本文整理汇总了PHP中Symfony\Component\DomCrawler\Crawler::addHtmlContent方法的典型用法代码示例。如果您正苦于以下问题：PHP Crawler::addHtmlContent方法的具体用法？PHP Crawler::addHtmlContent怎么用？PHP Crawler::addHtmlContent使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Symfony\Component\DomCrawler\Crawler的用法示例。
在下文中一共展示了Crawler::addHtmlContent方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的PHP代码示例。
示例1: process
/**
* Process the DOM
*
* @return array
* @throws Exception
*/
public function process()
{
// Check if HTML content is already set
$this->checkIfContentIsEmpty($this->html);
$items = [];
$total = 0;
$prepareItems = function (Crawler $nodeCrawler, $i) use(&$items, &$total) {
$title = $nodeCrawler->filter('h3 > a');
$link = $nodeCrawler->filter('h3 > a')->attr('href');
$price = $nodeCrawler->filter('p.pricePerUnit')->text();
$descriptionPage = $this->fetch($link);
//prepare items array
$items[$i]['title'] = trim($title->text());
$items[$i]['size'] = $this->sizeOf($descriptionPage);
$items[$i]['unit_price'] = $this->format($price);
$items[$i]['description'] = $this->getDescriptionFor($descriptionPage);
$total += $items[$i]['unit_price'];
};
// bind the closure to the object context
// so we can access the object inside the closure
$prepareItems->bindTo($this);
$this->domCrawler->addHtmlContent($this->html);
$this->domCrawler->filter('ul.productLister > li')->each($prepareItems);
$this->items = $items;
$this->total = number_format($total, 2);
unset($items);
unset($total);
return ['items' => $this->items, 'total' => $this->total];
}示例2: setUp
public function setUp()
{
$this->selectorProvider = new SelectorProvider();
$this->crawler = new Crawler();
$this->crawler->addHtmlContent($this->getValidHtml());
$this->itemsCssSelector = '.list-group .list-group-item';
$this->noItemsCssSelector = '.not-existing-class';
}示例3: setUp
public function setUp()
{
$this->listSelector = new Css(".list-group .list-group-item");
$this->emptyResultSelector = new Css(".non-existing");
$this->emptySelector = new Css("");
$this->crawler = new Crawler();
$this->crawler->addHtmlContent($this->getValidHtml());
}示例4: testAddHtmlContent
/**
* @covers Symfony\Component\DomCrawler\Crawler::addHtmlContent
*/
public function testAddHtmlContent()
{
$crawler = new Crawler();
$crawler->addHtmlContent('<html><div class="foo"></html>', 'UTF-8');
$this->assertEquals('foo', $crawler->filter('div')->attr('class'), '->addHtmlContent() adds nodes from an HTML string');
$crawler->addHtmlContent('<html><head><base href="http://symfony.com"></head><a href="/contact"></a></html>', 'UTF-8');
$this->assertEquals('http://symfony.com', $crawler->filter('base')->attr('href'), '->addHtmlContent() adds nodes from an HTML string');
$this->assertEquals('http://symfony.com/contact', $crawler->filter('a')->link()->getUri(), '->addHtmlContent() adds nodes from an HTML string');
}示例5: setUp
public function setUp()
{
$this->validCorrectPattern = '/user-(?P<value>\\d+)/';
$this->validNoMatchPattern = '/NO-MATCH_STRING-(?P<value>\\d+)/';
$this->validPatternWrongParam = '/NO-MATCH_STRING-(?P<wrong>\\d+)/';
$this->invalidPattern = '/$%#$>\\d+)))/';
$this->selectorProvider = new SelectorProvider();
$this->crawler = new Crawler();
$this->crawler->addHtmlContent($this->getValidHtml());
$this->itemCssSelector = '.list-group .list-group-item';
//will select first
$this->noItemsCssSelector = '.not-existing-class';
}示例6: extract
/**
* @param string $url
* @param array $tags
*
* @return WatchLink
*/
public function extract(string $url, array $tags) : WatchLink
{
$watchLink = new WatchLink();
$watchLink->setUrl($url);
$this->crawler->clear();
$this->crawler->addHtmlContent($this->fetcher->fetch($url));
$watchLink->setName($this->extractTitle());
$watchLink->setDescription($this->extractDescription());
$watchLink->setImage($this->extractImage());
foreach ($tags as $tag) {
$watchLink->addTag($this->tagRepository->findOrCreate($tag));
}
return $watchLink;
}示例7: filterPrice
/**
* Filter the price present on each countries price page, and return the price
*
* @param string $content
*
* @return string $price
*/
public function filterPrice($content)
{
$crawler = new Crawler();
$crawler->addHtmlContent($content);
$price = $crawler->filterXPath("html/body/div[1]/div[3]/div/div/div[3]/div[4]/div/table/tr[1]/td[2]")->extract('_text', 'td');
return trim($price[0]);
}示例8: transform
public function transform($category_page_url, $pretty_print_json = false)
{
$crawler = new Crawler();
/** loads the initial category page into a Crawler */
$crawler->addHtmlContent($this->page_manager->getPage($category_page_url), 'ISO-8859-1');
$category_page = new CategoryPage($crawler);
$product_collection = new ProductCollection();
/** loops through all the products on the category page */
/** @todo handle cases where HTML structure throws out the crawler more elegantly */
$category_page->getProducts()->each(function (Crawler $category_page_product_node, $i) use($product_collection) {
try {
$product_node = new CategoryPageProductNode($category_page_product_node);
$url_of_product_page = $product_node->getProductHref();
$crawler = new Crawler();
/** loads the product page */
$crawler->addHtmlContent($this->page_manager->getPage($url_of_product_page), 'ISO-8859-1');
$product_page = new ProductPage($crawler);
$product = new Product();
/** gets the content from either the product or category page and saves it in the product entity */
$product->setTitle($product_node->getTitle())->setDescription($product_page->getDescription())->setUnitPrice($product_node->getUnitPrice())->setSize($this->page_manager->getSizeOfPage($url_of_product_page));
$product_collection->addProduct($product);
} catch (\InvalidArgumentException $ex) {
}
});
/** Combines the results with the total of all the unit prices */
return json_encode(['results' => $product_collection->toArray(), 'total' => $product_collection->getSumOfUnitPrices() / 100], $pretty_print_json ? JSON_PRETTY_PRINT : 0);
}示例9: actionTrypostdata
/**
* simulate worldjournal ajax call to fetch content data
*/
public function actionTrypostdata()
{
$hostname = 'www.wjlife.com';
$optionVaules = ["relation" => "AND", "0" => ["relation" => "AND", "0" => ["key" => "wj_order_id"]]];
//all help wanted
$currentURL = "/cls_category/03-ny-help-wanted/";
//temp page number
$pno = 0;
$queryObject = ["keyword" => "", "pagesize" => 40, "pno" => $pno, "optionVaules" => $optionVaules, "currentURL" => "http://" . $hostname . $currentURL, "currentCatId" => 327, "currentStateId" => 152];
//language: chinese simplified
$wjlang = "zh-cn";
$requestUrl = "http://" . $hostname . "/wp-content/themes/wjlife/includes/classified-core.php?regions=state_ny&variant=" . $wjlang . "&t=" . time();
// echo "start...\n";
$client = new Client();
$crawler = $client->request("POST", $requestUrl, $queryObject, [], ['HTTP_X-Requested-With' => 'XMLHttpRequest', 'contentType' => 'application/x-www-form-urlencoded;charset=utf-8']);
$rowHtml = $crawler->html();
// if you want to echo out with correct encoding, do `echo utf8_decode($rowHtml)`
// echo utf8_decode($rowHtml);
// echo "end...\n";
$subCrawler = new Crawler();
$subCrawler->addHtmlContent($rowHtml);
$linkArray = $subCrawler->filter(".catDesc a")->each(function ($node, $index) {
return $href = $node->attr('href');
});
print_r($linkArray);
}示例10: setUp
public function setUp()
{
$html = file_get_contents(__DIR__ . '/../Fixtures/category-page-product-node.html');
$crawler = new Crawler();
$crawler->addHtmlContent($html, 'ISO-8859-1');
$this->SUT = new SUT($crawler);
}示例11: inlineImages
/**
* Replace all src of img.inline-image with an embedded image
*
* @param Swift_Message $message
*/
protected function inlineImages(Swift_Message $message)
{
$html = $message->getBody();
$crawler = new Crawler();
$crawler->addHtmlContent($html);
$imgs = array();
$replaces = array();
foreach ($crawler->filterXPath("//img[contains(concat(' ',normalize-space(@class), ' '), ' inline-image ')]") as $img) {
$normalized_src = $src = $img->getAttribute('src');
if (isset($replaces['src="' . $src . '"'])) {
continue;
}
// if starting with one slash, use local file
if (preg_match('#^/[^/]#', $normalized_src)) {
$normalized_src = $this->web_directory . parse_url($src, PHP_URL_PATH);
}
if (!isset($imgs[$normalized_src])) {
$swift_image = Swift_Image::fromPath($normalized_src);
$imgs[$normalized_src] = $message->embed($swift_image);
}
$replaces['src=\'' . $src . '\''] = 'src="' . $imgs[$normalized_src] . '"';
$replaces['src="' . $src . '"'] = 'src="' . $imgs[$normalized_src] . '"';
}
if (count($replaces)) {
$html = str_replace(array_keys($replaces), array_values($replaces), $html);
$message->setBody($html);
}
}示例12: setLaundryState
public function setLaundryState(&$laundryPlace)
{
$user = 'youruser';
$pass = 'yourpassword';
try {
$client = new Client($laundryPlace['url']);
$request = $client->get('/LaundryState', [], ['auth' => [$user, $pass, 'Digest'], 'timeout' => 1.5, 'connect_timeout' => 1.5]);
$response = $request->send();
$body = $response->getBody();
libxml_use_internal_errors(true);
$crawler = new Crawler();
$crawler->addContent($body);
foreach ($crawler->filter('img') as $img) {
$resource = $img->getAttribute('src');
$img->setAttribute('src', 'http://129.241.126.11/' . trim($resource, '/'));
}
$crawler->addHtmlContent('<h1>foobar</h1>');
//'<link href="http://129.241.126.11/pic/public_n.css" type="text/css">');
$laundryPlace['html'] = $crawler->html();
libxml_use_internal_errors(false);
preg_match_all('/bgColor=Green/', $body, $greenMatches);
preg_match_all('/bgColor=Red/', $body, $redMatches);
$laundryPlace['busy'] = count($redMatches[0]);
$laundryPlace['available'] = count($greenMatches[0]);
} catch (\Exception $e) {
$laundryPlace['available'] = self::NETWORK_ERROR;
$laundryPlace['busy'] = self::NETWORK_ERROR;
$laundryPlace['html'] = self::NETWORK_ERROR;
}
}示例13: testAddHtmlContent
/**
* @covers Symfony\Component\DomCrawler\Crawler::addHtmlContent
*/
public function testAddHtmlContent()
{
$crawler = new Crawler();
$crawler->addHtmlContent('<html><div class="foo"></html>', 'UTF-8');
$this->assertEquals('foo', $crawler->filter('div')->attr('class'), '->addHtmlContent() adds nodes from an HTML string');
}示例14: test_it_extracts_description
public function test_it_extracts_description()
{
$html = file_get_contents(__DIR__ . '/../Fixtures/product-page.html');
$crawler = new Crawler();
$crawler->addHtmlContent($html, 'ISO-8859-1');
$SUT = new SUT($crawler);
$this->assertEquals("Apricots", $SUT->getDescription());
}示例15: scrap
/**
* Scraps og:title off the page content
* @param string $url
* @return string
*/
public function scrap($url)
{
$title = 'Unable to parse';
$this->request->setMethod(HTTP_METH_GET);
$this->request->setUrl($url);
try {
$response = $this->request->send();
$this->crawler->addHtmlContent($response->getBody());
$subCrawler = $this->crawler->filterXPath('//head/meta[@property="og:title"]');
$meta = $subCrawler->getNode(0);
if ($meta) {
$title = $meta->getAttribute('content');
}
} catch (Exception $e) {
$title = $e->getMessage();
}
return $title;
}