好的,所以 preg_match_all 对雅虎不起作用。
我正在尝试 preg_match_all 使用 cURL curl_multi_getcontent 方法从 Yahoo 获得的结果。
我已成功获取该站点等,但是当我尝试获取链接的结果时,它不会匹配任何内容。当我在 Notepad++ 中使用正则表达式时,它成功但显然不是在 PHP 中。
我目前正在使用:
preg_match_all(
'#<span class="url" id="(.*?)">(.+?)</span>#si', $urlContents[2], $yahoo
);
例如,检查 HTML,[http://se.search.yahoo.com/search?p=random&toggle=1&cop=mss&ei=UTF-8&fr=yfp-t][1]
您会看到所有链接都以 . 开头<span class="url" id="something random">
和结尾</span>
。
有人可以帮助我如何检索这些信息吗?我只需要每个结果的实际链接地址。
整个 PHP 脚本
public function multiSearch($question)
{
$sites['google'] = "http://www.google.com/search?q={$question}&gl=sv";
$sites['bing'] = "http://www.bing.com/search?q={$question}";
$sites['yahoo'] = "http://se.search.yahoo.com/search?p={$question}";
$urlHandler = array();
foreach($sites as $site)
{
$handler = curl_init();
curl_setopt($handler, CURLOPT_URL, $site);
curl_setopt($handler, CURLOPT_HEADER, 0);
curl_setopt($handler, CURLOPT_RETURNTRANSFER, 1);
array_push($urlHandler, $handler);
}
$multiHandler = curl_multi_init();
foreach($urlHandler as $key => $url)
{
curl_multi_add_handle($multiHandler, $url);
}
$running = null;
do
{
curl_multi_exec($multiHandler, $running);
}
while($running > 0);
$urlContents = array();
foreach($urlHandler as $key => $url)
{
$urlContents[$key] = curl_multi_getcontent($url);
}
foreach($urlHandler as $key => $url)
{
curl_multi_remove_handle($multiHandler, $url);
}
foreach($urlContents as $urlContent)
{
preg_match_all('/<li class="g">(.*?)<\/li>/si', $urlContent, $matches);
//$this->view_data['results'][] = "Random";
}
preg_match_all('#<cite>(.+?)</cite>#si', $urlContents[1], $googleLinks);
preg_match_all('#<span class="url" id="(.*)">(.+?)</span>#si', $urlContents[2], $yahoo);
var_dump($yahoo);
die();
$findHtml = array('/<cite>/', '/<\/cite>/', '/<b>/', '/<\/b>/', '/ /', '/"/', '/<strong>/', '/<\/strong>/');
$removeHtml = array('', '', '', '', '', '', '', '');
foreach($googleLinks as $links => $val)
{
foreach($val as $link)
$this->view_data['results'][] = preg_replace($findHtml, $removeHtml, $link);
break;
}
}