Compare commits
14 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5313c71a0d | ||
|
|
d36ef3d424 | ||
|
|
4a4f613238 | ||
|
|
dc6a24618e | ||
|
|
74a7c6dbb6 | ||
|
|
67f65f958b | ||
|
|
78b6ba5cef | ||
|
|
3f019d34cc | ||
|
|
304260e484 | ||
|
|
704bd66b63 | ||
|
|
1acc162c18 | ||
|
|
553c97a0c1 | ||
|
|
bd66befcf0 | ||
|
|
19b0a5ae82 |
12
README.md
12
README.md
@@ -39,13 +39,17 @@ Crawl4AI is the #1 trending GitHub repository, actively maintained by a vibrant
|
||||
```bash
|
||||
# Install the package
|
||||
pip install crawl4ai
|
||||
|
||||
# Run post-installation setup
|
||||
crawl4ai-setup
|
||||
|
||||
# Install Playwright with system dependencies (recommended)
|
||||
playwright install --with-deps
|
||||
# Verify your installation
|
||||
crawl4ai-doctor
|
||||
```
|
||||
|
||||
# Or install specific browsers:
|
||||
playwright install --with-deps chrome # Recommended for Colab/Linux
|
||||
If you encounter any browser-related issues, you can install them manually:
|
||||
```bash
|
||||
python -m playwright install --with-deps chromium
|
||||
```
|
||||
|
||||
2. Run a simple web crawl:
|
||||
|
||||
@@ -1,2 +1,2 @@
|
||||
# crawl4ai/_version.py
|
||||
__version__ = "0.4.24"
|
||||
__version__ = "0.4.241"
|
||||
|
||||
@@ -83,7 +83,6 @@ class RelevantContentFilter(ABC):
|
||||
|
||||
return ' '.join(filter(None, query_parts))
|
||||
|
||||
|
||||
def extract_text_chunks(self, body: Tag, min_word_threshold: int = None) -> List[Tuple[str, str]]:
|
||||
"""
|
||||
Extracts text chunks from a BeautifulSoup body element while preserving order.
|
||||
|
||||
@@ -2,7 +2,6 @@ import subprocess
|
||||
import sys
|
||||
import asyncio
|
||||
from .async_logger import AsyncLogger, LogLevel
|
||||
from .docs_manager import DocsManager
|
||||
|
||||
# Initialize logger
|
||||
logger = AsyncLogger(log_level=LogLevel.DEBUG, verbose=True)
|
||||
@@ -12,24 +11,20 @@ def post_install():
|
||||
logger.info("Running post-installation setup...", tag="INIT")
|
||||
install_playwright()
|
||||
run_migration()
|
||||
asyncio.run(setup_docs())
|
||||
logger.success("Post-installation setup completed!", tag="COMPLETE")
|
||||
|
||||
def install_playwright():
|
||||
logger.info("Installing Playwright browsers...", tag="INIT")
|
||||
try:
|
||||
subprocess.check_call([sys.executable, "-m", "playwright", "install"])
|
||||
# subprocess.check_call([sys.executable, "-m", "playwright", "install", "--with-deps", "--force", "chrome"])
|
||||
subprocess.check_call([sys.executable, "-m", "playwright", "install", "--with-deps", "--force", "chromium"])
|
||||
logger.success("Playwright installation completed successfully.", tag="COMPLETE")
|
||||
except subprocess.CalledProcessError as e:
|
||||
logger.error(f"Error during Playwright installation: {e}", tag="ERROR")
|
||||
logger.warning(
|
||||
"Please run 'python -m playwright install' manually after the installation."
|
||||
)
|
||||
# logger.error(f"Error during Playwright installation: {e}", tag="ERROR")
|
||||
logger.warning(f"Please run '{sys.executable} -m playwright install --with-deps' manually after the installation.")
|
||||
except Exception as e:
|
||||
logger.error(f"Unexpected error during Playwright installation: {e}", tag="ERROR")
|
||||
logger.warning(
|
||||
"Please run 'python -m playwright install' manually after the installation."
|
||||
)
|
||||
# logger.error(f"Unexpected error during Playwright installation: {e}", tag="ERROR")
|
||||
logger.warning(f"Please run '{sys.executable} -m playwright install --with-deps' manually after the installation.")
|
||||
|
||||
def run_migration():
|
||||
"""Initialize database during installation"""
|
||||
@@ -45,7 +40,44 @@ def run_migration():
|
||||
logger.warning(f"Database initialization failed: {e}")
|
||||
logger.warning("Database will be initialized on first use")
|
||||
|
||||
async def setup_docs():
|
||||
"""Download documentation files"""
|
||||
docs_manager = DocsManager(logger)
|
||||
await docs_manager.update_docs()
|
||||
async def run_doctor():
|
||||
"""Test if Crawl4AI is working properly"""
|
||||
logger.info("Running Crawl4AI health check...", tag="INIT")
|
||||
try:
|
||||
from .async_webcrawler import AsyncWebCrawler, BrowserConfig, CrawlerRunConfig, CacheMode
|
||||
|
||||
browser_config = BrowserConfig(
|
||||
headless=True,
|
||||
browser_type="chromium",
|
||||
ignore_https_errors=True,
|
||||
light_mode=True,
|
||||
viewport_width=1280,
|
||||
viewport_height=720
|
||||
)
|
||||
|
||||
run_config = CrawlerRunConfig(
|
||||
cache_mode=CacheMode.BYPASS,
|
||||
screenshot=True,
|
||||
)
|
||||
|
||||
async with AsyncWebCrawler(config=browser_config) as crawler:
|
||||
logger.info("Testing crawling capabilities...", tag="TEST")
|
||||
result = await crawler.arun(
|
||||
url="https://crawl4ai.com",
|
||||
config=run_config
|
||||
)
|
||||
|
||||
if result and result.markdown:
|
||||
logger.success("✅ Crawling test passed!", tag="COMPLETE")
|
||||
return True
|
||||
else:
|
||||
raise Exception("Failed to get content")
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"❌ Test failed: {e}", tag="ERROR")
|
||||
return False
|
||||
|
||||
def doctor():
|
||||
"""Entry point for the doctor command"""
|
||||
import asyncio
|
||||
return asyncio.run(run_doctor())
|
||||
|
||||
@@ -9,6 +9,7 @@ Each section includes detailed examples and explanations of the new capabilities
|
||||
import asyncio
|
||||
import os
|
||||
import json
|
||||
import re
|
||||
from typing import List, Optional, Dict, Any
|
||||
from pydantic import BaseModel, Field
|
||||
from crawl4ai import (
|
||||
@@ -16,9 +17,12 @@ from crawl4ai import (
|
||||
BrowserConfig,
|
||||
CrawlerRunConfig,
|
||||
CacheMode,
|
||||
LLMExtractionStrategy
|
||||
LLMExtractionStrategy,
|
||||
JsonCssExtractionStrategy
|
||||
)
|
||||
from crawl4ai.content_filter_strategy import PruningContentFilter
|
||||
from crawl4ai.content_filter_strategy import RelevantContentFilter
|
||||
from crawl4ai.markdown_generation_strategy import DefaultMarkdownGenerator
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
# Sample HTML for demonstrations
|
||||
SAMPLE_HTML = """
|
||||
@@ -68,10 +72,7 @@ async def demo_ssl_features():
|
||||
print("\n1. Enhanced SSL & Security Demo")
|
||||
print("--------------------------------")
|
||||
|
||||
browser_config = BrowserConfig(
|
||||
ignore_https_errors=True,
|
||||
verbose=True
|
||||
)
|
||||
browser_config = BrowserConfig()
|
||||
|
||||
run_config = CrawlerRunConfig(
|
||||
cache_mode=CacheMode.BYPASS,
|
||||
@@ -84,37 +85,91 @@ async def demo_ssl_features():
|
||||
config=run_config
|
||||
)
|
||||
print(f"SSL Crawl Success: {result.success}")
|
||||
result.ssl_certificate.to_json(
|
||||
os.path.join(os.getcwd(), "ssl_certificate.json")
|
||||
)
|
||||
if not result.success:
|
||||
print(f"SSL Error: {result.error_message}")
|
||||
|
||||
async def demo_content_filtering():
|
||||
"""
|
||||
Smart Content Filtering Demo
|
||||
--------------------------
|
||||
----------------------
|
||||
|
||||
Demonstrates the new content filtering system with:
|
||||
1. Regular expression pattern matching
|
||||
2. Length-based filtering
|
||||
3. Custom filtering rules
|
||||
4. Content chunking strategies
|
||||
|
||||
This is particularly useful for:
|
||||
- Removing advertisements and boilerplate content
|
||||
- Extracting meaningful paragraphs
|
||||
- Filtering out irrelevant sections
|
||||
- Processing content in manageable chunks
|
||||
Demonstrates advanced content filtering capabilities:
|
||||
1. Custom filter to identify and extract specific content
|
||||
2. Integration with markdown generation
|
||||
3. Flexible pruning rules
|
||||
"""
|
||||
print("\n2. Smart Content Filtering Demo")
|
||||
print("--------------------------------")
|
||||
|
||||
content_filter = PruningContentFilter(
|
||||
min_word_threshold=50,
|
||||
threshold_type='dynamic',
|
||||
threshold=0.5
|
||||
# Create a custom content filter
|
||||
class CustomNewsFilter(RelevantContentFilter):
|
||||
def __init__(self):
|
||||
super().__init__()
|
||||
# Add news-specific patterns
|
||||
self.negative_patterns = re.compile(
|
||||
r'nav|footer|header|sidebar|ads|comment|share|related|recommended|popular|trending',
|
||||
re.I
|
||||
)
|
||||
self.min_word_count = 30 # Higher threshold for news content
|
||||
|
||||
def filter_content(self, html: str, min_word_threshold: int = None) -> List[str]:
|
||||
"""
|
||||
Implements news-specific content filtering logic.
|
||||
|
||||
Args:
|
||||
html (str): HTML content to be filtered
|
||||
min_word_threshold (int, optional): Minimum word count threshold
|
||||
|
||||
Returns:
|
||||
List[str]: List of filtered HTML content blocks
|
||||
"""
|
||||
if not html or not isinstance(html, str):
|
||||
return []
|
||||
|
||||
soup = BeautifulSoup(html, 'lxml')
|
||||
if not soup.body:
|
||||
soup = BeautifulSoup(f'<body>{html}</body>', 'lxml')
|
||||
|
||||
body = soup.find('body')
|
||||
|
||||
# Extract chunks with metadata
|
||||
chunks = self.extract_text_chunks(body, min_word_threshold or self.min_word_count)
|
||||
|
||||
# Filter chunks based on news-specific criteria
|
||||
filtered_chunks = []
|
||||
for _, text, tag_type, element in chunks:
|
||||
# Skip if element has negative class/id
|
||||
if self.is_excluded(element):
|
||||
continue
|
||||
|
||||
# Headers are important in news articles
|
||||
if tag_type == 'header':
|
||||
filtered_chunks.append(self.clean_element(element))
|
||||
continue
|
||||
|
||||
# For content, check word count and link density
|
||||
text = element.get_text(strip=True)
|
||||
if len(text.split()) >= (min_word_threshold or self.min_word_count):
|
||||
# Calculate link density
|
||||
links_text = ' '.join(a.get_text(strip=True) for a in element.find_all('a'))
|
||||
link_density = len(links_text) / len(text) if text else 1
|
||||
|
||||
# Accept if link density is reasonable
|
||||
if link_density < 0.5:
|
||||
filtered_chunks.append(self.clean_element(element))
|
||||
|
||||
return filtered_chunks
|
||||
|
||||
# Create markdown generator with custom filter
|
||||
markdown_gen = DefaultMarkdownGenerator(
|
||||
content_filter=CustomNewsFilter()
|
||||
)
|
||||
|
||||
run_config = CrawlerRunConfig(
|
||||
content_filter=content_filter,
|
||||
markdown_generator=markdown_gen,
|
||||
cache_mode=CacheMode.BYPASS
|
||||
)
|
||||
|
||||
@@ -124,25 +179,22 @@ async def demo_content_filtering():
|
||||
config=run_config
|
||||
)
|
||||
print("Filtered Content Sample:")
|
||||
print(result.markdown[:500] + "...\n")
|
||||
print(result.markdown[:500]) # Show first 500 chars
|
||||
|
||||
async def demo_json_extraction():
|
||||
"""
|
||||
Advanced JSON Extraction Demo
|
||||
Improved JSON Extraction Demo
|
||||
---------------------------
|
||||
|
||||
Demonstrates the enhanced JSON extraction capabilities:
|
||||
1. Using different input formats (markdown, html)
|
||||
2. Base element attributes extraction
|
||||
3. Complex nested structures
|
||||
4. Multiple extraction patterns
|
||||
1. Base element attributes extraction
|
||||
2. Complex nested structures
|
||||
3. Multiple extraction patterns
|
||||
|
||||
Key features shown:
|
||||
- Extracting from different input formats (markdown vs html)
|
||||
- Extracting attributes from base elements (href, data-* attributes)
|
||||
- Processing repeated patterns
|
||||
- Handling optional fields
|
||||
- Computing derived values
|
||||
"""
|
||||
print("\n3. Improved JSON Extraction Demo")
|
||||
print("--------------------------------")
|
||||
@@ -152,13 +204,17 @@ async def demo_json_extraction():
|
||||
schema={
|
||||
"name": "Blog Posts",
|
||||
"baseSelector": "div.article-list",
|
||||
"baseFields": [
|
||||
{"name": "list_id", "type": "attribute", "attribute": "data-list-id"},
|
||||
{"name": "category", "type": "attribute", "attribute": "data-category"}
|
||||
],
|
||||
"fields": [
|
||||
{
|
||||
"name": "posts",
|
||||
"selector": "article.post",
|
||||
"type": "nested_list",
|
||||
"baseFields": [
|
||||
{"name": "category", "type": "attribute", "attribute": "data-category"},
|
||||
{"name": "post_id", "type": "attribute", "attribute": "data-post-id"},
|
||||
{"name": "author_id", "type": "attribute", "attribute": "data-author"}
|
||||
],
|
||||
"fields": [
|
||||
@@ -378,10 +434,10 @@ async def main():
|
||||
print("====================================")
|
||||
|
||||
# Run all demos
|
||||
# await demo_ssl_features()
|
||||
# await demo_content_filtering()
|
||||
# await demo_json_extraction()
|
||||
await demo_input_formats()
|
||||
await demo_ssl_features()
|
||||
await demo_content_filtering()
|
||||
await demo_json_extraction()
|
||||
# await demo_input_formats()
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
|
||||
@@ -31,7 +31,14 @@ By the end of this guide, you’ll have installed Crawl4AI, performed a basic cr
|
||||
```bash
|
||||
pip install crawl4ai
|
||||
crawl4ai-setup
|
||||
playwright install --with-deps
|
||||
|
||||
# Verify your installation
|
||||
crawl4ai-doctor
|
||||
```
|
||||
|
||||
If you encounter any browser-related issues, you can install them manually:
|
||||
```bash
|
||||
python -m playwright install --with-deps chrome chromium
|
||||
```
|
||||
|
||||
- **`crawl4ai-setup`** installs and configures Playwright (Chromium by default).
|
||||
|
||||
76
pyproject.toml
Normal file
76
pyproject.toml
Normal file
@@ -0,0 +1,76 @@
|
||||
[build-system]
|
||||
requires = ["setuptools>=64.0.0", "wheel"]
|
||||
build-backend = "setuptools.build_meta"
|
||||
|
||||
[project]
|
||||
name = "Crawl4AI"
|
||||
dynamic = ["version"]
|
||||
description = "🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper"
|
||||
readme = "README.md"
|
||||
requires-python = ">=3.9"
|
||||
license = {text = "MIT"}
|
||||
authors = [
|
||||
{name = "Unclecode", email = "unclecode@kidocode.com"}
|
||||
]
|
||||
dependencies = [
|
||||
"aiosqlite~=0.20",
|
||||
"lxml~=5.3",
|
||||
"litellm>=1.53.1",
|
||||
"numpy>=1.26.0,<3",
|
||||
"pillow~=10.4",
|
||||
"playwright>=1.49.0",
|
||||
"python-dotenv~=1.0",
|
||||
"requests~=2.26",
|
||||
"beautifulsoup4~=4.12",
|
||||
"tf-playwright-stealth>=1.1.0",
|
||||
"xxhash~=3.4",
|
||||
"rank-bm25~=0.2",
|
||||
"aiofiles>=24.1.0",
|
||||
"colorama~=0.4",
|
||||
"snowballstemmer~=2.2",
|
||||
"pydantic>=2.10",
|
||||
"pyOpenSSL>=24.3.0",
|
||||
"psutil>=6.1.1",
|
||||
"nltk>=3.9.1",
|
||||
"playwright",
|
||||
"aiofiles"
|
||||
]
|
||||
classifiers = [
|
||||
"Development Status :: 3 - Alpha",
|
||||
"Intended Audience :: Developers",
|
||||
"License :: OSI Approved :: Apache Software License",
|
||||
"Programming Language :: Python :: 3",
|
||||
"Programming Language :: Python :: 3.9",
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
"Programming Language :: Python :: 3.13",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
torch = ["torch", "nltk", "scikit-learn"]
|
||||
transformer = ["transformers", "tokenizers"]
|
||||
cosine = ["torch", "transformers", "nltk"]
|
||||
sync = ["selenium"]
|
||||
all = [
|
||||
"torch",
|
||||
"nltk",
|
||||
"scikit-learn",
|
||||
"transformers",
|
||||
"tokenizers",
|
||||
"selenium"
|
||||
]
|
||||
|
||||
[project.scripts]
|
||||
crawl4ai-download-models = "crawl4ai.model_loader:main"
|
||||
crawl4ai-migrate = "crawl4ai.migrations:main"
|
||||
crawl4ai-setup = "crawl4ai.install:post_install"
|
||||
crawl4ai-doctor = "crawl4ai.install:doctor"
|
||||
crawl = "crawl4ai.cli:cli"
|
||||
|
||||
[tool.setuptools]
|
||||
packages = ["crawl4ai"]
|
||||
package-data = {"crawl4ai" = ["js_snippet/*.js"]}
|
||||
|
||||
[tool.setuptools.dynamic]
|
||||
version = {attr = "crawl4ai.__version__.__version__"}
|
||||
@@ -1,3 +1,5 @@
|
||||
# Note: These requirements are also specified in pyproject.toml
|
||||
# This file is kept for development environment setup and compatibility
|
||||
aiosqlite~=0.20
|
||||
lxml~=5.3
|
||||
litellm>=1.53.1
|
||||
@@ -14,4 +16,6 @@ aiofiles>=24.1.0
|
||||
colorama~=0.4
|
||||
snowballstemmer~=2.2
|
||||
pydantic>=2.10
|
||||
pyOpenSSL>=24.3.0
|
||||
pyOpenSSL>=24.3.0
|
||||
psutil>=6.1.1
|
||||
nltk>=3.9.1
|
||||
60
setup.py
60
setup.py
@@ -3,6 +3,8 @@ import os
|
||||
from pathlib import Path
|
||||
import shutil
|
||||
|
||||
# Note: Most configuration is now in pyproject.toml
|
||||
# This setup.py is kept for backwards compatibility
|
||||
|
||||
# Create the .crawl4ai folder in the user's home directory if it doesn't exist
|
||||
# If the folder already exists, remove the cache folder
|
||||
@@ -28,28 +30,20 @@ cache_folder.mkdir(exist_ok=True)
|
||||
for folder in content_folders:
|
||||
(crawl4ai_folder / folder).mkdir(exist_ok=True)
|
||||
|
||||
# Read requirements and version
|
||||
__location__ = os.path.realpath(os.path.join(os.getcwd(), os.path.dirname(__file__)))
|
||||
with open(os.path.join(__location__, "requirements.txt")) as f:
|
||||
requirements = f.read().splitlines()
|
||||
|
||||
with open("crawl4ai/__version__.py") as f:
|
||||
for line in f:
|
||||
if line.startswith("__version__"):
|
||||
version = line.split("=")[1].strip().strip('"')
|
||||
break
|
||||
|
||||
# Define requirements
|
||||
default_requirements = requirements
|
||||
torch_requirements = ["torch", "nltk", "scikit-learn"]
|
||||
transformer_requirements = ["transformers", "tokenizers"]
|
||||
cosine_similarity_requirements = ["torch", "transformers", "nltk"]
|
||||
sync_requirements = ["selenium"]
|
||||
version = "0.0.0" # This will be overridden by pyproject.toml's dynamic version
|
||||
try:
|
||||
with open("crawl4ai/__version__.py") as f:
|
||||
for line in f:
|
||||
if line.startswith("__version__"):
|
||||
version = line.split("=")[1].strip().strip('"')
|
||||
break
|
||||
except Exception:
|
||||
pass # Let pyproject.toml handle version
|
||||
|
||||
setup(
|
||||
name="Crawl4AI",
|
||||
version=version,
|
||||
description="🔥🕷️ Crawl4AI: Open-source LLM Friendly Web Crawler & scraper",
|
||||
description="🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & scraper",
|
||||
long_description=open("README.md", encoding="utf-8").read(),
|
||||
long_description_content_type="text/markdown",
|
||||
url="https://github.com/unclecode/crawl4ai",
|
||||
@@ -58,38 +52,18 @@ setup(
|
||||
license="MIT",
|
||||
packages=find_packages(),
|
||||
package_data={
|
||||
'crawl4ai': ['js_snippet/*.js'] # This matches the exact path structure
|
||||
},
|
||||
install_requires=default_requirements
|
||||
+ ["playwright", "aiofiles"], # Added aiofiles
|
||||
extras_require={
|
||||
"torch": torch_requirements,
|
||||
"transformer": transformer_requirements,
|
||||
"cosine": cosine_similarity_requirements,
|
||||
"sync": sync_requirements,
|
||||
"all": default_requirements
|
||||
+ torch_requirements
|
||||
+ transformer_requirements
|
||||
+ cosine_similarity_requirements
|
||||
+ sync_requirements,
|
||||
},
|
||||
entry_points={
|
||||
"console_scripts": [
|
||||
"crawl4ai-download-models=crawl4ai.model_loader:main",
|
||||
"crawl4ai-migrate=crawl4ai.migrations:main",
|
||||
'crawl4ai-setup=crawl4ai.install:post_install',
|
||||
'crawl=crawl4ai.cli:cli',
|
||||
],
|
||||
'crawl4ai': ['js_snippet/*.js']
|
||||
},
|
||||
classifiers=[
|
||||
"Development Status :: 3 - Alpha",
|
||||
"Intended Audience :: Developers",
|
||||
"License :: OSI Approved :: Apache Software License",
|
||||
"Programming Language :: Python :: 3",
|
||||
"Programming Language :: Python :: 3.7",
|
||||
"Programming Language :: Python :: 3.8",
|
||||
"Programming Language :: Python :: 3.9",
|
||||
"Programming Language :: Python :: 3.10",
|
||||
"Programming Language :: Python :: 3.11",
|
||||
"Programming Language :: Python :: 3.12",
|
||||
"Programming Language :: Python :: 3.13",
|
||||
],
|
||||
python_requires=">=3.7",
|
||||
python_requires=">=3.9",
|
||||
)
|
||||
|
||||
63
ssl_certificate.json
Normal file
63
ssl_certificate.json
Normal file
@@ -0,0 +1,63 @@
|
||||
{
|
||||
"subject": {
|
||||
"C": "US",
|
||||
"ST": "California",
|
||||
"L": "Los Angeles",
|
||||
"O": "Internet Corporation for Assigned Names and Numbers",
|
||||
"CN": "www.example.org"
|
||||
},
|
||||
"issuer": {
|
||||
"C": "US",
|
||||
"O": "DigiCert Inc",
|
||||
"CN": "DigiCert Global G2 TLS RSA SHA256 2020 CA1"
|
||||
},
|
||||
"version": 2,
|
||||
"serial_number": "0x75bcef30689c8addf13e51af4afe187",
|
||||
"not_before": "20240130000000Z",
|
||||
"not_after": "20250301235959Z",
|
||||
"fingerprint": "45463a42413a32363a44383a43313a43453a33373a37393a41433a37373a36333a30413a39303a46383a32313a36333a41333a44363a38393a32453a44363a41463a45453a34303a38363a37323a43463a31393a45423a41373a41333a3632",
|
||||
"signature_algorithm": "sha256WithRSAEncryption",
|
||||
"raw_cert": "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",
|
||||
"extensions": [
|
||||
{
|
||||
"name": "authorityKeyIdentifier",
|
||||
"value": "74:85:80:C0:66:C7:DF:37:DE:CF:BD:29:37:AA:03:1D:BE:ED:CD:17"
|
||||
},
|
||||
{
|
||||
"name": "subjectKeyIdentifier",
|
||||
"value": "4C:FE:D0:12:4D:2E:21:CF:6B:FA:F2:F2:B8:4C:49:02:1D:31:91:8A"
|
||||
},
|
||||
{
|
||||
"name": "subjectAltName",
|
||||
"value": "DNS:www.example.org, DNS:example.net, DNS:example.edu, DNS:example.com, DNS:example.org, DNS:www.example.com, DNS:www.example.edu, DNS:www.example.net"
|
||||
},
|
||||
{
|
||||
"name": "certificatePolicies",
|
||||
"value": "Policy: 2.23.140.1.2.2\n CPS: http://www.digicert.com/CPS"
|
||||
},
|
||||
{
|
||||
"name": "keyUsage",
|
||||
"value": "Digital Signature, Key Encipherment"
|
||||
},
|
||||
{
|
||||
"name": "extendedKeyUsage",
|
||||
"value": "TLS Web Server Authentication, TLS Web Client Authentication"
|
||||
},
|
||||
{
|
||||
"name": "crlDistributionPoints",
|
||||
"value": "Full Name:\n URI:http://crl3.digicert.com/DigiCertGlobalG2TLSRSASHA2562020CA1-1.crl\nFull Name:\n URI:http://crl4.digicert.com/DigiCertGlobalG2TLSRSASHA2562020CA1-1.crl"
|
||||
},
|
||||
{
|
||||
"name": "authorityInfoAccess",
|
||||
"value": "OCSP - URI:http://ocsp.digicert.com\nCA Issuers - URI:http://cacerts.digicert.com/DigiCertGlobalG2TLSRSASHA2562020CA1-1.crt"
|
||||
},
|
||||
{
|
||||
"name": "basicConstraints",
|
||||
"value": "CA:FALSE"
|
||||
},
|
||||
{
|
||||
"name": "ct_precert_scts",
|
||||
"value": "Signed Certificate Timestamp:\n Version : v1 (0x0)\n Log ID : 4E:75:A3:27:5C:9A:10:C3:38:5B:6C:D4:DF:3F:52:EB:\n 1D:F0:E0:8E:1B:8D:69:C0:B1:FA:64:B1:62:9A:39:DF\n Timestamp : Jan 30 19:22:50.340 2024 GMT\n Extensions: none\n Signature : ecdsa-with-SHA256\n 30:43:02:1F:40:51:0A:0C:4F:6C:10:55:C6:17:16:67:\n 6E:9A:F0:90:9E:F3:73:F5:25:9E:B0:9A:FE:7A:1A:C5:\n 5C:C8:C0:02:20:38:29:31:B1:28:E4:72:48:4D:34:4F:\n 9E:8C:93:E2:61:BC:70:BA:D6:8C:4B:E1:72:15:1D:11:\n C5:94:BA:4D:53\nSigned Certificate Timestamp:\n Version : v1 (0x0)\n Log ID : 7D:59:1E:12:E1:78:2A:7B:1C:61:67:7C:5E:FD:F8:D0:\n 87:5C:14:A0:4E:95:9E:B9:03:2F:D9:0E:8C:2E:79:B8\n Timestamp : Jan 30 19:22:50.288 2024 GMT\n Extensions: none\n Signature : ecdsa-with-SHA256\n 30:45:02:20:5D:BF:96:77:A5:91:5B:7E:0A:0C:DE:D1:\n A9:09:33:37:67:10:4C:42:CC:41:45:27:53:4B:A7:7C:\n 77:63:40:73:02:21:00:B2:E8:09:3F:66:4C:C3:7D:3B:\n 21:73:20:15:79:32:45:D5:2F:2B:93:7F:63:80:CC:03:\n 9A:ED:DF:31:D8:7E:97\nSigned Certificate Timestamp:\n Version : v1 (0x0)\n Log ID : E6:D2:31:63:40:77:8C:C1:10:41:06:D7:71:B9:CE:C1:\n D2:40:F6:96:84:86:FB:BA:87:32:1D:FD:1E:37:8E:50\n Timestamp : Jan 30 19:22:50.335 2024 GMT\n Extensions: none\n Signature : ecdsa-with-SHA256\n 30:46:02:21:00:E0:AA:21:FD:58:B3:75:05:35:B6:36:\n 76:13:65:46:81:64:97:5E:4C:27:42:68:98:86:60:1E:\n 29:C5:4B:1D:E0:02:21:00:FB:24:81:85:B1:D1:A8:97:\n B9:2C:B3:6A:5E:E2:56:2B:0A:03:D5:73:E8:86:66:4B:\n AA:9E:3D:BA:86:A8:6B:D1"
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user