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

Merge remote-tracking branch 'origin/main' into 0.3.74

Browse Source
This commit is contained in:
UncleCode
2024-11-18 21:15:04 +08:00
parent 852729ff38 38044d4afe
commit b6af94cbbb
11 changed files with 18 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
crawl4ai/async_crawler_strategy.py
View File

@@ -736,7 +736,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
if self.use_cached_html:
cache_file_path = os.path.join(
Path.home(), ".crawl4ai", "cache", hashlib.md5(url.encode()).hexdigest()
os.getenv("CRAWL4_AI_BASE_DIRECTORY", Path.home()), ".crawl4ai", "cache", hashlib.md5(url.encode()).hexdigest()
)
if os.path.exists(cache_file_path):
html = ""
@@ -940,7 +940,7 @@ class AsyncPlaywrightCrawlerStrategy(AsyncCrawlerStrategy):
if self.use_cached_html:
cache_file_path = os.path.join(
Path.home(), ".crawl4ai", "cache", hashlib.md5(url.encode()).hexdigest()
os.getenv("CRAWL4_AI_BASE_DIRECTORY", Path.home()), ".crawl4ai", "cache", hashlib.md5(url.encode()).hexdigest()
)
with open(cache_file_path, "w", encoding="utf-8") as f:
f.write(html)