php抓取这个网页的数据,只要数据,不要html内容,然后json后写入文件,新手求教

yanfangphp 2014-07-22 03:48:44
http://www.okooo.com/Upload/sohu/table_23.html
新收求教啊,这个难度在于正则上,不会写正则啊
...全文
363 4 打赏 收藏 转发到动态 举报
写回复
用AI写文章
4 条回复
切换为时间正序
请发表友善的回复…
发表回复
yanfangphp 2014-07-23
  • 打赏
  • 举报
回复
引用 1 楼 xuzuning 的回复:
$url = 'http://www.okooo.com/Upload/sohu/table_23.html';
$s = file_get_contents($url);
preg_match_all('#<table.+</table>#isU', $s, $m);
foreach(array_map('strip_tags', $m[0]) as $r) {
  $a = preg_split('/\s+/', $r, -1, PREG_SPLIT_NO_EMPTY);
  $res[] = array_chunk(array_slice($a, 0, -1), 3);
}
写文件你就自己练练手吧 就一个 file_put_contents 函数
哦 明白了 正则太弱了,想攻破,但是没信心啊
yanfangphp 2014-07-23
  • 打赏
  • 举报
回复
引用 1 楼 xuzuning 的回复:
$url = 'http://www.okooo.com/Upload/sohu/table_23.html';
$s = file_get_contents($url);
preg_match_all('#<table.+</table>#isU', $s, $m);
foreach(array_map('strip_tags', $m[0]) as $r) {
  $a = preg_split('/\s+/', $r, -1, PREG_SPLIT_NO_EMPTY);
  $res[] = array_chunk(array_slice($a, 0, -1), 3);
}

写文件你就自己练练手吧 就一个 file_put_contents 函数
array_map('strip_tags', $m[0]) 这个里边strip_tags在哪里定义的,他代表的不是自定义函数吗?
漫漫2009 2014-07-22
  • 打赏
  • 举报
回复
也不是非得用正则,试试用DOM处理,搜下Simple HTML DOM看
xuzuning 2014-07-22
  • 打赏
  • 举报
回复
$url = 'http://www.okooo.com/Upload/sohu/table_23.html';
$s = file_get_contents($url);
preg_match_all('#<table.+</table>#isU', $s, $m);
foreach(array_map('strip_tags', $m[0]) as $r) {
  $a = preg_split('/\s+/', $r, -1, PREG_SPLIT_NO_EMPTY);
  $res[] = array_chunk(array_slice($a, 0, -1), 3);
}
print_r($res);
echo json_encode($res);
Array
(
    [0] => Array
        (
            [0] => Array
                (
                    [0] => 排名
                    [1] => 球队
                    [2] => 积分
                )

            [1] => Array
                (
                    [0] => 1
                    [1] => 尤文图斯
                    [2] => 102
                )

            [2] => Array
                (
                    [0] => 2
                    [1] => 罗马
                    [2] => 85
                )

            [3] => Array
                (
                    [0] => 3
                    [1] => 那不勒斯
                    [2] => 78
                )

            [4] => Array
                (
                    [0] => 4
                    [1] => 佛罗伦萨
                    [2] => 65
                )

            [5] => Array
                (
                    [0] => 5
                    [1] => 国际米兰
                    [2] => 60
                )

            [6] => Array
                (
                    [0] => 6
                    [1] => 帕尔马
                    [2] => 58
                )

            [7] => Array
                (
                    [0] => 7
                    [1] => 都灵
                    [2] => 57
                )

            [8] => Array
                (
                    [0] => 8
                    [1] => AC米兰
                    [2] => 57
                )

            [9] => Array
                (
                    [0] => 9
                    [1] => 拉齐奥
                    [2] => 56
                )

            [10] => Array
                (
                    [0] => 10
                    [1] => 维罗纳
                    [2] => 54
                )

        )

    [1] => Array
        (
            [0] => Array
                (
                    [0] => 进球数
                    [1] => 球员
                    [2] => 球队
                )

            [1] => Array
                (
                    [0] => 22
                    [1] => 伊莫比莱
                    [2] => 都灵
                )

            [2] => Array
                (
                    [0] => 20
                    [1] => 托尼
                    [2] => 维罗纳
                )

            [3] => Array
                (
                    [0] => 19
                    [1] => 特维斯
                    [2] => 尤文图斯
                )

            [4] => Array
                (
                    [0] => 17
                    [1] => 帕拉西奥
                    [2] => 国际米兰
                )

            [5] => Array
                (
                    [0] => 17
                    [1] => 伊瓜因
                    [2] => 那不勒斯
                )

            [6] => Array
                (
                    [0] => 16
                    [1] => 略伦特
                    [2] => 尤文图斯
                )

            [7] => Array
                (
                    [0] => 16
                    [1] => 迪纳塔莱
                    [2] => 乌迪内斯
                )

            [8] => Array
                (
                    [0] => 16
                    [1] => 朱塞佩·罗西
                    [2] => 佛罗伦萨
                )

            [9] => Array
                (
                    [0] => 16
                    [1] => 贝拉尔迪
                    [2] => 莎索罗
                )

            [10] => Array
                (
                    [0] => 15
                    [1] => 卡列洪
                    [2] => 那不勒斯
                )

        )

)
[[["\u6392\u540d","\u7403\u961f","\u79ef\u5206"],["1","\u5c24\u6587\u56fe\u65af","102"],["2","\u7f57\u9a6c","85"],["3","\u90a3\u4e0d\u52d2\u65af","78"],["4","\u4f5b\u7f57\u4f26\u8428","65"],["5","\u56fd\u9645\u7c73\u5170","60"],["6","\u5e15\u5c14\u9a6c","58"],["7","\u90fd\u7075","57"],["8","AC\u7c73\u5170","57"],["9","\u62c9\u9f50\u5965","56"],["10","\u7ef4\u7f57\u7eb3","54"]],[["\u8fdb\u7403\u6570","\u7403\u5458","\u7403\u961f"],["22","\u4f0a\u83ab\u6bd4\u83b1","\u90fd\u7075"],["20","\u6258\u5c3c","\u7ef4\u7f57\u7eb3"],["19","\u7279\u7ef4\u65af","\u5c24\u6587\u56fe\u65af"],["17","\u5e15\u62c9\u897f\u5965","\u56fd\u9645\u7c73\u5170"],["17","\u4f0a\u74dc\u56e0","\u90a3\u4e0d\u52d2\u65af"],["16","\u7565\u4f26\u7279","\u5c24\u6587\u56fe\u65af"],["16","\u8fea\u7eb3\u5854\u83b1","\u4e4c\u8fea\u5185\u65af"],["16","\u6731\u585e\u4f69\u00b7\u7f57\u897f","\u4f5b\u7f57\u4f26\u8428"],["16","\u8d1d\u62c9\u5c14\u8fea","\u838e\u7d22\u7f57"],["15","\u5361\u5217\u6d2a","\u90a3\u4e0d\u52d2\u65af"]]]
写文件你就自己练练手吧 就一个 file_put_contents 函数

21,886

社区成员

发帖
与我相关
我的任务
社区描述
从PHP安装配置,PHP入门,PHP基础到PHP应用
社区管理员
  • 基础编程社区
加入社区
  • 近7日
  • 近30日
  • 至今
社区公告
暂无公告

试试用AI创作助手写篇文章吧