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

docs(examples): update demo scripts and fix output formats

Browse Source 
Update example scripts to reflect latest API changes and improve demonstrations:
- Increase test URLs in dispatcher example from 20 to 40 pages
- Comment out unused dispatcher strategies for cleaner output
- Fix scraping strategies performance script to use correct object notation
- Update v0_4_3_features_demo with additional feature mentions and uncomment demo sections

These changes make the examples more current and better aligned with the actual API.
This commit is contained in:
UncleCode
2025-01-22 20:40:03 +08:00
parent 2d69bf2366
commit 976ea52167
3 changed files with 26 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
docs/examples/scraping_strategies_performance.py
View File

@@ -117,17 +117,17 @@ def test_scraping():
timing_stats.report()
# Print stats of LXML output
print("\nLXML Output:")
print(f"\nExtracted links: {len(result_selected['links']['internal']) + len(result_selected['links']['external'])}")
print(f"Extracted images: {len(result_selected['media']['images'])}")
print(f"Clean HTML size: {len(result_selected['cleaned_html'])/1024:.2f} KB")
print("\Turbo Output:")
print(f"\nExtracted links: {len(result_selected.links.internal) + len(result_selected.links.external)}")
print(f"Extracted images: {len(result_selected.media.images)}")
print(f"Clean HTML size: {len(result_selected.cleaned_html)/1024:.2f} KB")
print(f"Scraping time: {t2 - t1:.2f} seconds")
# Print stats of original output
print("\nOriginal Output:")
print(f"\nExtracted links: {len(result_original['links']['internal']) + len(result_original['links']['external'])}")
print(f"Extracted images: {len(result_original['media']['images'])}")
print(f"Clean HTML size: {len(result_original['cleaned_html'])/1024:.2f} KB")
print(f"\nExtracted links: {len(result_original.links.internal) + len(result_original.links.external)}")
print(f"Extracted images: {len(result_original.media.images)}")
print(f"Clean HTML size: {len(result_original.cleaned_html)/1024:.2f} KB")
print(f"Scraping time: {t3 - t1:.2f} seconds")