问候。我有一个 php 脚本,它应该从批发商的网站上抓取产品信息并将该信息输入数据库。
我已经成功收集了示例产品的所有信息,并且在对所有 $v 变量进行简单回显时,所有内容都正确输出到屏幕。
现在,在我添加检查以查看产品的类别是否存在于数据库中并实际插入信息之后,我得到
[phpBB 调试] PHP 注意:在文件 /rip.php 第 35 行:尝试获取非对象的属性 [phpBB 调试] PHP 注意:在文件 /rip.php 的第 36 行:尝试获取非对象的属性[phpBB 调试] PHP 注意:在文件 /rip.php 第 38 行:未定义偏移量:3 [phpBB 调试] PHP 注意:在文件 /rip.php 第 38 行:未定义偏移量:2 [phpBB 调试] PHP 注意:在第 41 行的文件 /rip.php:尝试获取非对象的属性 致命错误:在第 42 行的 /XXXXX/public_html/XXXXX/rip.php 中的非对象上调用成员函数 find()
但是,所有产品的信息仍然输入到数据库中。
该脚本应该逐页进行,收集信息,但在第一个产品之后停止。
我正在使用 SC Chen 的 Simple HTML DOM scraper script (http://sourceforge.net/projects/simplehtmldom/) 和 phpBB 的数据库调用核心系统,这是我的 PHP 源代码:
<?php
define('IN_PHPBB', true);
$phpbb_root_path = (defined('PHPBB_ROOT_PATH')) ? PHPBB_ROOT_PATH : './';
$phpEx = substr(strrchr(__FILE__, '.'), 1);
include($phpbb_root_path . 'common.' . $phpEx);
include($phpbb_root_path . 'includes/simple_html_dom.' . $phpEx);
// Start session management
$user->session_begin();
$auth->acl($user->data);
$user->setup();
function save($in, $out)
{
$tempDir = './rip_images';
$finalDir = $out;
$imageUrl = $in;
$file = basename($imageUrl);
exec("cd $tempDir && wget --quiet $imageUrl");
if (rename("$tempDir/$file", "$finalDir") === false) {
die('Failed while trying to move image file from temp dir to final dir');
}
}
function scrape($i)
{
$html = file_get_html('XXXXXXXXX.com/index.php?main_page=product_info&products_id='.$i.'&zenid=e4b7dde8de02e1df005d4549e2e3e529');
foreach($html->find('body') as $html)
{
$item['title'] = trim($html->find('#productName', 0)->plaintext);
$item['price'] = trim($html->find('#productPrices', 0)->plaintext);
$item['cat'] = $html->find('#navBreadCrumb', 0)->plaintext;
list($home, $item['cat'], $item['subcat'], $title) = explode("::", $item['cat']);
$item['cat'] = str_replace(" ", "", $item['cat']);
$item['subcat'] = str_replace("\n", "", str_replace(" ", "", $item['subcat']));
$item['desc'] = trim($html->find('#productDescription', 0)->plaintext);
$item['model'] = $html->find('ul#productDetailsList', 0)->find('li', 0)->plaintext;
$item['model'] = explode(":", $item['model']);
$item['model'] = trim($item['model'][1]);
$item['manufacturer'] = $html->find('ul#productDetailsList', 0)->find('li', 1)->plaintext;
$item['manufacturer'] = explode(":", $item['manufacturer']);
$item['manufacturer'] = trim($item['manufacturer'][1]);
foreach($html->find('img') as $img)
{
if($img->alt == $item['title'])
{
$item['img_sm'] = $img->src;
$thumb_width = $img->width;
$thumb_height = $img->height;
}
}
$sm_img_src = "http://XXXXXXXXXX.com/".$item['img_sm'];
$lg_img_src = "http://XXXXXXXXXX.com/index.php?main_page=popup_image&pID=".$i;
$ext = strrchr($item['img_sm'], '.');
$filename = $item['model'] . $ext;
$new_sm = "./rip_images/small/{$filename}";
$new_lg = "./rip_images/large/{$filename}";
$item['image'] = $filename;
$file = file_get_contents($lg_img_src);
$f = fopen($new_lg,'w+');
fwrite($f,$file);
fclose($f);
save($sm_img_src,$new_sm);
$ret[] = $item;
}
$html->clear();
unset($html);
return $ret;
}
$i = 1;
$end = 9999999;
while($i < $end)
{
$ret = scrape($i);
foreach($ret as $v)
{
$item['title'] = $v['title'];
$item['price'] = $v['price'];
$item['desc'] = $v['desc'];
$item['model'] = $v['model'];
$item['manufacturer'] = $v['manufacturer'];
$item['image'] = $v['image'];
$item['cat'] = $v['cat'];
$item['subcat'] = $v['subcat'];
}
//see if parent cat exists
$sql = 'SELECT cat_id FROM ' . SHOP_CAT_TABLE . ' WHERE cat_name = "'.$db->sql_escape($item['cat']).'"';
$result = $db->sql_query($sql);
$parent = $db->sql_fetchrow($result);
// if not exists
if($parent['cat_id'] == '')
{
//add the parent cat to the db
$sql_ary = array(
'cat_name' => $item['cat'],
'cat_parent' => 0
);
$sql = 'INSERT INTO '.SHOP_CAT_TABLE.' '.$db->sql_build_array('INSERT', $sql_ary);
$db->sql_query($sql);
$cat_id = $db->sql_nextid();
//see if subcat exists
$sql = 'SELECT cat_id FROM ' . SHOP_CAT_TABLE . ' WHERE cat_name = "'.$db->sql_escape($item['subcat']).'"';
$result = $db->sql_query($sql);
$row = $db->sql_fetchrow($result);
// if not exists
if($row['cat_id'] == '')
{
//add subcat to db
$sql_ary = array(
'cat_name' => $db->sql_escape($item['subcat']),
'cat_parent' => $cat_id
);
$sql = 'INSERT INTO '.SHOP_CAT_TABLE.' '.$db->sql_build_array('INSERT', $sql_ary);
$db->sql_query($sql);
$item_cat = $db->sql_nextid();
}
else //if exists
{
$item_cat = $row['cat_id'];
}
}
else //if parent cat exists
{
//see if subcat exists
$sql = 'SELECT cat_id FROM ' . SHOP_CAT_TABLE . ' WHERE cat_name = "'.$db->sql_escape($item['subcat']).'"';
$result = $db->sql_query($sql);
$row = $db->sql_fetchrow($result);
// if not exists
if($row['cat_id'] == '')
{
//add the subcat to the db
$sql_ary = array(
'cat_name' => $db->sql_escape($item['subcat']),
'cat_parent' => $parent['cat_id']
);
$sql = 'INSERT INTO '.SHOP_CAT_TABLE.' '.$db->sql_build_array('INSERT', $sql_ary);
$db->sql_query($sql);
$item_cat = $db->sql_nextid();
}
else //if exists
{
$item_cat = $row['cat_id'];
}
}
$sql_ary = array(
'item_title' => $db->sql_escape($item['title']),
'item_price' => $db->sql_escape($item['price']),
'item_desc' => $db->sql_escape($item['desc']),
'item_model' => $db->sql_escape($item['model']),
'item_manufacturer' => $db->sql_escape($item['manufacturer']),
'item_image' => $db->sql_escape($item['image']),
'item_cat' => $db->sql_escape($item_cat)
);
$sql = 'INSERT INTO ' . SHOP_ITEM_TABLE . ' ' . $db->sql_build_array('INSERT', $sql_ary);
$db->sql_query($sql);
$i++;
}
?>
关于如何清除这些通知/错误并让脚本正确地遍历页面的任何建议?我几乎可以肯定这是我忽略的非常简单的事情......