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

Refactor content scraping strategies: comment out WebScrapingStrategy references and update to use LXMLWebScrapingStrategy across multiple files. Bring WebScrapingStrategy methods to LXMLWebScrapingStrategy

Browse Source
This commit is contained in:
ntohidi
2025-05-27 17:32:45 +02:00
parent 3b766e1aac
commit bfec5156ad
7 changed files with 76 additions and 850 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
tests/async/test_content_scraper_strategy.py
View File

@@ -12,10 +12,10 @@ parent_dir = os.path.dirname(
sys.path.append(parent_dir)
__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
from crawl4ai.content_scraping_strategy import WebScrapingStrategy
from crawl4ai.content_scraping_strategy import (
WebScrapingStrategy as WebScrapingStrategyCurrent,
)
from crawl4ai.content_scraping_strategy import LXMLWebScrapingStrategy
# from crawl4ai.content_scraping_strategy import (
# WebScrapingStrategy as WebScrapingStrategyCurrent,
# )
# from crawl4ai.content_scrapping_strategy_current import WebScrapingStrategy as WebScrapingStrategyCurrent
@@ -32,8 +32,8 @@ class TestResult:
class StrategyTester:
def __init__(self):
self.new_scraper = WebScrapingStrategy()
self.current_scraper = WebScrapingStrategyCurrent()
self.new_scraper = LXMLWebScrapingStrategy()
self.current_scraper = LXMLWebScrapingStrategy()
with open(__location__ + "/sample_wikipedia.html", "r", encoding="utf-8") as f:
self.WIKI_HTML = f.read()
self.results = {"new": [], "current": []}