热搜:NVER node 开发 php

怎么取出百度某排行榜50条并在每条加前后缀呢

2024-08-16 10:45:01
怎么取出百度某排行榜50条并在每条加前后缀呢

如http://top.baidu.com/buzz?b=26&c=1&fr=topcategory_c1


回复讨论(解决方案)

已把主要???集成??,加前後?你想怎?加都可以了。

<?phpfunction getContent($url){	$ch = curl_init();	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);		curl_setopt($ch, CURLOPT_URL, $url);	$response = curl_exec($ch);	if($error=curl_error($ch)){		die($error);	}	curl_close($ch);	$content = iconv('GB2312','UTF8',$response);	return $content;}function getKeywords($content){	// keywords	preg_match_all('/(.*?)<\/td>/is', $content, $keywords);	$data = $keywords[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/a>/is', $val, $tmp);		array_push($result, array('name'=>$tmp[2][0],'url'=>'http://top.baidu.com'.substr($tmp[1][0],1)));	}	return $result;}function getTc($content){	// tc	preg_match_all('/(.*?)<\/td>/is', $content, $tc);	$data = $tc[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/a>/is', $val, $tmp);		array_push($result, array('brief'=>$tmp[1][0], 'news'=>$tmp[1][1], 'tieba'=>$tmp[1][2]));	}	return $result;}function getNum($content){	// last	preg_match_all('/(.*?)<\/td>/is', $content, $last); //icon-rise up icon-fall down	$data = $last[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/span>/is', $val, $tmp);		array_push($result, array('flag'=>str_replace('icon-','',$tmp[1][0]), 'num'=>$tmp[2][0]));	}	return $result;}$url = 'http://top.baidu.com/buzz?b=26&c=1&fr=topcategory_c1';$content = getContent($url);$result = array();$keywords = getKeywords($content);$tc = getTc($content);$num = getNum($content);for($i=0,$len=count($keywords); $i<$len; $i++){	$tmp = array(		'name' => $keywords[$i]['name'],		'url' => $keywords[$i]['url'],		'brief' => $tc[$i]['brief'],		'news' => $tc[$i]['news'],		'tieba' => $tc[$i]['tieba'],		'flag' => $num[$i]['flag'],		'num' => $num[$i]['num']	);	array_push($result, $tmp);}echo '
';print_r($result);echo '
';?>

?集后的??格式如下:

Array(    [0] => Array        (            [name] => 匆匆那年            [url] => http://top.baidu.com/detail?b=26&c=1&w=%B4%D2%B4%D2%C4%C7%C4%EA            [brief] => http://baike.baidu.com/search/word?word=%B4%D2%B4%D2%C4%C7%C4%EA            [news] => http://news.baidu.com/ns?tn=news&from=news&cl=2&rn=20&ct=1&word=%B4%D2%B4%D2%C4%C7%C4%EA            [tieba] => http://tieba.baidu.com/f?kw=%B4%D2%B4%D2%C4%C7%C4%EA            [flag] => rise            [num] => 162540        )    [1] => Array        (            [name] => 一个人的武林            [url] => http://top.baidu.com/detail?b=26&c=1&w=%D2%BB%B8%F6%C8%CB%B5%C4%CE%E4%C1%D6            [brief] => http://baike.baidu.com/search/word?word=%D2%BB%B8%F6%C8%CB%B5%C4%CE%E4%C1%D6            [news] => http://news.baidu.com/ns?tn=news&from=news&cl=2&rn=20&ct=1&word=%D2%BB%B8%F6%C8%CB%B5%C4%CE%E4%C1%D6            [tieba] => http://tieba.baidu.com/f?kw=%D2%BB%B8%F6%C8%CB%B5%C4%CE%E4%C1%D6            [flag] => rise            [num] => 75428        )    [2] => Array        (            [name] => 星际穿越            [url] => http://top.baidu.com/detail?b=26&c=1&w=%D0%C7%BC%CA%B4%A9%D4%BD            [brief] => http://baike.baidu.com/search/word?word=%D0%C7%BC%CA%B4%A9%D4%BD            [news] => http://news.baidu.com/ns?tn=news&from=news&cl=2&rn=20&ct=1&word=%D0%C7%BC%CA%B4%A9%D4%BD            [tieba] => http://tieba.baidu.com/f?kw=%D0%C7%BC%CA%B4%A9%D4%BD            [flag] => rise            [num] => 70538        )    [3] => Array        (            [name] => 心花路放            [url] => http://top.baidu.com/detail?b=26&c=1&w=%D0%C4%BB%A8%C2%B7%B7%C5            [brief] => http://baike.baidu.com/search/word?word=%D0%C4%BB%A8%C2%B7%B7%C5            [news] => http://news.baidu.com/ns?tn=news&from=news&cl=2&rn=20&ct=1&word=%D0%C4%BB%A8%C2%B7%B7%C5            [tieba] => http://tieba.baidu.com/f?kw=%D0%C4%BB%A8%C2%B7%B7%C5            [flag] => fall            [num] => 68233        )        。。。)

function getContent 修改?以下代?。

function getContent($url){	$ch = curl_init();	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);		curl_setopt($ch, CURLOPT_URL, $url);	curl_setopt($ch, CURLOPT_TIMEOUT, 300);	$response = curl_exec($ch);	if($error=curl_error($ch)){		die($error);	}	curl_close($ch);	$content = iconv('GB2312','UTF8//IGNORE',$response);	return $content;}

已把主要???集成??,加前後?你想怎?加都可以了。

<?phpfunction getContent($url){	$ch = curl_init();	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);		curl_setopt($ch, CURLOPT_URL, $url);	$response = curl_exec($ch);	if($error=curl_error($ch)){		die($error);	}	curl_close($ch);	$content = iconv('GB2312','UTF8',$response);	return $content;}function getKeywords($content){	// keywords	preg_match_all('/(.*?)<\/td>/is', $content, $keywords);	$data = $keywords[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/a>/is', $val, $tmp);		array_push($result, array('name'=>$tmp[2][0],'url'=>'http://top.baidu.com'.substr($tmp[1][0],1)));	}	return $result;}function getTc($content){	// tc	preg_match_all('/(.*?)<\/td>/is', $content, $tc);	$data = $tc[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/a>/is', $val, $tmp);		array_push($result, array('brief'=>$tmp[1][0], 'news'=>$tmp[1][1], 'tieba'=>$tmp[1][2]));	}	return $result;}function getNum($content){	// last	preg_match_all('/(.*?)<\/td>/is', $content, $last); //icon-rise up icon-fall down	$data = $last[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/span>/is', $val, $tmp);		array_push($result, array('flag'=>str_replace('icon-','',$tmp[1][0]), 'num'=>$tmp[2][0]));	}	return $result;}$url = 'http://top.baidu.com/buzz?b=26&c=1&fr=topcategory_c1';$content = getContent($url);$result = array();$keywords = getKeywords($content);$tc = getTc($content);$num = getNum($content);for($i=0,$len=count($keywords); $i<$len; $i++){	$tmp = array(		'name' => $keywords[$i]['name'],		'url' => $keywords[$i]['url'],		'brief' => $tc[$i]['brief'],		'news' => $tc[$i]['news'],		'tieba' => $tc[$i]['tieba'],		'flag' => $num[$i]['flag'],		'num' => $num[$i]['num']	);	array_push($result, $tmp);}echo '
';print_r($result);echo '
';?>


为什么我测试时,这个数组输出的是空的

你的php文件是否utf8

你的php文件是否utf8


是的

那你先把getContent的返回?出,看看有什?。

?了,你把????打?,如果白屏估?是??。你是否有安?curl?
在?面?加上
ini_set('display_errors','on');
error_reporting(E_ALL);
看看有什??。如果提示curl?有安?的,
可以改getContent?

function getContent($url){    $response = file_get_contents($url); // ?句代替curl     $content = iconv('GB2312','UTF8//IGNORE',$response);     return $content;}

什么都没输出
编码换成ANSI也不成

你测试可用的文件能打包的吗

Notice: iconv() [function.iconv]: Wrong charset, conversion from `GB2312' to `UTF8//IGNORE' is not allowed in F:\PHPnow-1.5.6\vhosts\test.php on line 15

$content = iconv('GB2312','UTF-8',$response);


这样就成了


问题我是个菜鸟,这个数组要怎么取出来正常使用呢

$content = iconv('GBK','UTF-8//IGNORE', $response);

Notice: iconv() [function.iconv]: Wrong charset, conversion from `GB2312' to `UTF8//IGNORE' is not allowed in F:\PHPnow-1.5.6\vhosts\test.php on line 15

$content = iconv('GB2312','UTF8//IGNORE',$response);
改?
$content = iconv('GBK','UTF8//IGNORE',$response);
??

拿到???不知道怎?用。。。呵呵。

你想?示的?子是怎?的,就做成怎?的html,然後在需要的地方,插入????。

数组一巧不同,郁闷了

其实我只要成这样就行的

匆匆那年匆匆那年匆匆那年匆匆那年匆匆那年

??出的完整例子,你好好??下。
中?你想改什?,直接改就可以了。

<?phpfunction getContent($url){	$ch = curl_init();	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);		curl_setopt($ch, CURLOPT_URL, $url);	curl_setopt($ch, CURLOPT_TIMEOUT, 300);	$response = curl_exec($ch);	if($error=curl_error($ch)){		die($error);	}	curl_close($ch);	$content = iconv('GBK','UTF-8//IGNORE',$response);	return $content;}function getKeywords($content){	// keywords	preg_match_all('/(.*?)<\/td>/is', $content, $keywords);	$data = $keywords[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/a>/is', $val, $tmp);		array_push($result, array('name'=>$tmp[2][0],'url'=>'http://top.baidu.com'.substr($tmp[1][0],1)));	}	return $result;}function getTc($content){	// tc	preg_match_all('/(.*?)<\/td>/is', $content, $tc);	$data = $tc[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/a>/is', $val, $tmp);		array_push($result, array('brief'=>$tmp[1][0], 'news'=>$tmp[1][1], 'tieba'=>$tmp[1][2]));	}	return $result;}function getNum($content){	// last	preg_match_all('/(.*?)<\/td>/is', $content, $last); //icon-rise up icon-fall down	$data = $last[1];	$result = array();	foreach($data as $val){		preg_match_all('/(.*?)<\/span>/is', $val, $tmp);		array_push($result, array('flag'=>str_replace('icon-','',$tmp[1][0]), 'num'=>$tmp[2][0]));	}	return $result;}$url = 'http://top.baidu.com/buzz?b=340&c=1&fr=topbuzz_b339_c1';$content = getContent($url);$result = array();$keywords = getKeywords($content);$tc = getTc($content);$num = getNum($content);for($i=0,$len=count($keywords); $i<$len; $i++){	$tmp = array(		'name' => $keywords[$i]['name'],		'url' => $keywords[$i]['url'],		'brief' => $tc[$i]['brief'],		'news' => $tc[$i]['news'],		'tieba' => $tc[$i]['tieba'],		'flag' => $num[$i]['flag'],		'num' => $num[$i]['num']	);	array_push($result, $tmp);}?>      baidu   		<?php	$i = 1;	foreach($result as $val){	?>		<?php		$i++;	}	?>	
<?=$i ?> "><?=$val['name'] ?> ">?介 ">新? ">?吧 <?php if($val['flag']=='fall'){ echo '↓'; }else{echo '↑'; } ?><?=$val['num'] ?>