ayrisdev/crawl4ai
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(docs): enhance table data access example with a real url

Browse Source
This commit is contained in:
ntohidi
2025-08-06 15:19:37 +08:00
parent 45d8327d23
commit a5bcac4c9d
1 changed files with 27 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
docs/md_v2/core/crawler-result.md
View File

@@ -221,26 +221,34 @@ Tables that score above the threshold (default: 7) are extracted and stored in r
### Accessing Table data: ### Accessing Table data:
```python ```python
async with AsyncWebCrawler() as crawler: import asyncio
result = await crawler.arun( from crawl4ai import AsyncWebCrawler, CrawlerRunConfig
url="https://example.com/",
config=CrawlerRunConfig( async def main():
table_score_threshold=7 # Minimum score for table detection async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url="https://www.w3schools.com/html/html_tables.asp",
config=CrawlerRunConfig(
table_score_threshold=7 # Minimum score for table detection
)
) )
)
if result.success and result.tables:
if result.success and result.tables: print(f"Found {len(result.tables)} tables")
print(f"Found {len(result.tables)} tables")
for i, table in enumerate(result.tables):
for i, table in enumerate(result.tables): print(f"\nTable {i+1}:")
print(f"\nTable {i+1}:") print(f"Caption: {table.get('caption', 'No caption')}")
print(f"Caption: {table.get('caption', 'No caption')}") print(f"Headers: {table['headers']}")
print(f"Headers: {table['headers']}") print(f"Rows: {len(table['rows'])}")
print(f"Rows: {len(table['rows'])}")
# Print first few rows as example
# Print first few rows as example for j, row in enumerate(table['rows'][:3]):
for j, row in enumerate(table['rows'][:3]): print(f" Row {j+1}: {row}")
print(f" Row {j+1}: {row}")
if __name__ == "__main__":
asyncio.run(main())
``` ```
### Configuring Table Extraction: ### Configuring Table Extraction: