github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-11 07:50:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add HTML document_loader that includes page title metadata (#1720)

Browse Source 
This `BSHTMLLoader` document_loader loads an HTML document, extracts
text and adds the page title to the returned Document's metadata. The
loader uses the already installed bs4 package to extract both text
content and the page title.

Included in this PR is an example HTML file and an integration test that
tests against this file.

---------

Co-authored-by: Daniel Chalef <daniel.chalef@private.org>
This commit is contained in:
Daniel Chalef
2023-03-16 21:47:17 -07:00
committed by GitHub
parent 40e9488055
commit b157e0c1c3
5 changed files with 84 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
tests/integration_tests/document_loaders/test_bshtml.py Normal file
View File

@@ -0,0 +1,17 @@
from pathlib import Path
from langchain.document_loaders.html_bs import BSHTMLLoader
def test_bs_html_loader() -> None:
"""Test unstructured loader."""
file_path = Path(__file__).parent.parent / "examples/example.html"
loader = BSHTMLLoader(str(file_path))
docs = loader.load()
assert len(docs) == 1
metadata = docs[0].metadata
assert metadata["title"] == "Chew dad's slippers"
assert metadata["source"] == str(file_path)

25
tests/integration_tests/examples/example.html Normal file
View File

@@ -0,0 +1,25 @@
<html>
<head>
<title>Chew dad's slippers</title>
</head>
<body>
<h1>
Instead of drinking water from the cat bowl, make sure to steal water from
the toilet
</h1>
<h2>Chase the red dot</h2>
<p>
Munch, munch, chomp, chomp hate dogs. Spill litter box, scratch at owner,
destroy all furniture, especially couch get scared by sudden appearance of
cucumber cat is love, cat is life fat baby cat best buddy little guy for
catch eat throw up catch eat throw up bad birds jump on fridge. Purr like
a car engine oh yes, there is my human woman she does best pats ever that
all i like about her hiss meow .
</p>
<p>
Dead stare with ears cocked when owners are asleep, cry for no apparent
reason meow all night. Plop down in the middle where everybody walks favor
packaging over toy. Sit on the laptop kitty pounce, trip, faceplant.
</p>
</body>
</html>