File: sgml_linkextractor.html

package info (click to toggle)
python-scrapy 1.5.1-1%2Bdeb10u1
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 4,404 kB
  • sloc: python: 25,793; xml: 199; makefile: 95; sh: 33
file content (20 lines) | stat: -rw-r--r-- 643 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
<html>
<head>
<base href='http://example.com' />
<title>Sample page with links for testing RegexLinkExtractor</title>
</head>
<body>
<div id='wrapper'>
<div id='subwrapper'>
<area href='sample1.html' />
<a href='sample2.html'>sample 2<img src='sample2.jpg'/></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'><b>inner</b> tag</a>
<a href=' page 4.html '>href with whitespaces</a>
</div>
</body>
</html>