A simple HTML Parser
Project description
Haruka Parser
A simple HTML Parser
Install
pip install haruka-parser
Usage
from haruka_parser.extract import extract_text
html = """<!DOCTYPE html>
<html>
<body>
<!-- Using MathML -->
<p>Using MathJax:</p>
<script type="math/tex; mode=display" id="MathJax-Element-1">{e}^{i\pi }=-1</script>
<!-- Using MathML -->
<p>Using MathML:</p>
<math xmlns="http://www.w3.org/1998/Math/MathML">
<msup>
<mi>e</mi>
<mrow>
<mi>i</mi>
<mi>π</mi>
</mrow>
</msup>
<mo>=</mo>
<mn>-1</mn>
</math>
<!-- Using AsciiMath -->
<p>Using AsciiMath:</p>
<script type="math/asciimath">
e^(i*pi) = -1
</script>
</body>
</html>"""
text, info = extract_text(html)
print(text)
print(info)
Configurations
from haruka_parser.extract import DEFAULT_CONFIG
DEFAULT_CONFIG = {
"readability": False,
"skip_large_links": False,
"extract_latex": True,
"extract_cnki_latex": False,
"escape_dollars": True,
"remove_buttons": True,
"remove_edit_buttons": True,
"remove_image_figures": True,
"markdown_code": True,
"markdown_headings": True,
"remove_chinese": False,
"boilerplate_config": {
"enable": False,
"ratio_threshold": 0.18,
"absolute_threshold": 10,
"end_threshold": 15,
},
}
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
haruka_parser-0.5.2.tar.gz
(5.7 MB
view hashes)
Built Distribution
Close
Hashes for haruka_parser-0.5.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 032dafde13c49747e4c52b726bef283f62afa5d863e686915fe96375d85638aa |
|
MD5 | 776f956783567a227c8d62acdfe109fc |
|
BLAKE2b-256 | 6e148a1f0be74c9b500a58b2d5ee9b36dc06e0da8c718a073698cb62a468b024 |