mirror of
https://github.com/miniflux/v2.git
synced 2025-08-01 17:38:37 +00:00
Return outer HTML when scraping elements
This commit is contained in:
parent
30f22fbd78
commit
8e1ed8bef3
8 changed files with 73 additions and 8 deletions
12
reader/scraper/testdata/iframe.html
vendored
Normal file
12
reader/scraper/testdata/iframe.html
vendored
Normal file
|
@ -0,0 +1,12 @@
|
|||
<!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<body>
|
||||
<article>
|
||||
<iframe id="1" src="about:blank"></iframe>
|
||||
<iframe id="2" src="about:blank"></iframe>
|
||||
<iframe id="3" src="about:blank"></iframe>
|
||||
<iframe id="4" src="about:blank"></iframe>
|
||||
<iframe id="5" src="about:blank"></iframe>
|
||||
</article>
|
||||
</body>
|
||||
</html>
|
1
reader/scraper/testdata/iframe.html-result
vendored
Normal file
1
reader/scraper/testdata/iframe.html-result
vendored
Normal file
|
@ -0,0 +1 @@
|
|||
<iframe id="1" src="about:blank"></iframe><iframe id="2" src="about:blank"></iframe><iframe id="3" src="about:blank"></iframe><iframe id="4" src="about:blank"></iframe><iframe id="5" src="about:blank"></iframe>
|
12
reader/scraper/testdata/img.html
vendored
Normal file
12
reader/scraper/testdata/img.html
vendored
Normal file
|
@ -0,0 +1,12 @@
|
|||
<!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<body>
|
||||
<article>
|
||||
<img id="1" src="#" alt="" />
|
||||
<img id="2" src="#" alt="" />
|
||||
<img id="3" src="#" alt="" />
|
||||
<img id="4" src="#" alt="" />
|
||||
<img id="5" src="#" alt="" />
|
||||
</article>
|
||||
</body>
|
||||
</html>
|
1
reader/scraper/testdata/img.html-result
vendored
Normal file
1
reader/scraper/testdata/img.html-result
vendored
Normal file
|
@ -0,0 +1 @@
|
|||
<img id="1" src="#" alt=""/><img id="2" src="#" alt=""/><img id="3" src="#" alt=""/><img id="4" src="#" alt=""/><img id="5" src="#" alt=""/>
|
10
reader/scraper/testdata/p.html
vendored
Normal file
10
reader/scraper/testdata/p.html
vendored
Normal file
|
@ -0,0 +1,10 @@
|
|||
<!DOCTYPE html>
|
||||
<html lang="en-US">
|
||||
<body>
|
||||
<article>
|
||||
<p>Lorem ipsum dolor sit amet, consectetuer adipiscing ept.</p>
|
||||
<p>Apquam tincidunt mauris eu risus.</p>
|
||||
<p>Vestibulum auctor dapibus neque.</p>
|
||||
</article>
|
||||
</body>
|
||||
</html>
|
1
reader/scraper/testdata/p.html-result
vendored
Normal file
1
reader/scraper/testdata/p.html-result
vendored
Normal file
|
@ -0,0 +1 @@
|
|||
<p>Lorem ipsum dolor sit amet, consectetuer adipiscing ept.</p><p>Apquam tincidunt mauris eu risus.</p><p>Vestibulum auctor dapibus neque.</p>
|
Loading…
Add table
Add a link
Reference in a new issue