Spaces:
Sleeping
Sleeping
File size: 6,565 Bytes
6f509ec |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 |
#!/usr/bin/env python3
"""
Test script for the web crawler - tests only the URL frontier and downloader
without requiring MongoDB
"""
import os
import sys
import time
import logging
import threading
from urllib.parse import urlparse
import redis
# Make sure we're in the right directory
script_dir = os.path.dirname(os.path.abspath(__file__))
os.chdir(script_dir)
# Set up logging
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s [%(name)s] %(levelname)s: %(message)s',
handlers=[
logging.StreamHandler(sys.stdout),
logging.FileHandler(os.path.join(script_dir, 'test_crawler.log'))
]
)
logger = logging.getLogger("test_crawler")
# Import our modules
import config
from frontier import URLFrontier
from models import URL, Priority, URLStatus
from downloader import HTMLDownloader
from parser import HTMLParser
from robots import RobotsHandler
from dns_resolver import DNSResolver
# Import local configuration if available
try:
import local_config
# Override config settings with local settings
for key in dir(local_config):
if key.isupper():
setattr(config, key, getattr(local_config, key))
logger.info("Loaded local configuration")
except ImportError:
logger.warning("No local_config.py found - using default config")
def test_redis():
"""Test Redis connection"""
try:
logger.info(f"Testing Redis connection to {config.REDIS_URI}")
r = redis.from_url(config.REDIS_URI)
r.ping()
logger.info("Redis connection successful")
return True
except Exception as e:
logger.error(f"Redis connection failed: {e}")
return False
def test_robots_txt():
"""Test robots.txt handling"""
try:
logger.info("Testing robots.txt handling")
robots_handler = RobotsHandler()
test_urls = [
"https://www.google.com/",
"https://www.github.com/",
"https://sagarnildas.com/",
]
for url in test_urls:
logger.info(f"Checking robots.txt for {url}")
allowed, crawl_delay = robots_handler.can_fetch(url)
logger.info(f" Allowed: {allowed}, Crawl delay: {crawl_delay}")
return True
except Exception as e:
logger.error(f"Error testing robots.txt: {e}")
return False
def test_dns_resolver():
"""Test DNS resolver"""
try:
logger.info("Testing DNS resolver")
dns_resolver = DNSResolver()
test_domains = [
"www.google.com",
"www.github.com",
"example.com",
]
for domain in test_domains:
logger.info(f"Resolving {domain}")
ip = dns_resolver.resolve(f"https://{domain}/")
logger.info(f" IP: {ip}")
return True
except Exception as e:
logger.error(f"Error testing DNS resolver: {e}")
return False
def test_url_frontier():
"""Test URL frontier"""
try:
logger.info("Testing URL frontier")
frontier = URLFrontier()
# Clear frontier
frontier.clear()
# Add some URLs
test_urls = [
"https://www.google.com/",
"https://www.github.com/",
"https://sagarnildas.com/",
]
for i, url in enumerate(test_urls):
url_obj = URL(
url=url,
priority=Priority.MEDIUM,
status=URLStatus.PENDING,
depth=0
)
added = frontier.add_url(url_obj)
logger.info(f"Added {url}: {added}")
# Check size
size = frontier.size()
logger.info(f"Frontier size: {size}")
# Get next URL
url = frontier.get_next_url()
if url:
logger.info(f"Next URL: {url.url} (priority: {url.priority})")
else:
logger.info("No URL available")
return True
except Exception as e:
logger.error(f"Error testing URL frontier: {e}")
return False
def test_downloader():
"""Test HTML downloader"""
try:
logger.info("Testing HTML downloader")
downloader = HTMLDownloader()
test_urls = [
URL(url="https://sagarnildas.com/", priority=Priority.MEDIUM, status=URLStatus.PENDING, depth=0),
URL(url="https://www.google.com/", priority=Priority.MEDIUM, status=URLStatus.PENDING, depth=0),
]
for url_obj in test_urls:
logger.info(f"Downloading {url_obj.url}")
page = downloader.download(url_obj)
if page:
logger.info(f" Downloaded {page.content_length} bytes, status: {page.status_code}")
# Test parsing
parser = HTMLParser()
urls, metadata = parser.parse(page)
logger.info(f" Extracted {len(urls)} URLs and {len(metadata)} metadata items")
else:
logger.info(f" Download failed: {url_obj.error}")
return True
except Exception as e:
logger.error(f"Error testing HTML downloader: {e}")
return False
def run_tests():
"""Run all tests"""
logger.info("Starting crawler component tests")
tests = [
("Redis", test_redis),
("Robots.txt", test_robots_txt),
("DNS Resolver", test_dns_resolver),
("URL Frontier", test_url_frontier),
("HTML Downloader", test_downloader),
]
results = []
for name, test_func in tests:
logger.info(f"\n=== Testing {name} ===")
start_time = time.time()
success = test_func()
elapsed = time.time() - start_time
result = {
"name": name,
"success": success,
"time": elapsed
}
results.append(result)
logger.info(f"=== {name} test {'succeeded' if success else 'failed'} in {elapsed:.2f}s ===\n")
# Print summary
logger.info("\n=== Test Summary ===")
all_success = True
for result in results:
status = "SUCCESS" if result["success"] else "FAILED"
logger.info(f"{result['name']}: {status} ({result['time']:.2f}s)")
if not result["success"]:
all_success = False
if all_success:
logger.info("All tests passed!")
else:
logger.warning("Some tests failed. Check logs for details.")
return all_success
if __name__ == "__main__":
run_tests() |