File: linkextractor.html

package info (click to toggle)
python-scrapy 2.13.3-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 5,664 kB
  • sloc: python: 52,028; xml: 199; makefile: 25; sh: 7
file content (23 lines) | stat: -rw-r--r-- 830 bytes parent folder | download | duplicates (3)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
<!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'>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>