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

feat(cache): introduce CacheMode and CacheContext for enhanced caching behavior

Browse Source 
chore(requirements): add colorama dependency
refactor(config): add SHOW_DEPRECATION_WARNINGS flag and clean up code
fix(docs): update example scripts for clarity and consistency
This commit is contained in:
UncleCode
2024-11-17 15:30:56 +08:00
parent 4b45b28f25
commit 3a66aa8a60
10 changed files with 979 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
crawl4ai/async_crawler_strategy.py
View File

@@ -669,8 +669,8 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
if self.accept_downloads:
page.on("download", lambda download: asyncio.create_task(self._handle_download(download)))
if self.verbose:
print(f"[LOG] 🕸️ Crawling {url} using AsyncPlaywrightCrawlerStrategy...")
# if self.verbose:
# print(f"[LOG] 🕸️ Crawling {url} using AsyncPlaywrightCrawlerStrategy...")
if self.use_cached_html:
cache_file_path = os.path.join(
@@ -873,8 +873,8 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
await asyncio.sleep(screenshot_wait_for)
screenshot_data = await self.take_screenshot(page)
if self.verbose:
print(f"[LOG] ✅ Crawled {url} successfully!")
# if self.verbose:
# print(f"[LOG] ✅ Crawled {url} successfully!")
if self.use_cached_html:
cache_file_path = os.path.join(