File size: 10,407 Bytes
38b4eff | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 | # tools/web_fetcher.py
#
# Fetch and parse web content
# - Get page content
# - Extract text, links, images
# - Summarize (uses local model)
# - No external APIs (privacy-first)
import re
import json
import urllib.request
import urllib.error
from typing import Dict, Any, List, Optional
from html.parser import HTMLParser
class TextExtractor(HTMLParser):
"""Extract text content from HTML."""
def __init__(self):
super().__init__()
self.text_parts = []
self.current_tag = None
self.skip_tags = {'script', 'style', 'nav', 'footer', 'header', 'aside'}
self.links = []
self.images = []
self.meta = {}
def handle_starttag(self, tag, attrs):
self.current_tag = tag.lower()
attrs_dict = dict(attrs)
if tag.lower() == 'a' and 'href' in attrs_dict:
self.links.append({
'url': attrs_dict['href'],
'text': ''
})
elif tag.lower() == 'img' and 'src' in attrs_dict:
self.images.append({
'src': attrs_dict['src'],
'alt': attrs_dict.get('alt', '')
})
elif tag.lower() == 'meta':
name = attrs_dict.get('name') or attrs_dict.get('property', '')
content = attrs_dict.get('content', '')
if name and content:
self.meta[name] = content
def handle_endtag(self, tag):
self.current_tag = None
def handle_data(self, data):
if self.current_tag in self.skip_tags:
return
text = data.strip()
if text:
self.text_parts.append(text)
# Add text to last link if we're inside an anchor
if self.current_tag == 'a' and self.links:
self.links[-1]['text'] += ' ' + text
def get_text(self) -> str:
return ' '.join(self.text_parts)
class WebFetcher:
"""Fetch and parse web content without external APIs."""
def __init__(self, timeout: int = 30, max_size: int = 500000):
self.timeout = timeout
self.max_size = max_size
self.headers = {
'User-Agent': 'Mozilla/5.0 (compatible; NeuralAI/1.0)',
'Accept': 'text/html,application/xhtml+xml',
'Accept-Language': 'en-US,en;q=0.9',
}
def fetch(self, url: str) -> Dict[str, Any]:
"""
Fetch a URL and return parsed content.
Returns:
{
"success": bool,
"url": str,
"status": int,
"title": str,
"text": str,
"links": list,
"images": list,
"meta": dict
}
"""
try:
request = urllib.request.Request(url, headers=self.headers)
with urllib.request.urlopen(request, timeout=self.timeout) as response:
status = response.status
content = response.read(self.max_size).decode('utf-8', errors='ignore')
# Parse HTML
parser = TextExtractor()
parser.feed(content)
# Extract title
title_match = re.search(r'<title[^>]*>(.*?)</title>', content, re.IGNORECASE | re.DOTALL)
title = title_match.group(1).strip() if title_match else ""
# Clean title
title = re.sub(r'\s+', ' ', title)
return {
"success": True,
"url": url,
"status": status,
"title": title,
"text": parser.get_text()[:10000], # Limit text length
"links": parser.links[:50], # Limit links
"images": parser.images[:20], # Limit images
"meta": parser.meta
}
except urllib.error.HTTPError as e:
return {
"success": False,
"error": f"HTTP Error: {e.code} {e.reason}",
"url": url,
"status": e.code,
"title": "",
"text": "",
"links": [],
"images": [],
"meta": {}
}
except urllib.error.URLError as e:
return {
"success": False,
"error": f"URL Error: {str(e.reason)}",
"url": url,
"status": 0,
"title": "",
"text": "",
"links": [],
"images": [],
"meta": {}
}
except Exception as e:
return {
"success": False,
"error": str(e),
"url": url,
"status": 0,
"title": "",
"text": "",
"links": [],
"images": [],
"meta": {}
}
def extract_text(self, url: str) -> Dict[str, Any]:
"""
Extract only text content from a URL.
Returns:
{
"success": bool,
"url": str,
"title": str,
"text": str,
"word_count": int
}
"""
result = self.fetch(url)
if not result["success"]:
return {
"success": False,
"error": result.get("error", "Unknown error"),
"url": url,
"title": "",
"text": "",
"word_count": 0
}
text = result["text"]
words = text.split()
return {
"success": True,
"url": url,
"title": result["title"],
"text": text,
"word_count": len(words)
}
def extract_links(self, url: str) -> Dict[str, Any]:
"""
Extract all links from a URL.
Returns:
{
"success": bool,
"url": str,
"links": [{"url": str, "text": str}],
"total": int
}
"""
result = self.fetch(url)
if not result["success"]:
return {
"success": False,
"error": result.get("error", "Unknown error"),
"url": url,
"links": [],
"total": 0
}
# Filter and clean links
clean_links = []
for link in result["links"]:
href = link.get("url", "")
text = link.get("text", "").strip()
# Skip empty or javascript links
if not href or href.startswith("javascript:"):
continue
# Make relative URLs absolute
if href.startswith("/"):
from urllib.parse import urljoin
href = urljoin(url, href)
clean_links.append({
"url": href,
"text": text[:100] # Limit text length
})
return {
"success": True,
"url": url,
"links": clean_links,
"total": len(clean_links)
}
def get_meta(self, url: str) -> Dict[str, Any]:
"""
Extract metadata (OpenGraph, Twitter cards, etc) from a URL.
Returns:
{
"success": bool,
"url": str,
"title": str,
"description": str,
"image": str,
"meta": dict
}
"""
result = self.fetch(url)
if not result["success"]:
return {
"success": False,
"error": result.get("error", "Unknown error"),
"url": url,
"title": "",
"description": "",
"image": "",
"meta": {}
}
meta = result["meta"]
# Extract common metadata
title = (
meta.get("og:title") or
meta.get("twitter:title") or
result["title"]
)
description = (
meta.get("og:description") or
meta.get("twitter:description") or
meta.get("description", "")
)
image = (
meta.get("og:image") or
meta.get("twitter:image", "")
)
return {
"success": True,
"url": url,
"title": title,
"description": description,
"image": image,
"meta": meta
}
def check_status(self, url: str) -> Dict[str, Any]:
"""
Check if a URL is accessible (HEAD request).
Returns:
{
"success": bool,
"url": str,
"status": int,
"reachable": bool
}
"""
try:
request = urllib.request.Request(url, headers=self.headers, method='HEAD')
with urllib.request.urlopen(request, timeout=10) as response:
return {
"success": True,
"url": url,
"status": response.status,
"reachable": response.status < 400
}
except urllib.error.HTTPError as e:
return {
"success": True,
"url": url,
"status": e.code,
"reachable": False
}
except Exception as e:
return {
"success": False,
"error": str(e),
"url": url,
"status": 0,
"reachable": False
}
if __name__ == "__main__":
# Test the web fetcher
fetcher = WebFetcher()
print("Testing fetch...")
result = fetcher.fetch("https://example.com")
print(f"Title: {result.get('title')}")
print(f"Text length: {len(result.get('text', ''))}")
print(f"Links: {len(result.get('links', []))}")
print("\nTesting meta extraction...")
result = fetcher.get_meta("https://example.com")
print(f"Meta: {result}")
|