RomanNum3ral
/
scrapy
mirror of https://github.com/scrapy/scrapy.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

HTML Conventions

This commit is contained in:
FJMonteroInformatica 2022-03-17 20:09:56 +01:00
parent 9a28eb0bad
commit 6a3f2ee687
8 changed files with 96 additions and 96 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
docs/_static/selectors-sample1.html vendored
View File

@ -1,16 +1,17 @@
<html>
<head>
<base href='http://example.com/' />
<title>Example website</title>
</head>
<body>
<div id='images'>
<a href='image1.html'>Name: My image 1 <br /><img src='image1_thumb.jpg' /></a>
<a href='image2.html'>Name: My image 2 <br /><img src='image2_thumb.jpg' /></a>
<a href='image3.html'>Name: My image 3 <br /><img src='image3_thumb.jpg' /></a>
<a href='image4.html'>Name: My image 4 <br /><img src='image4_thumb.jpg' /></a>
<a href='image5.html'>Name: My image 5 <br /><img src='image5_thumb.jpg' /></a>
</div>
</body>
</html>
<!DOCTYPE html>
<html>
<head>
<base href='http://example.com/' />
<title>Example website</title>
</head>
<body>
<div id='images'>
<a href='image1.html'>Name: My image 1 <br /><img src='image1_thumb.jpg' alt='image1'/></a>
<a href='image2.html'>Name: My image 2 <br /><img src='image2_thumb.jpg' alt='image2'/></a>
<a href='image3.html'>Name: My image 3 <br /><img src='image3_thumb.jpg' alt='image3'/></a>
<a href='image4.html'>Name: My image 4 <br /><img src='image4_thumb.jpg' alt='image4'/></a>
<a href='image5.html'>Name: My image 5 <br /><img src='image5_thumb.jpg' alt='image5'/></a>
</div>
</body>
</html>

40
tests/sample_data/link_extractor/linkextractor.html
View File

@ -1,20 +1,22 @@
<!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' />
<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>
<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>

8
tests/sample_data/link_extractor/linkextractor_latin1.html
View File

@ -1,3 +1,5 @@
<!DOCTYPE html>
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=latin-1">
@ -7,11 +9,11 @@
<body>
<div id='wrapper'>
<div id='subwrapper'>
<a href='sample_ń.html'><img src='sample2.jpg'/></a>
<a href='sample_ñ.html'><img src='sample2.jpg' alt='sample2'/></a>
</div>
<a href='sample_á.html' title='sample á'>sample á text</a>
<a href='sample_á.html' title='sample á'>sample á text</a>
<div id='subwrapper2'>
<a href='sample_ö.html?price=Ł32&ľ=unit'><img src='sample3.jpg'/></a>
<a href='sample_ö.html?price=£32&µ=unit'><img src='sample3.jpg' alt='sample3'/></a>
</div>
</div>
</body>

3
tests/sample_data/link_extractor/linkextractor_no_href.html
View File

@ -1,3 +1,5 @@
<!DOCTYPE html>
<html>
<head>
<base href='http://example.com' />
@ -21,5 +23,4 @@
</div>
</div>
</body>
</html>

23
tests/sample_data/link_extractor/linkextractor_noenc.html
View File

@ -1,14 +1,17 @@
<!DOCTYPE html>
<html>
<head>
<base href='http://example.com' />
<title>Sample page without encoding for testing LinkExtractor</title>
</head>
<head>
<base href='http://example.com' />
<title>Sample page without encoding for testing LinkExtractor</title>
</head>
<body>
<div id='wrapper'>
<div id='subwrapper'>
<a href='sample_ñ.html'><img src='sample2.jpg'/></a>
</div>
<a href='sample_€.html' title='sample €'>sample € text</a>
</div>
<div id='wrapper'>
<div id='subwrapper'>
<a href='sample_ñ.html'><img src='sample2.jpg' alt='sample2'/></a>
</div>
<a href='sample_€.html' title='sample €'>sample € text</a>
</div>
</body>
</html>

31
tests/sample_data/test_site/index.html
View File

@ -1,18 +1,15 @@
<!DOCTYPE html>
<html>
<head>
<title>Scrapy test site</title>
</head>
<body>
<h1>Scrapy test site</h1>
<ul>
<li><a href="item1.html">Item 1</li>
<li><a href="item2.html">Item 2</li>
<li><a href="item999.html">Item 999 (not found)</li>
</ul>
</body>
</html>
<head>
<title>Scrapy test site</title>
</head>
<body>
<h1>Scrapy test site</h1>
<ul>
<li><a href="item1.html">Item 1</a></li>
<li><a href="item2.html">Item 2</a></li>
<li><a href="item999.html">Item 999 (not found)</a></li>
</ul>
</body>
</html>

27
tests/sample_data/test_site/item1.html
View File

@ -1,17 +1,14 @@
<!DOCTYPE html>
<html>
<head>
<title>Item 1 - Scrapy test site</title>
</head>
<body>
<h1>Item 1 name</h1>
<ul>
<li>Price: $100</li>
<li>Stock: 12</li>
</ul>
</body>
<head>
<title>Item 1 - Scrapy test site</title>
</head>
<body>
<h1>Item 1 name</h1>
<ul>
<li>Price: $100</li>
<li>Stock: 12</li>
</ul>
</body>
</html>

29
tests/sample_data/test_site/item2.html
View File

@ -1,17 +1,14 @@
<!DOCTYPE html>
<html>
<head>
<title>Item 2 - Scrapy test site</title>
</head>
<body>
<h1>Item 2 name</h1>
<ul>
<li>Price: $200</li>
<li>Stock: 5</li>
</ul>
</body>
</html>
<head>
<title>Item 2 - Scrapy test site</title>
</head>
<body>
<h1>Item 2 name</h1>
<ul>
<li>Price: $200</li>
<li>Stock: 5</li>
</ul>
</body>
</html>