simple_html_dom(1)
// Create DOM from URL or file
$html = file_get_html(‘http://www.google.com/‘);
// Find all images
foreach($html->find(‘img‘) as $element)
echo $element->src . ‘<br>‘;
// Find all links
foreach($html->find(‘a‘) as $element)
echo $element->href . ‘<br>‘;
// Create DOM from string
$html = str_get_html(‘<div id="hello">Hello</div><div id="world">World</div>‘);
$html->find(‘div‘, 1)->class = ‘bar‘;
$html->find(‘div[id=hello]‘, 0)->innertext = ‘foo‘;
echo $html; // Output: <div id="hello">foo</div><div id="world" class="bar">World</div>
// Dump contents (without tags) from HTML
echo file_get_html(‘http://www.google.com/‘)->plaintext;
// Create DOM from URL
$html = file_get_html(‘http://slashdot.org/‘);
// Find all article blocks
foreach($html->find(‘div.article‘) as $article) {
$item[‘title‘] = $article->find(‘div.title‘, 0)->plaintext;
$item[‘intro‘] = $article->find(‘div.intro‘, 0)->plaintext;
$item[‘details‘] = $article->find(‘div.details‘, 0)->plaintext;
$articles[] = $item;
}
print_r($articles);
How to create HTML DOM object?
// Create a DOM object
$html = new simple_html_dom();
// Load HTML from a string
$html->load(‘<html><body>Hello!</body></html>‘);
// Load HTML from a URL
$html->load_file(‘http://www.google.com/‘);
// Load HTML from a HTML file
$html->load_file(‘test.htm‘);
How to find HTML elements?
// Find all anchors, returns a array of element objects
$ret = $html->find(‘a‘);
// Find (N)th anchor, returns element object or null if not found (zero based)
$ret = $html->find(‘a‘, 0);
// Find lastest anchor, returns element object or null if not found (zero based)
$ret = $html->find(‘a‘, -1);
// Find all <div> with the id attribute
$ret = $html->find(‘div[id]‘);
// Find all <div> which attribute id=foo
$ret = $html->find(‘div[id=foo]‘);
// Find all element which id=foo
$ret = $html->find(‘#foo‘);
// Find all element which class=foo
$ret = $html->find(‘.foo‘);
// Find all element has attribute id
$ret = $html->find(‘*[id]‘);
// Find all anchors and images
$ret = $html->find(‘a, img‘);
// Find all anchors and images with the "title" attribute
$ret = $html->find(‘a[title], img[title]‘);
// Find all <li> in <ul>
$es = $html->find(‘ul li‘);
// Find Nested <div> tags
$es = $html->find(‘div div div‘);
// Find all <td> in <table> which class="hello"
$es = $html->find(‘table.hello td‘);
// Find all td tags with attribite align=center in table tags
$es = $html->find(‘‘table td[align=center]‘);
// Find all <li> in <ul>
foreach($html->find(‘ul‘) as $ul)
{
foreach($ul->find(‘li‘) as $li)
{
// do something...
}
}
// Find first <li> in first <ul>
$e = $html->find(‘ul‘, 0)->find(‘li‘, 0);
// Find all text blocks
$es = $html->find(‘text‘);
// Find all comment (<!--...-->) blocks
$es = $html->find(‘comment‘);
Supports these operators in attribute selectors:
Filter | Description |
---|---|
[attribute] | Matches elements that have the specified attribute. |
[!attribute] | Matches elements that don‘t have the specified attribute. |
[attribute=value] | Matches elements that have the specified attribute with a certain value. |
[attribute!=value] | Matches elements that don‘t have the specified attribute with a certain value. |
[attribute^=value] | Matches elements that have the specified attribute and it starts with a certain value. |
[attribute$=value] | Matches elements that have the specified attribute and it ends with a certain value. |
[attribute*=value] | Matches elements that have the specified attribute and it contains a certain value |
郑重声明:本站内容如果来自互联网及其他传播媒体,其版权均属原媒体及文章作者所有。转载目的在于传递更多信息及用于网络分享,并不代表本站赞同其观点和对其真实性负责,也不构成任何其他建议。