From 32065fa06a38a2895df8b6cf0689042c6857fc31 Mon Sep 17 00:00:00 2001 From: Aaron2516 Date: Sat, 10 May 2025 11:32:48 +0800 Subject: [PATCH] Fixed the incorrect elapsed calculation method and inappropriate output format --- docs/examples/scraping_strategies_performance.py | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/examples/scraping_strategies_performance.py b/docs/examples/scraping_strategies_performance.py index 87fb8ac5b..1f2751693 100644 --- a/docs/examples/scraping_strategies_performance.py +++ b/docs/examples/scraping_strategies_performance.py @@ -1,9 +1,9 @@ -import time, re -from crawl4ai.content_scraping_strategy import WebScrapingStrategy, LXMLWebScrapingStrategy -import time import functools +import time from collections import defaultdict +from crawl4ai.content_scraping_strategy import WebScrapingStrategy, LXMLWebScrapingStrategy + class TimingStats: def __init__(self): self.stats = defaultdict(lambda: defaultdict(lambda: {"calls": 0, "total_time": 0})) @@ -95,7 +95,7 @@ def test_scraping(): # Time the scraping print("\nStarting scrape...") - start_time = time.time() + start_time = time.perf_counter() kwargs = { "url": "http://example.com", @@ -117,7 +117,7 @@ def test_scraping(): timing_stats.report() # Print stats of LXML output - print("\Turbo Output:") + print("\nTurbo 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")