Notice (8): file_put_contents(): Write of 270 bytes failed with errno=28 No space left on device [CORE/src/Log/Engine/FileLog.php, line 140]

        if (!$mask) {
            file_put_contents($pathname, $message . "\n", FILE_APPEND);

file_put_contents - [internal], line ??
Cake\Log\Engine\FileLog::log() - CORE/src/Log/Engine/FileLog.php, line 140
Cake\Log\Log::write() - CORE/src/Log/Log.php, line 392
Cake\Log\Log::warning() - CORE/src/Log/Log.php, line 477
DebugKit\ToolbarService::isSuspiciouslyProduction() - ROOT/vendor/cakephp/debug_kit/src/ToolbarService.php, line 169
DebugKit\ToolbarService::isEnabled() - ROOT/vendor/cakephp/debug_kit/src/ToolbarService.php, line 105
DebugKit\Plugin::bootstrap() - ROOT/vendor/cakephp/debug_kit/src/Plugin.php, line 48
Cake\Http\BaseApplication::pluginBootstrap() - CORE/src/Http/BaseApplication.php, line 182
Cake\Http\Server::bootstrap() - CORE/src/Http/Server.php, line 111
Cake\Http\Server::run() - CORE/src/Http/Server.php, line 79
[main] - ROOT/webroot/index.php, line 40

Notice (8): SplFileObject::fwrite() [<a href='https://secure.php.net/splfileobject.fwrite'>splfileobject.fwrite</a>]: Write of 5131 bytes failed with errno=28 No space left on device [CORE/src/Cache/Engine/FileEngine.php, line 141]

Code Context

        $success = $this->_File->ftruncate(0) &&
            $this->_File->fwrite($contents) &&
            $this->_File->fflush();

SplFileObject::fwrite() - [internal], line ??
Cake\Cache\Engine\FileEngine::set() - CORE/src/Cache/Engine/FileEngine.php, line 141
Cake\Database\Schema\CachedCollection::describe() - CORE/src/Database/Schema/CachedCollection.php, line 85
Cake\ORM\Table::getSchema() - CORE/src/ORM/Table.php, line 513
Cake\ORM\Query::addDefaultTypes() - CORE/src/ORM/Query.php, line 290
Cake\ORM\Query::__construct() - CORE/src/ORM/Query.php, line 184
Cake\ORM\Table::query() - CORE/src/ORM/Table.php, line 1702
Cake\ORM\Table::find() - CORE/src/ORM/Table.php, line 1263
App\Controller\NewsController::action_() - APP/Controller/NewsController.php, line 6437
App\Controller\NewsController::get_data() - APP/Controller/NewsController.php, line 5701
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5625
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3226
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317

Notice (8): SplFileObject::fwrite() [<a href='https://secure.php.net/splfileobject.fwrite'>splfileobject.fwrite</a>]: Write of 114 bytes failed with errno=28 No space left on device [CORE/src/Cache/Engine/FileEngine.php, line 141]

Code Context

        $success = $this->_File->ftruncate(0) &&
            $this->_File->fwrite($contents) &&
            $this->_File->fflush();

SplFileObject::fwrite() - [internal], line ??
Cake\Cache\Engine\FileEngine::set() - CORE/src/Cache/Engine/FileEngine.php, line 141
Cake\Cache\Cache::write() - CORE/src/Cache/Cache.php, line 266
App\Controller\NewsController::action_() - APP/Controller/NewsController.php, line 6766
App\Controller\NewsController::get_data() - APP/Controller/NewsController.php, line 5701
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5625
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3634
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 77
Cake\Http\Middleware\CsrfProtectionMiddleware::process() - CORE/src/Http/Middleware/CsrfProtectionMiddleware.php, line 164
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\I18n\Middleware\LocaleSelectorMiddleware::process() - CORE/src/I18n/Middleware/LocaleSelectorMiddleware.php, line 61
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73

Warning (512): long cache was unable to write 'dd555357217bf27ac1330a08f2725a09' to Cake\Cache\Engine\FileEngine cache [CORE/src/Cache/Cache.php, line 275]

Code Context

                ),
                E_USER_WARNING
            );

Cake\Cache\Cache::write() - CORE/src/Cache/Cache.php, line 275
App\Controller\NewsController::action_() - APP/Controller/NewsController.php, line 6766
App\Controller\NewsController::get_data() - APP/Controller/NewsController.php, line 5701
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5625
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3634
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 77
Cake\Http\Middleware\CsrfProtectionMiddleware::process() - CORE/src/Http/Middleware/CsrfProtectionMiddleware.php, line 164
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\I18n\Middleware\LocaleSelectorMiddleware::process() - CORE/src/I18n/Middleware/LocaleSelectorMiddleware.php, line 61
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\Http\Middleware\BodyParserMiddleware::process() - CORE/src/Http/Middleware/BodyParserMiddleware.php, line 157

Notice (8): SplFileObject::fwrite() [<a href='https://secure.php.net/splfileobject.fwrite'>splfileobject.fwrite</a>]: Write of 111 bytes failed with errno=28 No space left on device [CORE/src/Cache/Engine/FileEngine.php, line 141]

Code Context

        $success = $this->_File->ftruncate(0) &&
            $this->_File->fwrite($contents) &&
            $this->_File->fflush();

SplFileObject::fwrite() - [internal], line ??
Cake\Cache\Engine\FileEngine::set() - CORE/src/Cache/Engine/FileEngine.php, line 141
Cake\Cache\Cache::write() - CORE/src/Cache/Cache.php, line 266
App\Controller\NewsController::action_() - APP/Controller/NewsController.php, line 6766
App\Controller\NewsController::get_data() - APP/Controller/NewsController.php, line 5701
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5625
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3663
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 77
Cake\Http\Middleware\CsrfProtectionMiddleware::process() - CORE/src/Http/Middleware/CsrfProtectionMiddleware.php, line 164
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\I18n\Middleware\LocaleSelectorMiddleware::process() - CORE/src/I18n/Middleware/LocaleSelectorMiddleware.php, line 61
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73

Warning (512): long cache was unable to write 'de3a572e5a94ea9294d8c765a1b3d126' to Cake\Cache\Engine\FileEngine cache [CORE/src/Cache/Cache.php, line 275]

Code Context

                ),
                E_USER_WARNING
            );

Cake\Cache\Cache::write() - CORE/src/Cache/Cache.php, line 275
App\Controller\NewsController::action_() - APP/Controller/NewsController.php, line 6766
App\Controller\NewsController::get_data() - APP/Controller/NewsController.php, line 5701
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5625
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3663
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 77
Cake\Http\Middleware\CsrfProtectionMiddleware::process() - CORE/src/Http/Middleware/CsrfProtectionMiddleware.php, line 164
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\I18n\Middleware\LocaleSelectorMiddleware::process() - CORE/src/I18n/Middleware/LocaleSelectorMiddleware.php, line 61
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\Http\Middleware\BodyParserMiddleware::process() - CORE/src/Http/Middleware/BodyParserMiddleware.php, line 157

Notice (8): unserialize() [<a href='https://secure.php.net/function.unserialize'>function.unserialize</a>]: Error at offset 85980 of 86005 bytes [APP/Controller/NewsController.php, line 5571]

Code Context

               {
                      $a=unserialize($line2);
               }

unserialize - [internal], line ??
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5571
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::article_show() - APP/Controller/NewsController.php, line 4290
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3822
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 77
Cake\Http\Middleware\CsrfProtectionMiddleware::process() - CORE/src/Http/Middleware/CsrfProtectionMiddleware.php, line 164
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\I18n\Middleware\LocaleSelectorMiddleware::process() - CORE/src/I18n/Middleware/LocaleSelectorMiddleware.php, line 61
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\Http\Middleware\BodyParserMiddleware::process() - CORE/src/Http/Middleware/BodyParserMiddleware.php, line 157
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\Routing\Middleware\RoutingMiddleware::process() - CORE/src/Routing/Middleware/RoutingMiddleware.php, line 161

Notice (8): unserialize() [<a href='https://secure.php.net/function.unserialize'>function.unserialize</a>]: Error at offset 90093 of 90101 bytes [APP/Controller/NewsController.php, line 5571]

Code Context

               {
                      $a=unserialize($line2);
               }

unserialize - [internal], line ??
App\Controller\NewsController::action_cache() - APP/Controller/NewsController.php, line 5571
App\Controller\NewsController::cache_action() - APP/Controller/NewsController.php, line 5281
App\Controller\NewsController::article_show() - APP/Controller/NewsController.php, line 4310
App\Controller\NewsController::view() - APP/Controller/NewsController.php, line 3822
Cake\Controller\Controller::invokeAction() - CORE/src/Controller/Controller.php, line 539
Cake\Controller\ControllerFactory::handle() - CORE/src/Controller/ControllerFactory.php, line 140
Cake\Controller\ControllerFactory::invoke() - CORE/src/Controller/ControllerFactory.php, line 115
Cake\Http\BaseApplication::handle() - CORE/src/Http/BaseApplication.php, line 317
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 77
Cake\Http\Middleware\CsrfProtectionMiddleware::process() - CORE/src/Http/Middleware/CsrfProtectionMiddleware.php, line 164
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\I18n\Middleware\LocaleSelectorMiddleware::process() - CORE/src/I18n/Middleware/LocaleSelectorMiddleware.php, line 61
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\Http\Middleware\BodyParserMiddleware::process() - CORE/src/Http/Middleware/BodyParserMiddleware.php, line 157
Cake\Http\Runner::handle() - CORE/src/Http/Runner.php, line 73
Cake\Routing\Middleware\RoutingMiddleware::process() - CORE/src/Routing/Middleware/RoutingMiddleware.php, line 161

PHP 采集原理思路

PHP 2014-12-08 10:33:03 转载来源: 网络整理/侵权必删

本文为大家讲解的是php在开发采集程序时的原理和思路，感兴趣的同学参考下。由于需要，要写一个简单的PHP采集程序，照例是到网上找了一堆教程，然后照猫画虎，可是发现网上的教程全是似是而非，没有一个真正能用的

本文为大家讲解的是php在开发采集程序时的原理和思路，感兴趣的同学参考下。

由于需要，要写一个简单的PHP采集程序，照例是到网上找了一堆教程，然后照猫画虎，可是发现网上的教程全是似是而非，没有一个真正能用的。

苦想了几天，终于弄明白了里面的道理。在这里写出来，请高手指正。
采集程序的思路很简单，无非就是先打一个页面，一般都是列表页，取得里面全部链接的地址，然后打开逐条链接，寻找我们感兴趣的东西，如果找到，就把它入库或别的处理。下面以一个很简单的例子来说说。

首先确定一个采集页，一般就是列表面了。这里目标是:http://www.phperz.com。这是一个列表页，我们的目的就是采集这个列表页上全部的文章。

有列表页了，第一步先打开它，把它的内容纳入到我们的程序中来。一般用fopen或是file_get_contents这两个函数，我们这里用fopen作例子。怎么打开它呢？很简单：$source=fopen("http://www.phperz.com",'r')；实际上已经把内容纳入到我们的程序中来了。注意得到的$source是一个资源，不是可处理的文本，所以再用函数fread将内容读到一个变量中，这次就是真正的可编辑的文本了。

例子：
$content=fread($source,99999);后面的数字表示字节数，填个大的就行。你用file_put_contents将$content写入到一个文本文件，可以看出里面的内容其实就是网页的源码。

得到了网页的源码，我们就要分析里面的文章链接地址，这里要用到正则表达式了，通过查看源代码，我们可以看到里面文章的链接地址全是这个样子<div class="in_arttitle"><a href="http://www.phperz.com/article/10/1022/273.html">

将数据库连接代码封装在函数里，在需要读取时调用..</a>
我们就可以写正则表达式了。$count=preg_match_all("/<div class="in_arttitle"><ashref="(.+?)">(.+?)</a>/",$content,$art_list);
其中数组$art_list[1][$s]里面包含的就是某个文章的链接地址。而$art_list[2][$s]包含的就是某一文章的标题。到了这一步就可以算成功了一半了。

接着用for循环依次打每个链接，然后像取得标题一样的方法取得内容即可。以上这些和我在网上找的教程都差不多，但是到了这个for循环网上的教程可就差劲，还没找到一篇可以说清这个事的文章，刚开始我是用js来帮助循环的，还是用实例说吧，刚开始我是这样做的：
for($i=0;$i<20;4i++ {
中间就是采集内容的部分了，省略了
采集了一页，肯定要采集再一页啊
可是再用fopen打开链接时就不行了。请求失败什么的，用js也不行，最后才知道要用这句echo "<META HTTP-EQUIV=REFRESH CONTENT='0;URL=aa.php?id=1'>";其中aa.php就是我们的程序的文件名， id后面的数字就可以帮助我们实现循环，采集多个页面。这就是能真正循环起来的关键
}
脑子有点难受，写得有点乱，将就着看吧，在高手看来这可能没什么大不了的，可是对于我等菜鸟来说，实在是很有帮助。

标签: PHP 采集原理思路