| 代码如下 |
复制代码 |
|
/*
抓取百度收录代码
*/
function baidu($s){
$baidu="http://www.baidu.com/s?wd=site%3A".$s;
$site=file_get_contents($baidu);
//$site=iconv("gb2312", "UTF-8", $site);
ereg("找到相关网页(.*)篇，", $site,$count);
$count=str_replace("找到相关网页","",$count);
$count=str_replace("篇，","",$count);
$count=str_replace("约","",$count);
$count=str_replace(",","",$count);
return $count[0];
}
echo baidu(www.hzhuti.com); //获取好主题在百度中的收录数量
?>
|
/*
Grab Baidu included code
*/
function baidu($s){
$baidu="http://www.baidu.com/s?wd=site%3A".$s;
$site=file_get_contents($baidu);
//$site=iconv("gb2312", "UTF-8", $site);
ereg("Relevant web pages (.*) found,", $site,$count);
$count=str_replace("Find relevant web pages","",$count);
$count=str_replace("article,","",$count);
$count=str_replace("about","",$count);
$count=str_replace(",","",$count);
Return $count[0];
}
echo baidu(www.hzhuti.com); //Get the number of good topics included in Baidu
| 代码如下 |
复制代码 |
|
/**
* * @user 小杰
* @return array 返回百度的热词数据(数组返回)
*/
function getBaiduHotKeyWord()
{
$templateRss = file_get_contents('http://top.baidu.com/rss_xml.php?p=top10');
If (preg_match('/ /is', $templateRss, $_description)) {
$templateRss = $_description [0];
$templateRss = str_replace("&", "&", $templateRss);
}
$templateRss = "" . $templateRss;
$xml = simplexml_load_String($templateRss);
foreach ($xml->tbody->tr as $temp) {
if (!empty ($temp->td->a)) {
$keyArray [] = trim(($temp->td->a));
}
}
return $keyArray;
}
print_r(getBaiduHotKeyWord());
|
?>
Get Baidu’s hot words
| The code is as follows |
Copy code |
/**
* * @user 小杰
* @return array Returns Baidu’s hot word data (array return)
*/
function getBaiduHotKeyWord()
{
$templateRss = file_get_contents('http://top.baidu.com/rss_xml.php?p=top10');
If (preg_match('//is', $templateRss, $_description)) {
$templateRss = $_description [0];
$templateRss = str_replace("&", "&", $templateRss);
}
$templateRss = "" . $templateRss;
$xml = simplexml_load_String($templateRss);
foreach ($xml->tbody->tr as $temp) {
if (!empty ($temp->td->a)) {
$keyArray [] = trim(($temp->td->a));
}
}
return $keyArray;
}
print_r(getBaiduHotKeyWord());
|
I found this on the Internet and modified it slightly. Write the following code into the php file
Baidu inclusion and Baidu snapshot time
The code is as follows
| 代码如下 |
复制代码 |
|
$domain = “http://www.hzhuti.com/nokia/5230/ *欲查询的域名*/
$site_url = ‘http://www.baidu.com/s?wd=site%3A’;
$all = $site_url.$domain; /*域名所有收录的网址*/
$today = $all.’&lm=1′; /*域名今日收录的网址*/
$utf_pattern = “/找到相关结果数(.*)个/”;
$kz_pattern = “/(.*)/”; /*用以匹配快照日期的字符串*/
$times = “/d{4}-d{1,2}-d{1,2}/”; /*匹配快照日期的正则表达式，如:2011-8-4*/
$s0 = @file_get_contents($all); /*将site:www.ninthday.net的网页置入$s0字符串中*/
$s1 = @file_get_contents($today);
preg_match($utf_pattern,$s0,$all_num); /*匹配”找到相关结果数*个”*/
preg_match($utf_pattern,$s1,$today_num);
preg_match($kz_pattern,$s0,$temp);
preg_match($times,$temp[0],$screenshot);
if($all_num[1] == “”)
$all_num[1] = 0;
if($today_num[1] == “”)
$today_num[1] = 0;
if($screenshot[0] == “”)
$screenshot[0] = “暂无快照”;
?>
Test
百度收录：” target=”_blank”>
百度今日收录：” target=”_blank”>
百度快照日期：”>
|
|
Copy code
|
|
|
$domain = “http://www.hzhuti.com/nokia/5230/ *Domain name to be queried*/
$site_url = ‘http://www.baidu.com/s?wd=site%3A’;<🎜>
$all = $site_url.$domain; /*All URLs included in the domain name*/<🎜>
$today = $all.’&lm=1′; /*The URL of the domain name included today*/<🎜>
$utf_pattern = "/Number of related results found (.*)/";<🎜>
$kz_pattern = “/(.*)/”; /*String used to match snapshot date*/
$times = “/d{4}-d{1,2}-d{1,2}/”; /*Regular expression matching snapshot date, such as: 2011-8-4*/
$s0 = @file_get_contents($all); /*Place the web page of site:www.ninthday.net into the $s0 string*/
$s1 = @file_get_contents($today);
Preg_match($utf_pattern,$s0,$all_num); /*Match "Number of relevant results found*"*/
Preg_match($utf_pattern,$s1,$today_num);
Preg_match($kz_pattern,$s0,$temp);
Preg_match($times,$temp[0],$screenshot);
If($all_num[1] == “”)
$all_num[1] = 0;
If($today_num[1] == “”)
$today_num[1] = 0;
If($screenshot[0] == “”)
$screenshot[0] = “No snapshot yet”;
?>
Test
| Date | Baidu included | Baidu included today | Baidu snapshot date |
| | | | |
Baidu included:” target=”_blank”>
Baidu included today: ” target=”_blank”>
Baidu snapshot date: ”>
The above method has not been strictly considered. If the server does not support the file_get_contents function, we will not be able to operate it, so we can also use curl operation, which is more convenient and can imitate users.
http://www.bkjia.com/PHPjc/631640.htmlwww.bkjia.comtruehttp: //www.bkjia.com/PHPjc/631640.htmlTechArticleIf you take a closer look, you can find a problem. Let’s grab Baidu’s collection or snapshot or There is a function file_get_contents() in the hot word program, which is a php collection network...
|
