File size: 12,847 Bytes
bf64b03 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 | """
VortexScienceScraper: Scrapes scientific content from open access sources.
Respects robots.txt and rate limits.
"""
import time
import requests
from typing import List, Dict, Optional
from urllib.robotparser import RobotFileParser
from pathlib import Path
import json
class VortexScienceScraper:
"""
Scrapes scientific content from open access sources.
Sources: arXiv, PubMed Central, Wikipedia, NIST, NASA.
"""
SOURCES = {
"arxiv": {
"base_url": "https://arxiv.org",
"search_url": "https://arxiv.org/search/",
"rate_limit": 1.0, # seconds between requests
"robots": "https://arxiv.org/robots.txt",
},
"pubmed": {
"base_url": "https://www.ncbi.nlm.nih.gov/pmc",
"search_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/",
"rate_limit": 0.5,
"robots": "https://www.ncbi.nlm.nih.gov/robots.txt",
},
"wikipedia": {
"base_url": "https://en.wikipedia.org",
"search_url": "https://en.wikipedia.org/w/api.php",
"rate_limit": 0.1,
"robots": "https://en.wikipedia.org/robots.txt",
},
"nist": {
"base_url": "https://webbook.nist.gov",
"search_url": "https://webbook.nist.gov/cgi/cbook.cgi",
"rate_limit": 1.0,
"robots": "https://webbook.nist.gov/robots.txt",
},
"nasa": {
"base_url": "https://ntrs.nasa.gov",
"search_url": "https://ntrs.nasa.gov/api/citations/search",
"rate_limit": 1.0,
"robots": "https://ntrs.nasa.gov/robots.txt",
},
}
def __init__(
self,
output_dir: str = "./data/scraped",
respect_robots: bool = True,
user_agent: str = "VortexScientificBot/1.0",
):
"""
Initialize scraper.
Args:
output_dir: Directory to save scraped data
respect_robots: Whether to respect robots.txt
user_agent: User agent string for requests
"""
self.output_dir = Path(output_dir)
self.output_dir.mkdir(parents=True, exist_ok=True)
self.respect_robots = respect_robots
self.user_agent = user_agent
self.session = requests.Session()
self.session.headers.update({"User-Agent": user_agent})
# Cache for robots.txt
self.robots_cache = {}
# Rate limit tracking
self.last_request_time = {}
def _check_robots_allowed(self, url: str) -> bool:
"""Check if robots.txt allows scraping the URL."""
if not self.respect_robots:
return True
# Extract base domain
from urllib.parse import urlparse
parsed = urlparse(url)
base_url = f"{parsed.scheme}://{parsed.netloc}"
if base_url not in self.robots_cache:
rp = RobotFileParser()
rp.set_url(base_url + "/robots.txt")
try:
rp.read()
self.robots_cache[base_url] = rp
except Exception as e:
print(f"Could not read robots.txt for {base_url}: {e}")
return False
rp = self.robots_cache[base_url]
return rp.can_fetch(self.user_agent, url)
def _rate_limit(self, source: str):
"""Enforce rate limiting for a source."""
now = time.time()
last = self.last_request_time.get(source, 0)
delay = self.SOURCES[source]["rate_limit"]
if now - last < delay:
time.sleep(delay - (now - last))
self.last_request_time[source] = time.time()
def scrape_arxiv(
self,
query: str,
max_results: int = 100,
categories: Optional[List[str]] = None,
) -> List[Dict]:
"""
Scrape arXiv papers.
Args:
query: Search query
max_results: Maximum number of results
categories: Optional list of arXiv categories (e.g., ['physics', 'math'])
Returns:
List of paper metadata and abstracts
"""
papers = []
params = {
"query": query,
"searchtype": "all",
"abstracts": "show",
"size": min(max_results, 200), # arXiv max per page
"order": "-announced_date_first",
}
if categories:
params["filter"] = "categories:" + "+OR+".join(categories)
url = self.SOURCES["arxiv"]["search_url"]
if not self._check_robots_allowed(url):
print(f"Robots.txt disallows scraping {url}")
return papers
try:
self._rate_limit("arxiv")
response = self.session.get(url, params=params)
response.raise_for_status()
# Parse HTML (simplified - would use BeautifulSoup in practice)
# For now, return placeholder
print(f"Scraped arXiv query '{query}' - got response status {response.status_code}")
# Placeholder: would extract paper titles, abstracts, PDF links
for i in range(min(10, max_results)):
papers.append({
"source": "arxiv",
"title": f"Paper {i}",
"abstract": "Abstract placeholder...",
"pdf_url": f"https://arxiv.org/pdf/{i}.pdf",
})
except Exception as e:
print(f"Error scraping arXiv: {e}")
return papers
def scrape_pubmed(
self,
query: str,
max_results: int = 100,
) -> List[Dict]:
"""Scrape PubMed Central articles."""
articles = []
# PubMed API endpoint
url = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils/esearch.fcgi"
params = {
"db": "pmc",
"term": query,
"retmax": max_results,
"retmode": "json",
}
if not self._check_robots_allowed(url):
print(f"Robots.txt disallows {url}")
return articles
try:
self._rate_limit("pubmed")
response = self.session.get(url, params=params)
response.raise_for_status()
data = response.json()
pmc_ids = data.get("esearchresult", {}).get("idlist", [])
for pmc_id in pmc_ids[:10]: # Limit for demo
articles.append({
"source": "pubmed",
"pmc_id": pmc_id,
"url": f"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC{pmc_id}/",
})
print(f"Found {len(pmc_ids)} PubMed articles")
except Exception as e:
print(f"Error scraping PubMed: {e}")
return articles
def scrape_wikipedia(
self,
topic: str,
max_pages: int = 10,
) -> List[Dict]:
"""Scrape Wikipedia science articles."""
pages = []
# Wikipedia API
url = "https://en.wikipedia.org/w/api.php"
params = {
"action": "query",
"format": "json",
"prop": "extracts",
"exintro": True,
"titles": topic,
"redirects": True,
}
if not self._check_robots_allowed(url):
print(f"Robots.txt disallows {url}")
return pages
try:
self._rate_limit("wikipedia")
response = self.session.get(url, params=params)
response.raise_for_status()
data = response.json()
pages_data = data.get("query", {}).get("pages", {})
for page_id, page in pages_data.items():
if "extract" in page:
pages.append({
"source": "wikipedia",
"title": page.get("title", ""),
"text": page.get("extract", ""),
})
except Exception as e:
print(f"Error scraping Wikipedia: {e}")
return pages
def scrape_nist(
self,
element: str,
) -> List[Dict]:
"""Scrape NIST chemistry webbook for element data."""
data = []
url = "https://webbook.nist.gov/cgi/cbook.cgi"
params = {
"Formula": element,
"Units": "SI",
"Submit": "Submit",
}
if not self._check_robots_allowed(url):
print(f"Robots.txt disallows {url}")
return data
try:
self._rate_limit("nist")
response = self.session.get(url, params=params)
response.raise_for_status()
# Placeholder - would parse HTML tables
data.append({
"source": "nist",
"element": element,
"html": response.text[:1000],
})
except Exception as e:
print(f"Error scraping NIST: {e}")
return data
def scrape_nasa(
self,
query: str,
max_results: int = 50,
) -> List[Dict]:
"""Scrape NASA technical reports."""
reports = []
url = "https://ntrs.nasa.gov/api/citations/search"
params = {
"q": query,
"page[size]": max_results,
}
if not self._check_robots_allowed(url):
print(f"Robots.txt disallows {url}")
return reports
try:
self._rate_limit("nasa")
response = self.session.get(url, params=params)
response.raise_for_status()
data = response.json()
for item in data.get("data", [])[:10]:
reports.append({
"source": "nasa",
"title": item.get("attributes", {}).get("title", ""),
"abstract": item.get("attributes", {}).get("abstract", ""),
"download_url": item.get("attributes", {}).get("downloads", {}).get("pdf", ""),
})
except Exception as e:
print(f"Error scraping NASA: {e}")
return reports
def save_results(
self,
results: List[Dict],
filename: str,
):
"""Save scraped results to JSON."""
output_path = self.output_dir / filename
with open(output_path, "w", encoding="utf-8") as f:
json.dump(results, f, indent=2, ensure_ascii=False)
print(f"Saved {len(results)} results to {output_path}")
def scrape_all_sources(
self,
queries: Dict[str, str],
max_per_source: int = 50,
) -> Dict[str, List[Dict]]:
"""
Scrape all sources with given queries.
Args:
queries: Dict mapping source name to query string
max_per_source: Max results per source
Returns:
Dict mapping source to list of results
"""
all_results = {}
for source, query in queries.items():
if source not in self.SOURCES:
print(f"Unknown source: {source}")
continue
print(f"Scraping {source} with query: {query}")
if source == "arxiv":
results = self.scrape_arxiv(query, max_results=max_per_source)
elif source == "pubmed":
results = self.scrape_pubmed(query, max_results=max_per_source)
elif source == "wikipedia":
results = self.scrape_wikipedia(query, max_pages=max_per_source)
elif source == "nist":
results = self.scrape_nist(query)
elif source == "nasa":
results = self.scrape_nasa(query, max_results=max_per_source)
else:
results = []
all_results[source] = results
# Save intermediate results
self.save_results(results, f"{source}_results.json")
return all_results
def test_scraper():
"""Test the scraper (limited)."""
scraper = VortexScienceScraper()
# Test Wikipedia (lightweight)
print("Testing Wikipedia scrape...")
results = scraper.scrape_wikipedia("quantum mechanics", max_pages=2)
print(f"Got {len(results)} Wikipedia pages")
# Test arXiv (rate limited)
print("Testing arXiv scrape...")
results = scraper.scrape_arxiv("quantum", max_results=5)
print(f"Got {len(results)} arXiv papers")
print("Scraper test passed!")
if __name__ == "__main__":
test_scraper()
|