mirror of https://github.com/scrapy/scrapy.git
22 lines
777 B
HTML
22 lines
777 B
HTML
<!DOCTYPE html>
|
|
|
|
<html>
|
|
<head>
|
|
<base href='http://example.com' />
|
|
<title>Sample page with links for testing LinkExtractor</title>
|
|
</head>
|
|
<body>
|
|
<div id='wrapper'>
|
|
<div id='subwrapper'>
|
|
<area href='sample1.html' alt='sample1'/>
|
|
<a href='sample2.html'>sample 2<img src='sample2.jpg' alt='sample2'/></a>
|
|
</div>
|
|
<a href='http://example.com/sample3.html' title='sample 3'>sample 3 text</a>
|
|
<a href='sample3.html'>sample 3 repetition</a>
|
|
<a href='sample3.html#foo'>sample 3 repetition with fragment</a>
|
|
<a href='http://www.google.com/something'></a>
|
|
<a href='http://example.com/innertag.html'><strong>inner</strong> tag</a>
|
|
<a href='page 4.html'>href with whitespaces</a>
|
|
</div>
|
|
</body>
|
|
</html> |