1. 程式人生 > 其它 >php採集頁面指定標籤裡面的內容

php採集頁面指定標籤裡面的內容

/*
* 引數說明: $tag_id:所要獲取的元素Tag Id $url:所要獲取頁面的Url $tag:所要獲取的標籤 $data
*/
function getWebTag($tag_id, $url = false, $tag = 'div', $data = false) {
    if ($url !== false) {
        $data = file_get_contents ( $url );
    }
    $charset_pos = stripos ( $data, 'charset' );
    if ($charset_pos) {
        if
(stripos ( $data, 'utf-8', $charset_pos )) { $data = iconv ( 'utf-8', 'utf-8', $data ); } else if (stripos ( $data, 'gb2312', $charset_pos )) { $data = iconv ( 'gb2312', 'utf-8', $data ); } else if (stripos ( $data, 'gbk', $charset_pos )) { $data = iconv
( 'gbk', 'utf-8', $data ); } } preg_match_all ( '/<' . $tag . '/i', $data, $pre_matches, PREG_OFFSET_CAPTURE ); // 獲取所有div字首 preg_match_all ( '/<\/' . $tag . '/i', $data, $suf_matches, PREG_OFFSET_CAPTURE ); // 獲取所有div字尾 $hit = strpos ( $data, $tag_id ); if ($hit == - 1)
return false; // 未命中 $divs = array (); // 合併所有div foreach ( $pre_matches [0] as $index => $pre_div ) { $divs [( int ) $pre_div [1]] = 'p'; $divs [( int ) $suf_matches [0] [$index] [1]] = 's'; } // 對div進行排序 $sort = array_keys ( $divs ); asort ( $sort ); $count = count ( $pre_matches [0] ); foreach ( $pre_matches [0] as $index => $pre_div ) { // <div $hit <div+1 時div被命中 if (($pre_matches [0] [$index] [1] < $hit) && ($hit < $pre_matches [0] [$index + 1] [1])) { $deeper = 0; // 彈出被命中div前的div while ( array_shift ( $sort ) != $pre_matches [0] [$index] [1] && ($count --) ) continue; // 對剩餘div進行匹配,若下一個為字首,則向下一層,$deeper加1, // 否則後退一層,$deeper減1,$deeper為0則命中匹配,計算div長度 foreach ( $sort as $key ) { if ($divs [$key] == 'p') $deeper ++; else if ($deeper == 0) { $length = $key - $pre_matches [0] [$index] [1]; break; } else { $deeper --; } } $hitDivString = substr ( $data, $pre_matches [0] [$index] [1], $length ) . '</' . $tag . '>'; break; } } return $hitDivString; } echo getWebTag ( 'id="content"', 'http://www.cdlyh.com/article/read/id/12345.html', 'div' );