/**
* 截取字符串，用...代替
*/
function sub_str($str, $number)
{
if (strlen_utf8($str) > $number) {
return substr_utf8($str, 0, $number) . '...';
}
return $str;
}
/**
* 生成描述，注意：必须先生成标题！
*/
function GenerateDescription()
{
$arrKeys = $this->arrKeys;
$arrKeys = $this->JumbleArrayUseFeature($arrKeys);
$exKey = $arrKeys[0];
$arrDescription = array_slice($this->arrContent, 0, 5);
$Description = implode('|', $arrDescription) . '|' . $this->key . '|' . $exKey;
$arrDescription = explode('|', $Description);
//描述部分用随机就行了。没必要伪随机
shuffle($arrDescription);
$Description = implode('', $arrDescription);
$Description = replace_dbs($Description, '.');
$this->descriptions = substr_utf8($Description, 0, 1000);
}
/**
* Smarty truncate modifier plugin
*
* Type: modifier<br>
* Name: utf8_truncate<br>
* @author jack.z
* @param string
* @param integer
* @param string
* @param boolean
* @param boolean
* @return string
*/
function smarty_modifier_utf8_truncate($string, $length = 80, $etc = '...', $break_words = false, $middle = false)
{
return $returnstr = substr_utf8(StripHTML($string), 0, $length) . $etc;
}
function out_view($arr, $arr_view, $domain, $base_url)
{
global $cfg_tk_pid;
$con = file_get_contents("./templets/view.html");
/* =================
* 生成链接
* =================
*
* 生成相关链接
* $key_link:由关键词列表生成关键词连接集
*/
$arr_keys = explode(",", $arr['keys']);
//生成相关关键词链接
$key_link = '';
//由关键词动态生成，不记录在cache，但要输出
foreach ($arr_keys as $kk) {
$key_epath = get_epath($kk);
$arr_temp = explode("/", $key_epath);
$key_link .= '<li><a href="http://' . $arr_temp[0] . $domain . '/' . $arr_temp[1] . '">' . $kk . '</a></li>';
}
/*
* $tag_link:生成tag链接，包含随机部分及互连部分
*/
$tag_link = $arr['flink'];
//生成tag链接，包含随机部分及互连部分（数据库给出）
$arr_randkey = explode(',', $arr['tag_key']);
foreach ($arr_randkey as $kk) {
$key_epath = get_epath($kk);
$arr_temp = explode("/", $key_epath);
$tag_link .= '<li><a href="http://' . $arr_temp[0] . $domain . '/' . $arr_temp[1] . '">' . $kk . '</a></li>';
}
$base = str_replace('/x', '', $base_url . 'x');
/*
* 替换数组
*/
$arr_rep = array();
$arr_rep['key'] = $arr['key'];
$arr_rep['title'] = $arr_view['title'];
$arr_rep['maintitle'] = $arr['title'];
$description = preg_replace("%<[^>]+>%", ',', $arr_view['description']);
$description = substr_utf8($description, 0, 50);
$arr_rep['miaoshu'] = $description;
$arr_rep['base_url'] = $base;
$arr_rep['body'] = $arr_view['body'] . "<br>" . "您可能感兴趣：<br>" . $arr_view['x_link'];
if ($arr_rep['body'] == '') {
//如果尚未生成文章内容
$arr_rep['body'] = '暂无数据，请等待。错误编码：' . md5($base_url);
}
$arr_rep['adkey'] = $arr['adkey'];
$arr_rep['adkey_code'] = urlencode($arr['adkey']);
$arr_rep['adkey_iconv'] = urlencode(iconv("UTF-8", "GBK//IGNORE", $arr['adkey']));
$arr_rep['pid'] = $cfg_tk_pid;
$arr_rep['keys_link'] = $key_link;
$arr_rep['tag_link'] = $tag_link;
/*
* 替换
*/
foreach ($arr_rep as $k => $v) {
$con = str_replace('{' . $k . '}', $v, $con);
}
echo $con;
include './fun/robot.php';
}
function truncate($text, $length = 200, $ending = '...', $exact = true, $considerHtml = true)
{
if ($considerHtml) {
// if the plain text is shorter than the maximum length, return the whole text
if (strlen_utf8(preg_replace('/<.*?>/u', '', $text)) <= $length) {
return $text;
}
// splits all html-tags to scanable lines
preg_match_all('/(<.+?>)?([^<>]*)/su', $text, $lines, PREG_SET_ORDER);
$total_length = strlen_utf8($ending);
$open_tags = array();
$truncate = '';
foreach ($lines as $line_matchings) {
// if there is any html-tag in this line, handle it and add it (uncounted) to the output
if (!empty($line_matchings[1])) {
// if it's an "empty element" with or without xhtml-conform closing slash (f.e. <br/>)
if (preg_match('/^<(\\s*.+?\\/\\s*|\\s*(img|br|input|hr|area|base|basefont|col|frame|isindex|link|meta|param)(\\s.+?)?)>$/isu', $line_matchings[1])) {
// do nothing
} else {
if (preg_match('/^<\\s*\\/([^\\s]+?)\\s*>$/us', $line_matchings[1], $tag_matchings)) {
// delete tag from $open_tags list
$pos = array_search($tag_matchings[1], $open_tags);
if ($pos !== false) {
unset($open_tags[$pos]);
}
} else {
if (preg_match('/^<\\s*([^\\s>!]+).*?>$/su', $line_matchings[1], $tag_matchings)) {
// add tag to the beginning of $open_tags list
array_unshift($open_tags, strtolower($tag_matchings[1]));
}
}
}
// add html-tag to $truncate'd text
$truncate .= $line_matchings[1];
}
// calculate the length of the plain text part of the line; handle entities as one character
$content_length = strlen_utf8(preg_replace('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/ui', ' ', $line_matchings[2]));
if ($total_length + $content_length > $length) {
// the number of characters which are left
$left = $length - $total_length;
$entities_length = 0;
// search for html entities
if (preg_match_all('/&[0-9a-z]{2,8};|&#[0-9]{1,7};|&#x[0-9a-f]{1,6};/iu', $line_matchings[2], $entities, PREG_OFFSET_CAPTURE)) {
// calculate the real length of all entities in the legal range
foreach ($entities[0] as $entity) {
if ($entity[1] + 1 - $entities_length <= $left) {
$left--;
$entities_length += strlen_utf8($entity[0]);
} else {
// no more characters left
break;
}
}
}
$truncate .= substr_utf8($line_matchings[2], 0, $left + $entities_length);
// maximum lenght is reached, so get off the loop
break;
} else {
$truncate .= $line_matchings[2];
$total_length += $content_length;
}
// if the maximum length is reached, get off the loop
if ($total_length >= $length) {
break;
}
}
} else {
if (strlen_utf8($text) <= $length) {
return $text;
} else {
$truncate = substr_utf8($text, 0, $length - strlen_utf8($ending));
}
}
// if the words shouldn't be cut in the middle...
if (!$exact) {
// ...search the last occurance of a space...
$spacepos = strrpos($truncate, ' ');
if (isset($spacepos)) {
// ...and cut the text in this position
$truncate = substr_utf8($truncate, 0, $spacepos);
}
}
// add the defined ending to the text
$truncate .= $ending;
if ($considerHtml) {
// close all unclosed html-tags
foreach ($open_tags as $tag) {
$truncate .= '</' . $tag . '>';
}
}
return $truncate;
}
/**
* 抓取文章
*/
function CrawlView()
{
if (count($this->listNotCrawl) < 1) {
//全部抓取完毕，不再抓取
//$this->isUp=FALSE;
return;
}
if ($this->errorTime > 6) {
//错误超过6次，跳过
array_splice($this->listNotCrawl, 0, 1);
$this->errorTime = 0;
$this->isUp = TRUE;
return;
}
$articleId = $this->listNotCrawl[0];
$data = CurlGet('http://zhidao.baidu.com/question/' . $articleId . '.html');
$data = iconv("GBK", "UTF-8", $data);
//标题
$title = '';
if (preg_match('%<title>([^>]+?)_%sim', $data, $arr)) {
$title = strip_tags($arr[1]);
}
if ($title == '') {
$this->isUp = TRUE;
$this->errorTime += 1;
return;
}
/*描述
$question_description='';
if(preg_match('%<pre id="question-content">([^<]+)</pre>%sim',$data,$arr)){
$question_description=trim($arr[1]);
}*/
//最佳答案
$answers = '';
if (preg_match('%<pre id="best-answer-content[^>]+?>([^<]+?)</pre>%sim', $data, $arr)) {
$answers[] = str_replace(array('\\r', '\\n', '\\r\\n'), '<br>', strip_tags(trim($arr[1])));
}
//其他答案
if (preg_match_all('%<pre class="reply[^>]+?>([^<]+?)</pre>%sim', $data, $arr)) {
foreach ($arr[1] as $r) {
$answers[] = str_replace(array('\\r', '\\n', '\\r\\n'), '<br>', strip_tags(trim($r)));
}
}
$data = null;
$arr = null;
unset($data, $arr);
$arrBody = explode('<br>', $this->body);
$arrBody = array_merge($arrBody, $answers);
if (count($arrBody) <= 1) {
$body = $arrBody[0];
} else {
shuffle($arrBody);
$body = implode('<br>', $arrBody);
}
$body = str_replace($title, '', $body);
$arrBody = explode('<br>', $body);
shuffle($arrBody);
$body = implode('<br>', $arrBody);
if ($this->title == '') {
$this->title = $title;
}
$this->errorTime = 0;
if (strlen($body) > 20000) {
//body达到20K，不再抓取。
$body = substr_utf8($body, 0, 20000);
$this->body = $body;
$body = null;
$this->listNotCrawl = array();
$this->isUp = TRUE;
return;
}
$this->body = $body;
$body = null;
array_splice($this->listNotCrawl, 0, 1);
//去掉成功的文章
$this->isUp = TRUE;
}
function randart($key, $keys, $a_no, $base_url)
{
global $cfg_xs_url;
$url = 'http://' . $base_url . 'read-' . $a_no . 'html';
$md5_url = md5($url);
/*
* 生成指纹序列
* $art_sp:文章指纹序列
* $choas_sp:乱序指纹序列
*/
for ($i = 0; $i < 5; $i++) {
//标题指纹序列
$art_sp[$i] = toTen(substr($md5_url, $i * 4, 4)) + 1;
}
$choas_sp = str_split(toTen(substr($md5_url, 0, 8)) . toTen(substr($md5_url, 8, 8)) . toTen(substr($md5_url, 16, 8)) . toTen(substr($md5_url, 24, 8)), 1);
/*
* 副关键词
*/
$arr_keys = explode(",", $keys);
$arr_keys = arr_choas($arr_keys, $choas_sp);
$key2 = $arr_keys[0];
/*
* 确定标题
* 先从5个文本组合副关键词组合打乱一次
* 再提取20字符，加入主关键词打乱一次
*/
$title = '';
$des = '';
for ($i = 0; $i < 5; $i++) {
$temp = file_get_contents($cfg_xs_url . $art_sp[$i] . ".txt");
$title .= $temp . '|' . $key2;
$des .= $temp;
}
$arr_title = explode("|", $title);
$arr_title = arr_choas($arr_title, $choas_sp);
//按指纹乱序标题
$title = implode('|', $arr_title);
$title = preg_replace("%<[^>]+>%", ',', $title);
//防止网址中字母被匹配
$title = str_replace(array(',', '。', '：', '”', '“', '！', '……', '？', '；', ' ', '，'), '', $title);
$title = replace_db($title, '');
$title = substr_utf8($title, 0, 20);
$arr_title = explode("|", $title . '|' . $key);
$arr_title = arr_choas($arr_title, $choas_sp);
$title = implode('', $arr_title);
/*
* 确定描述
*/
if (rand(0, 10) > 7) {
$arr_des = explode('|', $des . '|' . $key2 . '|' . $key);
} else {
$arr_des = explode('|', $des . '|' . $key);
}
shuffle($arr_des);
$des = implode('', $arr_des);
$des = replace_dbs($des, '.');
$des = substr_utf8($des, 0, 500);
/*
* 返回
* $arr_res[]
*/
$arr_res = array();
$arr_res['title'] = $title;
$arr_res['des'] = $des;
return $arr_res;
}
function insertart($key, $keys, $a_no, $base_url)
{
global $cfg_xs_url;
$url = 'http://' . $base_url . 'reads-' . $a_no . 'html';
$md5_url = md5($url);
/*
* 生成指纹序列
* $body_sp:正文指纹序列
* $choas_sp:乱序指纹序列
*/
for ($i = 0; $i < 7; $i++) {
//标题取第1个,文章28个指纹序列
$body_sp[$i] = toTen(substr($md5_url, $i * 4, 4)) + 1;
$body_sp[$i + 7] = toTen(substr($md5_url, $i * 4 + 1, 4)) + 1;
$body_sp[$i + 14] = toTen(substr($md5_url, $i * 4 + 2, 4)) + 1;
$body_sp[$i + 21] = toTen(substr($md5_url, $i * 4 + 3, 4)) + 1;
}
$choas_sp = str_split(toTen(substr($md5_url, 0, 8)) . toTen(substr($md5_url, 8, 8)) . toTen(substr($md5_url, 16, 8)) . toTen(substr($md5_url, 24, 8)), 1);
/*
* 副关键词
*/
$arr_keys = explode(",", $keys);
$arr_keys = arr_choas($arr_keys, $choas_sp);
$key2 = $arr_keys[0];
/*
* 确定标题
* 选取第一个文章。
* 按指纹插入关键词。
*/
$title = file_get_contents($cfg_xs_url . $body_sp[0] . ".txt");
$body = $title;
$arr_title = explode("|", $title);
$arr_key = array($key, $key2);
$title = arr_insertkey($arr_title, $choas_sp, $arr_key, 1);
$title = preg_replace("%<[^>]+>%", ',', $title);
//防止网址中字母被匹配
$title = str_replace(array(',', '。', '：', '”', '“', '！', '……', '？', '；', ' ', '，'), '', $title);
$title = replace_db($title, '');
$title = substr_utf8($title, 0, 20);
/*
* 确定描述
* 选取28个文章。
* 按指纹插入关键词。
*/
for ($i = 0; $i < 28; $i++) {
$temp = file_get_contents($cfg_xs_url . $body_sp[$i] . ".txt");
$body .= '|' . $temp;
if ($i % 5 > 3) {
$body .= '<br>';
}
}
$arr_body = explode('|', $body);
$arr_key = explode(",", $key . ',' . $keys . ',' . $key . ',' . $key . ',' . $key);
$body = arr_insertkey($arr_body, $choas_sp, $arr_key, 10);
$body = replace_dbs($body, '.');
$body = str_replace(' ', '', $body);
//$body=substr_utf8($body,0,500);
/*
* 返回
* $arr_res[]
*/
$arr_res = array();
$arr_res['title'] = $title;
$arr_res['body'] = $body;
return $arr_res;
}
<?php
header('Content-type:text/html;charset=utf-8');
function substr_utf8($str, $start, $length = null)
{
$arr = preg_split("//u", $str, -1, PREG_SPLIT_NO_EMPTY);
var_dump($arr);
}
$str = '传智播客PHP学院';
substr_utf8($str);
function readart($key, $keys, $a_no, $base_url)
{
global $cfg_xs_url;
$url = 'http://' . $base_url . 'read-' . $a_no . 'html';
$md5_url = md5($url);
/*
* 生成指纹序列
* $art_sp:文章指纹序列
* $body_sp:正文指纹序列
* $choas_sp:乱序指纹序列
*/
for ($i = 0; $i < 7; $i++) {
//标题5个,文章28个指纹序列
$body_sp[$i] = toTen(substr($md5_url, $i * 4, 4)) + 1;
$body_sp[$i + 7] = toTen(substr($md5_url, $i * 4 + 1, 4)) + 1;
$body_sp[$i + 14] = toTen(substr($md5_url, $i * 4 + 2, 4)) + 1;
$body_sp[$i + 21] = toTen(substr($md5_url, $i * 4 + 3, 4)) + 1;
if ($i < 5) {
$art_sp[$i] = $body_sp[$i];
}
//标题文章序列
}
$choas_sp = str_split(toTen(substr($md5_url, 0, 8)) . toTen(substr($md5_url, 8, 8)) . toTen(substr($md5_url, 16, 8)) . toTen(substr($md5_url, 24, 8)), 1);
/*
* 副关键词
*/
$arr_keys = explode(",", $keys);
$arr_keys = arr_choas($arr_keys, $choas_sp);
$key2 = $arr_keys[0];
/*
* 确定标题
* 先从5个文本组合副关键词组合打乱一次
* 再提取20字符，加入主关键词打乱一次
*/
$title = '';
$des = '';
for ($i = 0; $i < 5; $i++) {
$temp = file_get_contents($cfg_xs_url . $art_sp[$i] . ".txt");
$title .= $temp . '|' . $key2;
}
$body = $title;
$arr_title = explode("|", $title);
$arr_title = arr_choas($arr_title, $choas_sp);
//按指纹乱序标题
$title = implode('|', $arr_title);
$title = preg_replace("%<[^>]+>%", ',', $title);
//防止网址中字母被匹配
$title = str_replace(array(',', '。', '：', '”', '“', '！', '……', '？', '；', ' ', '，'), '', $title);
$title = replace_db($title, '');
$title = substr_utf8($title, 0, 20);
$arr_title = explode("|", $title . '|' . $key);
$arr_title = arr_choas($arr_title, $choas_sp);
$title = implode('', $arr_title);
/*
* 确定正文
*/
for ($i = 5; $i < 28; $i++) {
$temp = file_get_contents($cfg_xs_url . $body_sp[$i] . ".txt");
$body .= '|' . $temp;
if ($i < 16) {
$body .= '|' . $key . '|' . '。<br>';
}
}
$arr_body = explode("|", $body);
$arr_body = arr_choas($arr_body, $choas_sp);
$body = implode('', $arr_body) . '。';
$body = replace_dbs($body, '。');
/*
* 返回
* $arr_res[]
*/
$arr_res = array();
$arr_res['title'] = $title;
$arr_res['body'] = $body;
return $arr_res;
}
{
return join("", array_slice(preg_split("//u", $str, -1, PREG_SPLIT_NO_EMPTY), $start, $lenth));
}
$str = '贾智超敬爱之巢';
echo substr_utf8($str, 2, 1);
echo "<br/>-----------------------------------------------------------------------------<br/>";
$str1 = '一二三四五六七吧九十';
echo mb_substr($str1, 2, 3);
echo "<br/>-----------------------------------------------------------------------------<br/>";
/**
* 求解字符串的字符数，
*/
$a = '中国2北333京';
echo mb_strlen($a, 'utf8');
//获取字符串长度
echo "<br/>";
echo mb_substr($a, 3, 1, 'utf8');
//截取字符串
/**
* 自定义函数实现求其长度
* @param $str String要计算的字符串
* @return int 字符串的长度
*/
echo "<br/>";
function strlen_utf8($str)
{
return count(preg_split('//u', $str, -1, PREG_SPLIT_NO_EMPTY));
}
$a = '中国2北343433京';
echo substr_utf8($a, 3, 1);
//生成taglink
$tagLink = '';
$arrTagKey = explode(',', $indexCache->tagKey);
foreach ($arrTagKey as $v) {
$tagEPath = GetEPath($v);
$arr = explode('/', $tagEPath);
$tagLink .= '<li><a href="http://' . $arr[0] . $indexCache->mainDomain . '/' . $arr[1] . '">' . $v . '</li>';
}
//替换数组
$arrReplace = array();
$arrReplace['key'] = $indexCache->key;
$arrReplace['keys'] = $indexCache->keys;
$arrReplace['title'] = $baidu->title;
$arrReplace['maintitle'] = $indexCache->title;
$arrReplace['adkey'] = $indexCache->adKey;
$arrReplace['keyslink'] = $keysLink;
$arrReplace['taglink'] = $tagLink;
if ($baidu->body == '') {
$arrReplace['body'] = '暂无数据，请等待。错误编码：' . md5($indexCache->baseUrl . $viewID);
} else {
$arrReplace['body'] = $baidu->body;
}
$arrReplace['body'] .= '您可能感兴趣：<br>' . $baidu->links;
$arrReplace['baseurl'] = $indexCache->baseUrl;
$description = preg_replace("%<[^>]+>%", ',', $baidu->description);
$description = substr_utf8($description, 0, 50);
$arrReplace['description'] = $description;
foreach ($arrReplace as $k => $v) {
$templets = str_replace('{' . $k . '}', $v, $templets);
}
echo $templets;
function messagecutstr($str, $length = 0, $dot = ' ...')
{
$str = messagesafeclear($str);
$sppos = strpos($str, chr(0) . chr(0) . chr(0));
if ($sppos !== false) {
$str = substr($str, 0, $sppos);
}
#loadcache(array('bbcodes_display', 'bbcodes', 'smileycodes', 'smilies', 'smileytypes', 'domainwhitelist'));
$bbcodes = 'b|i|u|p|color|size|font|align|list|indent|float';
$bbcodesclear = 'email|code|free|table|tr|td|img|swf|flash|attach|media|audio|groupid|payto';
$str = preg_replace("/\\[i=?.*?\\](.*?)\\[\\/i\\]/is", '', $str);
$str = strip_tags(preg_replace(array("/\\[hide=?\\d*\\](.*?)\\[\\/hide\\]/is", "/\\[quote](.*?)\\[\\/quote]/si", "/\\[url=?.*?\\](.+?)\\[\\/url\\]/si", "/\\[({$bbcodesclear})=?.*?\\](.*?)\\[\\/\\1\\]/si", "/\\[({$bbcodes})=?.*?\\]/i", "/\\[\\/({$bbcodes})\\]/i"), array('', '', '\\1', '', '', ''), $str));
if ($length) {
// $str = cutstr($str, $length, $dot);
$str = substr_utf8($str, 0, $length);
}
#$str = preg_replace($_G['cache']['smilies']['searcharray'], '', $str);
return trim($str);
}
