Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 5 additions & 5 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -118,7 +118,7 @@ if __name__=="__main__":
markdown = extract(url, html)
```

### only extract by magic-html
### only extract main_html by magic-html

```python
from llm_web_kit.simple import extract_magic_html
Expand All @@ -127,17 +127,17 @@ from loguru import logger

def extract(url:str, html:str) -> str:
try:
nlp_md = extract_main_html_by_maigic_html(url, html)
# or mm_nlp_md = extract_pure_html_to_mm_md(url, html)
return nlp_md
main_html = extract_main_html_by_maigic_html(url, html)
# or mm_main_html = extract_pure_html_to_mm_md(url, html)
return main_html
except Exception as e:
logger.exception(e)
return None

if __name__=="__main__":
url = ""
html = ""
markdown = extract(url, html)
main_html = extract(url, html)
```

## Pipeline
Expand Down