mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-09 12:21:57 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Use feedparser for RSS parsing (#1362)

Browse source 
Fixes #1171
Fixes #870 (probably, would need to test against a Wallabag Atom file to
Fixes #135
Fixes #123
Fixes #106
This commit is contained in:
Nick Sweeting 2024-03-14 01:51:45 -07:00 • committed by GitHub
commit 099f7d00fe
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 158 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

24
tests/mock_server/templates/example.atom Normal file
View file

@ -0,0 +1,24 @@
<?xml version="1.0" encoding="utf-8"?>
<feed
xml:lang="en"
xmlns="http://www.w3.org/2005/Atom"
>
<id>http://www.example.com/</id>
<title>Example of an Atom feed</title>
<link rel="self" type="application/atom+xml" href="http://www.example.com/index.atom" />
<link rel="alternate" type="text/html" href="http://www.example.com/" />
<author>
<name>Jim Winstead</name>
</author>
<updated>2024-02-26T03:18:26Z</updated>
<entry>
<title>Example</title>
<link rel="alternate" type="text/html" href="http://127.0.0.1:8080/static/example.com.html" />
<id>tag:example.com,2024-02-25:3319</id>
<updated>2024-02-26T03:18:26Z</updated>
<published>2024-02-25T19:18:25-08:00</published>
<category term="Tag1" scheme="http://example.com/archive" />
<category term="Tag2" scheme="http://example.com/archive" />
<content type="html">This is some &lt;b&gt;content&lt;/b&gt;</content>
</entry>
</feed>

32
tests/mock_server/templates/example.rss Normal file
View file

@ -0,0 +1,32 @@
<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:admin="http://webns.net/mvcb/"
xmlns:content="http://purl.org/rss/1.0/modules/content/"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#">
<channel>
<title>Sample Feed</title>
<link>http://example.org/</link>
<description>For documentation only</description>
<dc:language>en-us</dc:language>
<dc:creator>Nobody (nobody@example.org)</dc:creator>
<dc:rights>Public domain</dc:rights>
<dc:date>2024-02-26T17:28:12-08:00</dc:date>
<admin:generatorAgent rdf:resource="http://www.example.org/"/>
<admin:errorReportsTo rdf:resource="mailto:nobody@example.org"/>
<item>
<title>First!</title>
<link>http://127.0.0.1:8080/static/example.com.html</link>
<guid isPermaLink="false">just-an@example.org</guid>
<description>
This has a description.
</description>
<dc:subject>Tag1 Tag2</dc:subject>
<dc:date>2024-02-26T17:28:12-08:00</dc:date>
<content:encoded><![CDATA[
This has a <b>description</b>.]]>
</content:encoded>
</item>
</channel>
</rss>