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

Apply Ruff Corrections

Browse Source
This commit is contained in:
UncleCode
2025-01-13 19:19:58 +08:00
parent c3370ec5da
commit 8ec12d7d68
84 changed files with 6861 additions and 5076 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
docs/examples/ssl_example.py
View File

@@ -5,42 +5,47 @@ import os
from crawl4ai import AsyncWebCrawler, CrawlerRunConfig, CacheMode
# Create tmp directory if it doesn't exist
parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
parent_dir = os.path.dirname(
os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
)
tmp_dir = os.path.join(parent_dir, "tmp")
os.makedirs(tmp_dir, exist_ok=True)
async def main():
# Configure crawler to fetch SSL certificate
config = CrawlerRunConfig(
fetch_ssl_certificate=True,
cache_mode=CacheMode.BYPASS # Bypass cache to always get fresh certificates
cache_mode=CacheMode.BYPASS, # Bypass cache to always get fresh certificates
)
async with AsyncWebCrawler() as crawler:
result = await crawler.arun(
url='https://example.com',
config=config
)
result = await crawler.arun(url="https://example.com", config=config)
if result.success and result.ssl_certificate:
cert = result.ssl_certificate
# 1. Access certificate properties directly
print("\nCertificate Information:")
print(f"Issuer: {cert.issuer.get('CN', '')}")
print(f"Valid until: {cert.valid_until}")
print(f"Fingerprint: {cert.fingerprint}")
# 2. Export certificate in different formats
cert.to_json(os.path.join(tmp_dir, "certificate.json")) # For analysis
print("\nCertificate exported to:")
print(f"- JSON: {os.path.join(tmp_dir, 'certificate.json')}")
pem_data = cert.to_pem(os.path.join(tmp_dir, "certificate.pem")) # For web servers
pem_data = cert.to_pem(
os.path.join(tmp_dir, "certificate.pem")
) # For web servers
print(f"- PEM: {os.path.join(tmp_dir, 'certificate.pem')}")
der_data = cert.to_der(os.path.join(tmp_dir, "certificate.der")) # For Java apps
der_data = cert.to_der(
os.path.join(tmp_dir, "certificate.der")
) # For Java apps
print(f"- DER: {os.path.join(tmp_dir, 'certificate.der')}")
if __name__ == "__main__":
asyncio.run(main())