyoo.com/image/";
$url_3 = "http://www.bruceyoo.com/image/index.html";
$url_4 = "http://";
$url_5 = "http://www.burceyoo.com/index.html";
$url_6 = "www.burceyoo.com/index.html";
echo "{$url_1} base_page: " . get_base_page_address($url_1) . "\n";
echo "{$url_2} base_page: " . get_base_page_address($url_2) . "\n";
echo "{$url_3} base_page: " . get_base_page_address($url_3) . "\n";
echo "{$url_4} base_page: " . get_base_page_address($url_4) . "\n";
echo "{$url_5} base_page: " . get_base_page_address($url_5) . "\n";
echo "{$url_6} base_page: " . get_base_page_address($url_6) . "\n";
echo "--------------------------------------------------------\n";
/*
应该使用base_page_address 测试直接使用原url address
*/
echo "{$url_1} base_domain: " . get_base_domain_address($url_1) . "\n";
echo "{$url_2} base_domain: " . get_base_domain_address($url_2) . "\n";
echo "{$url_3} base_domain: " . get_base_domain_address($url_3) . "\n";
// echo "url_4 base_domain: ".get_base_domain_address($url_4) ."\n"; #会报错，看可以继续运行返回为空
echo "{$url_5} base_domain: " . get_base_domain_address($url_5) . "\n";
echo "{$url_6} base_domain: " . get_base_domain_address($url_6) . "\n";
echo "--------------------------------------------------------\n";
$link_1 = "../image/book1.jpg";
$link_2 = "./image/book2.jpg";
$link_3 = "/image/book3.jpg";
$link_4 = "image/book4.jpg";
