mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
ddd595fe81
# Improve Evernote Document Loader When exporting from Evernote you may export more than one note. Currently the Evernote loader concatenates the content of all notes in the export into a single document and only attaches the name of the export file as metadata on the document. This change ensures that each note is loaded as an independent document and all available metadata on the note e.g. author, title, created, updated are added as metadata on each document. It also uses an existing optional dependency of `html2text` instead of `pypandoc` to remove the need to download the pandoc application via `download_pandoc()` to be able to use the `pypandoc` python bindings. Fixes #4493 Co-authored-by: Mike McGarry <mike.mcgarry@finbourne.com> Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
28 lines
1.1 KiB
XML
28 lines
1.1 KiB
XML
<?xml version="1.0" encoding="UTF-8"?>
|
|
<!DOCTYPE en-export SYSTEM "http://xml.evernote.com/pub/evernote-export4.dtd">
|
|
<en-export export-date="20230611T011239Z" application="Evernote" version="10.56.9">
|
|
<note>
|
|
<title>Test</title>
|
|
<created>20230511T011217Z</created>
|
|
<updated>20240714T011228Z</updated>
|
|
<note-attributes>
|
|
<author>Michael McGarry</author>
|
|
</note-attributes>
|
|
<content>
|
|
<![CDATA[<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
|
<!DOCTYPE en-note SYSTEM "http://xml.evernote.com/pub/enml2.dtd"><en-note><div>abc</div></en-note> ]]>
|
|
</content>
|
|
</note>
|
|
<note>
|
|
<title>Summer Training Program</title>
|
|
<created>20221227T015948Z</created>
|
|
<note-attributes>
|
|
<author>Mike McGarry</author>
|
|
<source>mobile.iphone</source>
|
|
</note-attributes>
|
|
<content>
|
|
<![CDATA[<?xml version="1.0" encoding="UTF-8" standalone="no"?>
|
|
<!DOCTYPE en-note SYSTEM "http://xml.evernote.com/pub/enml2.dtd"><en-note><div><b>Jan - March 2022</b></div></en-note> ]]>
|
|
</content>
|
|
</note>
|
|
</en-export> |