Spaces:

hchevva
/

TOXRA.AI

Sleeping

App Files Files Community

hchevva commited on 14 days ago

Commit

fc29964

verified ·

1 Parent(s): 05faca4

Upload 14 files

Browse files

Files changed (12) hide show

core/.DS_Store +0 -0
core/__init__.py +1 -0
core/config.py +34 -12
core/pdf_report.py +72 -60
core/rate_limit.py +56 -43
core/sources/__init__.py +1 -0
core/sources/ai_summary.py +24 -16
core/sources/cdc.py +268 -329
core/sources/ctx.py +136 -16
core/sources/ntp.py +47 -1
core/sources/pubchem.py +159 -170
core/sources/scholar.py +9 -5

core/.DS_Store ADDED Viewed

Binary file (6.15 kB). View file

core/__init__.py CHANGED Viewed

	@@ -0,0 +1 @@


1	+ """Core package for the HF demo app."""

core/config.py CHANGED Viewed

@@ -1,17 +1,39 @@
-import os
-from pydantic import BaseModel
-class Settings(BaseModel):
-    openai_api_key: str | None = os.getenv("OPENAI_API_KEY")
-    openai_model: str = os.getenv("OPENAI_MODEL", "gpt-4o")
-    ctx_api_key: str | None = os.getenv("CTX_API_KEY")
-    ctx_base_url: str = os.getenv("CTX_BASE_URL", "https://comptox.epa.gov/ctx-api")
-    http_timeout_s: float = float(os.getenv("HTTP_TIMEOUT_S", "12"))
-    cache_ttl_seconds: int = int(os.getenv("CACHE_TTL_SECONDS", "86400"))  # 24h
-    max_ai_summaries_per_day: int = int(os.getenv("MAX_AI_SUMMARIES_PER_DAY", "100"))
-    redis_url: str | None = os.getenv("REDIS_URL")
-settings = Settings()

+from __future__ import annotations
+from pydantic import Field, AliasChoices
+from pydantic_settings import BaseSettings, SettingsConfigDict
+class Settings(BaseSettings):
+    # App behavior
+    max_ai_summaries_per_day: int = 25
+    cache_ttl_seconds: int = 3600
+    # OpenAI
+    openai_api_key: str = Field(
+        default="",
+        validation_alias=AliasChoices("OPENAI_API_KEY", "OPENAI_KEY"),
+    )
+    openai_model: str = Field(
+        default="gpt-4o-mini",
+        validation_alias=AliasChoices("OPENAI_MODEL"),
+    )
+    openai_timeout_seconds: int = Field(default=30, validation_alias=AliasChoices("OPENAI_TIMEOUT"))
+    # Optional Redis backing for rate limits
+    redis_url: str = Field(default="", validation_alias=AliasChoices("REDIS_URL"))
+    # CTX / CompTox
+    ctx_base_url: str = Field(
+        default="https://comptox.epa.gov/ctx-api",
+        validation_alias=AliasChoices("CTX_BASE_URL"),
+    )
+    ctx_api_key: str = Field(
+        default="",
+        validation_alias=AliasChoices("CTX_API_KEY", "COMPTOX_API_KEY", "CTX_KEY"),
+    )
+    model_config = SettingsConfigDict(env_prefix="", case_sensitive=False)
+settings = Settings()

core/pdf_report.py CHANGED Viewed

@@ -1,65 +1,77 @@
 from __future__ import annotations
 import json
-from datetime import datetime
-from pathlib import Path
 from typing import Any, Dict, Tuple
 from reportlab.lib.pagesizes import letter
-from reportlab.lib.styles import getSampleStyleSheet
-from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, Preformatted, PageBreak
-from reportlab.lib.units import inch
-def _pretty(obj: Any) -> str:
-    return json.dumps(obj, indent=2, ensure_ascii=False)
-def build_pdf(cas: str, evidence: Dict[str, Any], ai_summary: str | None) -> Tuple[str, str]:
-    ts = datetime.utcnow().strftime("%Y%m%d_%H%M%S")
-    out_dir = Path("outputs")
-    out_dir.mkdir(parents=True, exist_ok=True)
-    json_path = out_dir / f"toxrai_{cas}_{ts}.json"
-    pdf_path  = out_dir / f"toxrai_{cas}_{ts}.pdf"
-    json_path.write_text(_pretty({
-        "cas": cas,
-        "generated_utc": datetime.utcnow().isoformat() + "Z",
-        "evidence": evidence,
-        "ai_summary": ai_summary,
-    }), encoding="utf-8")
-    styles = getSampleStyleSheet()
-    doc = SimpleDocTemplate(
-        str(pdf_path),
-        pagesize=letter,
-        leftMargin=0.75*inch, rightMargin=0.75*inch,
-        topMargin=0.75*inch, bottomMargin=0.75*inch
-    )
-    story = []
-    story.append(Paragraph("ToxRAI Report", styles["Title"]))
-    story.append(Paragraph(f"<b>CAS:</b> {cas}", styles["Normal"]))
-    story.append(Paragraph(f"<b>Generated (UTC):</b> {datetime.utcnow().isoformat()}Z", styles["Normal"]))
-    story.append(Spacer(1, 12))
-    story.append(Paragraph("<b>AI Summary</b>", styles["Heading2"]))
-    story.append(Paragraph(ai_summary.replace("\n", "<br/>"), styles["Normal"]) if ai_summary else Paragraph("Not generated.", styles["Normal"]))
-    story.append(PageBreak())
-    story.append(Paragraph("<b>Raw Source Outputs</b>", styles["Heading2"]))
-    story.append(Paragraph("If a section is too large, see the JSON evidence packet (downloaded alongside this PDF).", styles["Normal"]))
-    story.append(Spacer(1, 12))
-    MAX_CHARS = 12000
-    for k, v in evidence.items():
-        story.append(Paragraph(f"<b>{k}</b>", styles["Heading3"]))
-        txt = _pretty(v)
-        if len(txt) > MAX_CHARS:
-            story.append(Paragraph(f"Output too large for PDF ({len(txt)} chars). Truncated below; see JSON for full content.", styles["Normal"]))
-            story.append(Spacer(1, 6))
-            story.append(Preformatted(txt[:MAX_CHARS] + "\n... (truncated)", styles["Code"]))
-        else:
-            story.append(Preformatted(txt, styles["Code"]))
-        story.append(Spacer(1, 12))
-    doc.build(story)
-    return str(pdf_path), str(json_path)

 from __future__ import annotations
 import json
+import os
+import tempfile
+import textwrap
+from datetime import datetime, timezone
 from typing import Any, Dict, Tuple
 from reportlab.lib.pagesizes import letter
+from reportlab.pdfgen import canvas
+def _safe_text(value: Any) -> str:
+    if value is None:
+        return ""
+    return str(value).encode("ascii", "replace").decode("ascii")
+def _wrap_lines(text: str, width: int = 95) -> list[str]:
+    lines: list[str] = []
+    for raw in (text or "").splitlines():
+        if not raw:
+            lines.append("")
+            continue
+        lines.extend(textwrap.wrap(raw, width=width))
+    return lines
+def build_pdf(cas: str, evidence: Dict[str, Any], ai_summary: str | None = None) -> Tuple[str, str]:
+    """Generate a PDF + JSON evidence packet and return file paths."""
+    stamp = datetime.now(timezone.utc).strftime("%Y%m%d_%H%M%S")
+    safe_cas = _safe_text(cas or "unknown").replace("/", "_").replace(" ", "_")
+    out_dir = os.path.join(tempfile.gettempdir(), "toxrai_reports")
+    os.makedirs(out_dir, exist_ok=True)
+    pdf_path = os.path.join(out_dir, f"toxrai_{safe_cas}_{stamp}.pdf")
+    json_path = os.path.join(out_dir, f"toxrai_{safe_cas}_{stamp}.json")
+    # JSON evidence
+    with open(json_path, "w", encoding="utf-8") as f:
+        json.dump(evidence, f, ensure_ascii=False, indent=2, default=str)
+    # PDF
+    c = canvas.Canvas(pdf_path, pagesize=letter)
+    width, height = letter
+    y = height - 40
+    def draw_line(line: str):
+        nonlocal y
+        if y < 50:
+            c.showPage()
+            y = height - 40
+        c.drawString(40, y, _safe_text(line))
+        y -= 14
+    draw_line("ToxRAI Evidence Report")
+    draw_line(f"CAS / Query: {safe_cas}")
+    draw_line(f"Generated: {datetime.now(timezone.utc).isoformat()} UTC")
+    draw_line("")
+    if ai_summary:
+        draw_line("AI Summary")
+        for line in _wrap_lines(ai_summary, width=90):
+            draw_line(line)
+        draw_line("")
+    # Include a compact evidence snapshot
+    evidence_text = json.dumps(evidence, ensure_ascii=False, indent=2, default=str)
+    if len(evidence_text) > 8000:
+        evidence_text = evidence_text[:8000] + "\n... (truncated)"
+    draw_line("Evidence JSON (truncated)")
+    for line in _wrap_lines(evidence_text, width=95):
+        draw_line(line)
+    c.save()
+    return pdf_path, json_path

core/rate_limit.py CHANGED Viewed

@@ -1,50 +1,63 @@
 from __future__ import annotations
-import os, json, datetime
-from pathlib import Path
-from typing import Tuple
 from .config import settings
 def _today_key() -> str:
-    return datetime.date.today().isoformat()
-def _redis_client():
-    if not settings.redis_url:
-        return None
-    try:
-        from redis import Redis
-        return Redis.from_url(settings.redis_url, decode_responses=True)
-    except Exception:
-        return None
-def check_and_increment_global_ai_cap() -> Tuple[bool, dict]:
-    limit = settings.max_ai_summaries_per_day
-    day = _today_key()
-    r = _redis_client()
-    if r:
-        key = f"toxrai:ai_summaries:{day}"
-        val = r.incr(key)
-        if val == 1:
-            r.expire(key, 60 * 60 * 24 * 2)
-        return (val <= limit), {"store": "redis", "day": day, "count": int(val), "limit": limit}
-    # fallback: file (may reset on restart if no persistent volume)
-    path = Path("/data/toxrai_limits.json") if os.path.isdir("/data") else Path(".toxrai_limits.json")
-    data = {}
-    if path.exists():
-        try:
-            data = json.loads(path.read_text(encoding="utf-8") or "{}")
-        except Exception:
-            data = {}
-    data.setdefault("ai_summaries", {})
-    data["ai_summaries"].setdefault(day, 0)
-    data["ai_summaries"][day] += 1
-    try:
-        path.write_text(json.dumps(data, indent=2), encoding="utf-8")
-    except Exception:
-        pass
-    count = int(data["ai_summaries"][day])
-    return (count <= limit), {"store": "file", "path": str(path), "day": day, "count": count, "limit": limit}

 from __future__ import annotations
+import threading
+from datetime import datetime, timezone
+from typing import Dict, Tuple, Any
 from .config import settings
+_lock = threading.Lock()
+_state: Dict[str, Any] = {"date": None, "count": 0}
 def _today_key() -> str:
+    return datetime.now(timezone.utc).strftime("%Y%m%d")
+def _in_memory_increment(limit: int) -> Tuple[bool, Dict[str, Any]]:
+    info: Dict[str, Any] = {"limit": limit}
+    with _lock:
+        today = _today_key()
+        if _state["date"] != today:
+            _state["date"] = today
+            _state["count"] = 0
+        _state["count"] += 1
+        count = int(_state["count"])
+    info["count"] = count
+    info["remaining"] = max(0, limit - count)
+    return count <= limit, info
+def _redis_increment(limit: int) -> Tuple[bool, Dict[str, Any]]:
+    info: Dict[str, Any] = {"limit": limit}
+    import redis  # local import to keep optional
+    client = redis.from_url(settings.redis_url, decode_responses=True)
+    key = f"toxrai:ai_cap:{_today_key()}"
+    count = int(client.incr(key))
+    if count == 1:
+        # expire a bit after 24h to avoid unbounded growth
+        client.expire(key, 60 * 60 * 48)
+    info["count"] = count
+    info["remaining"] = max(0, limit - count)
+    return count <= limit, info
+def check_and_increment_global_ai_cap() -> Tuple[bool, Dict[str, Any]]:
+    """Global daily cap to prevent overuse in public demos."""
+    limit = int(settings.max_ai_summaries_per_day or 0)
+    if limit <= 0:
+        return True, {"limit": limit, "count": 0, "remaining": None}
+    if settings.redis_url:
+        try:
+            return _redis_increment(limit)
+        except Exception as e:
+            # Fall back to in-memory, but report the error for debugging.
+            allowed, info = _in_memory_increment(limit)
+            info["redis_error"] = str(e)
+            return allowed, info
+    return _in_memory_increment(limit)

core/sources/__init__.py CHANGED Viewed

	@@ -0,0 +1 @@


1	+ """Source adapters for external datasets and services."""

core/sources/ai_summary.py CHANGED Viewed

@@ -1,23 +1,31 @@
 from __future__ import annotations
-from openai import OpenAI
-from ..config import settings
-def generate_ai_summary(prompt: str) -> dict:
-    if not settings.openai_api_key:
-        return {"ok": False, "error": "OPENAI_API_KEY is not configured."}
-    client = OpenAI(api_key=settings.openai_api_key)
-    resp = client.responses.create(
-    model=settings.openai_model,
-    input=[{"role": "user", "content": prompt}],
-    max_output_tokens=900,
-)
     try:
-        text = resp.output[0].content[0].text
-    except Exception:
-        text = str(resp)
-    return {"ok": True, "text": text, "raw": resp.model_dump()}

 from __future__ import annotations
+from typing import Dict, Any
+from openai import OpenAI
+from core.config import settings
+def generate_ai_summary(prompt: str) -> Dict[str, Any]:
+    if not prompt:
+        return {"ok": False, "error": "Empty prompt"}
+    if not settings.openai_api_key:
+        return {"ok": False, "error": "Missing OPENAI_API_KEY"}
     try:
+        client = OpenAI(api_key=settings.openai_api_key, timeout=settings.openai_timeout_seconds)
+        resp = client.chat.completions.create(
+            model=settings.openai_model,
+            messages=[
+                {"role": "system", "content": "You are a careful, concise toxicology assistant."},
+                {"role": "user", "content": prompt},
+            ],
+            temperature=0.2,
+        )
+        text = (resp.choices[0].message.content or "").strip()
+        if not text:
+            return {"ok": False, "error": "Empty response from model"}
+        return {"ok": True, "text": text}
+    except Exception as e:
+        return {"ok": False, "error": str(e)}

core/sources/cdc.py CHANGED Viewed

@@ -1,343 +1,282 @@
-"""CDC/ATSDR ToxProfiles local index + search.
-Why local?
-- CDC ToxProfiles don't have a simple public search API.
-- Production code typically uses a prebuilt index (CAS/name -> URL).
-This file mirrors that approach: you maintain TOXPROFILES as a list of dicts.
-Each item MUST look like:
-    {"name": "Acetone", "cas": "67-64-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=5&tid=1"}
-Return shape is stable for Gradio rendering:
-    {"ok": True, "query": "...", "cas": "...", "matches": [...], "total": N}
-"""
 from __future__ import annotations
 import re
-from typing import Any, Dict, List, Optional
-# Each entry: {"name": str, "cas": str, "url": str}
-TOXPROFILES: List[Dict[str, str]] = [
-      {"name": "Acetone", "cas": "67-64-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=5&tid=1" },
-      {"name": "Acrolein", "cas": "107-02-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=557&tid=102" },
-      {"name": "Acrylamide", "cas": "79-06-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1112&tid=236" },
-      {"name": "Acrylonitrile", "cas": "107-13-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=447&tid=78" },
-      {"name": "Aldrin", "cas": "309-00-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=317&tid=56" },
-      {"name": "Aluminum", "cas": "7429-90-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=191&tid=34" },
-      {"name": "Americium", "cas": "7440-35-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=811&tid=158" },
-      {"name": "Ammonia", "cas": "7664-41-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=11&tid=2" },
-      {"name": "Antimony", "cas": "7440-36-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=332&tid=58" },
-      {"name": "Arsenic", "cas": "7440-38-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=22&tid=3" },
-      {"name": "Asbestos", "cas": "1332-21-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=30&tid=4" },
-      {"name": "Atrazine", "cas": "1912-24-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=338&tid=59" },
-      {"name": "1,3-Butadiene", "cas": "106-99-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=459&tid=81" },
-      {"name": "1-Bromopropane", "cas": "NA", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1471&tid=285" },
-      {"name": "2,3-Benzofuran", "cas": "271-89-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=915&tid=187" },
-      {"name": "2-Butanone", "cas": "78-93-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=343&tid=60" },
-      {"name": "2-Butoxyethanol", "cas": "111-76-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=347&tid=61" },
-      {"name": "2-Butoxyethanol Acetate", "cas": "112-07-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=347&tid=61" },
-      {"name": "Barium", "cas": "7440-39-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=327&tid=57" },
-      {"name": "Benzene", "cas": "71-43-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=40&tid=14" },
-      {"name": "Benzidine", "cas": "92-87-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=569&tid=105" },
-      {"name": "Beryllium", "cas": "7440-41-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1441&tid=33" },
-      {"name": "Bis(2-chloroethyl) Ether (BCEE)", "cas": "111-44-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=817&tid=159" },
-      {"name": "Bis(chloromethyl) Ether", "cas": "542-88-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=919&tid=188" },
-      {"name": "Boron", "cas": "7440-42-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=453&tid=80" },
-      {"name": "Bromodichloromethane", "cas": "75-27-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=708&tid=127" },
-      {"name": "Bromoform", "cas": "75-25-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=713&tid=128" },
-      {"name": "Dibromochloromethane", "cas": "124-48-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=713&tid=128" },
-      {"name": "Bromomethane", "cas": "74-83-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=822&tid=160" },
-      {"name": "Cadmium", "cas": "7440-43-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=48&tid=15" },
-      {"name": "Carbon Disulfide", "cas": "782-182-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=474&tid=84" },
-      {"name": "Carbon Monoxide", "cas": "630-08-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1145&tid=253" },
-      {"name": "Carbon Tetrachloride", "cas": "56-23-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=196&tid=35" },
-      {"name": "Cesium", "cas": "7440-46-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=578&tid=107" },
-      {"name": "Chlordane", "cas": "12789-03-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=355&tid=62" },
-      {"name": "Chlordecone", "cas": "143-50-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1190&tid=276" },
-      {"name": "Chlorfenvinphos", "cas": "470-90-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=932&tid=193" },
-      {"name": "Chlorinated Dibenzo-p-dioxins (CDDs)", "cas": "NA", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=366&tid=63" },
-      {"name": "Chlorine", "cas": "7782-50-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1079&tid=36" },
-      {"name": "Chlorine Dioxide", "cas": "10049-04-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=582&tid=108" },
-      {"name": "Chlorite", "cas": "7758-19-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=582&tid=108" },
-      {"name": "Chlorobenzene", "cas": "108-90-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=489&tid=87" },
-      {"name": "Chlorodibenzofurans (CDFs)", "cas": "NA", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=938&tid=194" },
-      {"name": "Chloroethane", "cas": "75-00-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=827&tid=161" },
-      {"name": "Chloroform", "cas": "67-66-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=53&tid=16" },
-      {"name": "Chloromethane", "cas": "74-87-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=587&tid=109" },
-      {"name": "Chlorophenols", "cas": "58-90-2, 88-06-2, 95-57-8, 95-95-4, 106-48-9, 120-83-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=941&tid=195" },
-      {"name": "Chlorpyrifos", "cas": "2921-88-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=495&tid=88" },
-      {"name": "Chromium", "cas": "7440-47-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=62&tid=17" },
-      {"name": "Cobalt", "cas": "7440-48-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=373&tid=64" },
-      {"name": "Copper", "cas": "7440-50-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=206&tid=37" },
-      {"name": "Wood Creosote", "cas": "8021-39-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=66&tid=18" },
-      {"name": "Coal Tar Creosote", "cas": "8001-58-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=66&tid=18" },
-      {"name": "Coal Tar", "cas": "8007-45-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=66&tid=18" },
-      {"name": "Cresols", "cas": "1319-77-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=946&tid=196" },
-      {"name": "Cyanide", "cas": "74-90-8; 143-33-9; 151-50-8; 592-01-8; 544-92-3; 506-61-6; 460-19-5; 506-77-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=72&tid=19" },
-      {"name": "1,1-Dichloroethane", "cas": "75-34-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=718&tid=129" },
-      {"name": "1,1-Dichloroethene", "cas": "75-35-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=722&tid=130" },
-      {"name": "1,2-Dibromo-3-chloropropane", "cas": "96-12-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=852&tid=166" },
-      {"name": "1,2-Dibromoethane", "cas": "106-93-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=726&tid=131" },
-      {"name": "1,2-Dichloroethane", "cas": "107-06-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=592&tid=110" },
-      {"name": "1,2-Dichloropropane", "cas": "78-87-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=831&tid=162" },
-      {"name": "1,2-Diphenylhydrazine", "cas": "122-66-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=952&tid=198" },
-      {"name": "1,3-Dinitrobenzene", "cas": "99-65-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=842&tid=164" },
-      {"name": "1,3,5-Trinitrobenzene", "cas": "99-35-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=842&tid=164" },
-      {"name": "1,4 Dioxane", "cas": "123-91-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=955&tid=199" },
-      {"name": "2,4-Dichlorophenoxyacetic Acid (2,4-D)", "cas": "NA", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1481&tid=288" },
-      {"name": "3,3'-Dichlorobenzidine", "cas": "91-94-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=959&tid=200" },
-      {"name": "DDT", "cas": "50-29-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=81&tid=20" },
-      {"name": "DDE", "cas": "72-55-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=81&tid=20" },
-      {"name": "DDD", "cas": "72-54-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=81&tid=20" },
-      {"name": "DEET (N,N-diethyl-meta-toluamide)", "cas": "NA", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1451&tid=201" },
-      {"name": "Di(2-Ethylhexyl)Phthalate (DEHP)", "cas": "117-81-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=684&tid=65" },
-      {"name": "Di-n-butyl Phthalate", "cas": "84-74-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=859&tid=167" },
-      {"name": "Di-n-octylphthalate (DNOP)", "cas": "117-84-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=973&tid=204" },
-      {"name": "Diazinon", "cas": "333-41-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=512&tid=90" },
-      {"name": "1,2-Dichlorobenzene", "cas": "95-50-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=704&tid=126" },
-      {"name": "1,3-Dichlorobenzene", "cas": "541-73-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=704&tid=126" },
-      {"name": "1,4-Dichlorobenzene", "cas": "106-46-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=704&tid=126" },
-      {"name": "Dichloropropenes", "cas": "26952-23-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=836&tid=163" },
-      {"name": "Dichlorvos", "cas": "62-73-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=597&tid=111" },
-      {"name": "Diethyl phthalate", "cas": "84-66-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=603&tid=112" },
-      {"name": "Diisopropyl Methylphosphonate (DIMP)", "cas": "1445-75-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=969&tid=203" },
-      {"name": "Dinitrocresols (4,6-DNOC)", "cas": "534-52-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1025&tid=218" },
-      {"name": "Dinitrophenols (2,4-DNP)", "cas": "51-28-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=729&tid=132" },
-      {"name": "Dinitrotoluenes (2,4-)", "cas": "121-14-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165" },
-      {"name": "Dinitrotoluenes (2,6-)", "cas": "606-20-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165" },
-      {"name": "Dinitrotoluenes (Mixture)", "cas": "25321-14-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165" },
-      {"name": "Dinitrotoluenes (Other isomers)", "cas": "", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165" },
-      {"name": "Disulfoton", "cas": "0298-04-04", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=978&tid=205" },
-      {"name": "Dieldrin", "cas": "60-57-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=317&tid=56" },
-      {"name": "Endosulfan (mixture)", "cas": "115-29-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=609&tid=113" },
-      {"name": "Endosulfan (α-isomer)", "cas": "959-98-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=609&tid=113" },
-      {"name": "Endosulfan (β-isomer)", "cas": "33213-65-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=609&tid=113" },
-      {"name": "Endrin", "cas": "72-20-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=617&tid=114" },
-      {"name": "Ethion", "cas": "0563-12-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=983&tid=206" },
-      {"name": "Ethylbenzene", "cas": "100-41-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=383&tid=66" },
-      {"name": "Ethylene Glycol", "cas": "107-21-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=86&tid=21" },
-      {"name": "Ethylene Oxide", "cas": "75-21-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=734&tid=133" },
-      {"name": "Fluorides, Hydrogen Fluoride, and Fluorine", "cas": "7664-39-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=212&tid=38" },
-      {"name": "Fluorides, Hydrogen Fluoride, and Fluorine", "cas": "7782-41-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=212&tid=38" },
-      {"name": "Fluorides, Hydrogen Fluoride, and Fluorine", "cas": "7681-49-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=212&tid=38" },
-      {"name": "Formaldehyde", "cas": "50-00-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=220&tid=39" },
-      {"name": "Fuel Oils / Kerosene (Kerosene/Fuel Oil #1)", "cas": "8008-20-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91" },
-      {"name": "Fuel Oils / Kerosene (Fuel Oil #2)", "cas": "68476-30-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91" },
-      {"name": "Fuel Oils / Kerosene (Fuel Oil #3)", "cas": "70892-10-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91" },
-      {"name": "Fuel Oils / Kerosene (Fuel Oil #4)", "cas": "68476-34-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91" },
-      {"name": "Fuel Oils / Kerosene (Fuel Oil #5)", "cas": "68476-31-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91" },
-      {"name": "Gasoline, Automotive (mixture)", "cas": "8006-61-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=468&tid=83" },
-      {"name": "Glutaraldehyde", "cas": "111-30-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1467&tid=284" },
-      {"name": "Glyphosate", "cas": "1071-83-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1488&tid=293" },
-      {"name": "Guthion (Azinphos-methyl)", "cas": "86-50-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1037&tid=207" },
-      {"name": "2-Hexanone", "cas": "591-78-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=738&tid=134" },
-      {"name": "Heptachlor/Heptachlor Epoxide", "cas": "76-44-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=746&tid=135" },
-      {"name": "Heptachlor/Heptachlor Epoxide", "cas": "1024-57-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=746&tid=135" },
-      {"name": "Hexachlorobenzene", "cas": "118-74-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=627&tid=115" },
-      {"name": "Hexachlorobutadiene", "cas": "87-68-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=865&tid=168" },
-      {"name": "Hexachlorocyclohexane (HCH) (Technical Grade)", "cas": "608-73-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138" },
-      {"name": "Hexachlorocyclohexane (HCH) (α-isomer)", "cas": "319-84-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138" },
-      {"name": "Hexachlorocyclohexane (HCH) (β-isomer)", "cas": "319-85-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138" },
-      {"name": "Hexachlorocyclohexane (HCH) (γ-isomer/Lindane)", "cas": "58-89-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138" },
-      {"name": "Hexachlorocyclohexane (HCH) (δ-isomer)", "cas": "319-86-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138" },
-      {"name": "Hexachlorocyclopentadiene (HCCPD)", "cas": "77-47-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=992&tid=208" },
-      {"name": "Hexachloroethane", "cas": "67-72-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=870&tid=169" },
-      {"name": "Hexamethylene Diisocyanate (HDI)", "cas": "822-06-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=874&tid=170" },
-      {"name": "HMX (Octogen)", "cas": "2691-41-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=877&tid=171" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "55957-10-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "68937-40-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "50815-84-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "55962-27-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "66594-31-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "63848-94-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "107028-44-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydraulic Fluids (Mineral oil base example)", "cas": "28777-70-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141" },
-      {"name": "Hydrazines (Hydrazine)", "cas": "0302-01-02", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=502&tid=89" },
-      {"name": "Hydrazines (1,1-Dimethylhydrazine)", "cas": "57-14-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=502&tid=89" },
-      {"name": "Hydrazines (1,2-Dimethylhydrazine)", "cas": "540-73-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=502&tid=89" },
-      {"name": "Hydrogen Sulfide", "cas": "7783-06-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=389&tid=67" },
-      {"name": "Carbonyl Sulfide", "cas": "463-58-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=389&tid=67" },
-      {"name": "n-Hexane", "cas": "110-54-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=393&tid=68" },
-      {"name": "Iodine (elemental)", "cas": "7553-56-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=479&tid=85" },
-      {"name": "Ionizing Radiation", "cas": "N/A", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=484&tid=86" },
-      {"name": "Isophorone", "cas": "78-59-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=763&tid=148" },
-      {"name": "Jet Fuels JP-4 and JP-7 (Mixture)", "cas": "50815-00-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=768&tid=149" },
-      {"name": "JP-5, JP-8, and Jet A (Kerosene base)", "cas": "8008-20-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=773&tid=150" },
-      {"name": "Lead (elemental)", "cas": "7439-92-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=96&tid=22" },
-      {"name": "4,4′-Methylenebis(2-Chloroaniline) (MBOCA)", "cas": "101-14-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=997&tid=209" },
-      {"name": "4,4′-Methylenedianiline", "cas": "101-77-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1001&tid=210" },
-      {"name": "Malathion", "cas": "121-75-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=522&tid=92" },
-      {"name": "Manganese (elemental)", "cas": "7439-96-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=102&tid=23" },
-      {"name": "Mercury (elemental)", "cas": "7439-97-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=115&tid=24" },
-      {"name": "Methoxychlor", "cas": "72-43-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=778&tid=151" },
-      {"name": "Methyl Mercaptan", "cas": "74-93-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=224&tid=40" },
-      {"name": "Methyl Parathion", "cas": "298-00-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=636&tid=117" },
-      {"name": "Methyl tert-Butyl Ether (MTBE)", "cas": "1634-04-04", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=228&tid=41" },
-      {"name": "Methylene Chloride", "cas": "75-09-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=234&tid=42" },
-      {"name": "Mirex", "cas": "2385-85-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1190&tid=276" },
-      {"name": "Chlordecone", "cas": "143-50-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1190&tid=276" },
-      {"name": "Molybdenum (elemental)", "cas": "7439-98-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1482&tid=289" },
-      {"name": "n-Nitrosodi-n-propylamine", "cas": "621-64-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1005&tid=211" },
-      {"name": "N-Nitrosodimethylamine (NDMA)", "cas": "62-75-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=884&tid=173" },
-      {"name": "n-Nitrosodiphenylamine", "cas": "86-30-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1009&tid=212" },
-      {"name": "Naphthalene, 1-Methylnaphthalene, 2-Methylnaphthalene", "cas": "91-20-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=240&tid=43" },
-      {"name": "Naphthalene, 1-Methylnaphthalene, 2-Methylnaphthalene", "cas": "90-12-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=240&tid=43" },
-      {"name": "Naphthalene, 1-Methylnaphthalene, 2-Methylnaphthalene", "cas": "91-57-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=240&tid=43" },
-      {"name": "Nickel (elemental)", "cas": "7440-02-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=245&tid=44" },
-      {"name": "Nitrate and Nitrite (Nitrate ion)", "cas": "14797-55-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1452&tid=258" },
-      {"name": "Nitrate and Nitrite (Nitrite ion)", "cas": "14797-65-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1452&tid=258" },
-      {"name": "Nitrobenzene", "cas": "98-95-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=532&tid=95" },
-      {"name": "Nitrophenols (Group - e.g., 2-Nitrophenol)", "cas": "88-75-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=880&tid=172" },
-      {"name": "Nitrophenols (Group - e.g., 4-Nitrophenol)", "cas": "0100-02-07", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=880&tid=172" },
-      {"name": "Otto Fuel II and its Components (Mixture)", "cas": "6423-43-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=781&tid=152" },
-      {"name": "Parathion", "cas": "56-38-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1425&tid=246" },
-      {"name": "Pentachlorophenol", "cas": "87-86-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=402&tid=70" },
-      {"name": "Perchlorates (Group - e.g., Ammonium)", "cas": "7790-98-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=895&tid=181" },
-      {"name": "Perchlorates (Group - e.g., Potassium)", "cas": "7778-74-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=895&tid=181" },
-      {"name": "Perfluoroalkyls (Group - e.g., PFOA)", "cas": "335-67-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1117&tid=237" },
-      {"name": "Perfluoroalkyls (Group - e.g., PFOS)", "cas": "1763-23-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1117&tid=237" },
-      {"name": "Phenol", "cas": "108-95-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=148&tid=27" },
-      {"name": "Phosphate Ester Flame Retardants (Group - e.g., TBP)", "cas": "126-73-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1119&tid=239" },
-      {"name": "Phosphate Ester Flame Retardants (Group - e.g., TDCPP)", "cas": "13674-87-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1119&tid=239" },
-      {"name": "Phosphorus, White (elemental)", "cas": "7723-14-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=285&tid=52" },
-      {"name": "Plutonium (elemental)", "cas": "2023631", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=648&tid=119" },
-      {"name": "Polybrominated Biphenyls (PBBs) (Group - e.g., Hexa-)", "cas": "12584439", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=529&tid=94" },
-      {"name": "Polybrominated Diphenyl Ethers (PBDEs) (Group - e.g., Deca-)", "cas": "1163-19-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=901&tid=183" },
-      {"name": "Polybrominated Diphenyl Ethers (PBDEs) (Group - Penta- mixture)", "cas": "32534-81-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=901&tid=183" },
-      {"name": "Polybrominated Diphenyl Ethers (PBDEs) (Group - Octa- mixture)", "cas": "32536-52-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=901&tid=183" },
-      {"name": "Polychlorinated Biphenyls (PCBs) (Mixture)", "cas": "1336-36-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=142&tid=26" },
-      {"name": "Polycyclic Aromatic Hydrocarbons (PAHs) (Group - e.g., BaP)", "cas": "50-32-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=122&tid=25" },
-      {"name": "Polycyclic Aromatic Hydrocarbons (PAHs) (Group - e.g., Naphthalene)", "cas": "91-20-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=122&tid=25" },
-      {"name": "Propylene Glycol", "cas": "57-55-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1122&tid=240" },
-      {"name": "Pyrethrins and Pyrethroids (Pyrethrins mixture)", "cas": "8003-34-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=787&tid=153" },
-      {"name": "Pyrethrins and Pyrethroids (e.g., Permethrin)", "cas": "52645-53-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=787&tid=153" },
-      {"name": "Pyridine", "cas": "110-86-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=535&tid=96" },
-      {"name": "Radiation, Ionizing", "cas": "N/A", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=484&tid=86" },
-      {"name": "Radium (elemental)", "cas": "7440-14-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=791&tid=154" },
-      {"name": "Radon (elemental)", "cas": "10043-92-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=407&tid=71" },
-      {"name": "RDX (Cyclonite)", "cas": "121-82-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=412&tid=72" },
-      {"name": "Selenium (elemental)", "cas": "7782-49-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=153&tid=28" },
-      {"name": "Silica (Silicon Dioxide)", "cas": "7631-86-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1483&tid=290" },
-      {"name": "Silica (Crystalline - Quartz)", "cas": "14808-60-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1483&tid=290" },
-      {"name": "Silver (elemental)", "cas": "7440-22-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=539&tid=97" },
-      {"name": "Stoddard Solvent (mixture)", "cas": "8052-41-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=416&tid=73" },
-      {"name": "Strontium (elemental)", "cas": "7440-24-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=656&tid=120" },
-      {"name": "Styrene", "cas": "100-42-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=421&tid=74" },
-      {"name": "Sulfur Dioxide", "cas": "2025884", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=253&tid=46" },
-      {"name": "Sulfur Mustard", "cas": "505-60-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=905&tid=184" },
-      {"name": "Sulfur Trioxide & Sulfuric Acid", "cas": "2025949", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=256&tid=47" },
-      {"name": "Sulfur Trioxide & Sulfuric Acid", "cas": "7664-93-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=256&tid=47" },
-      {"name": "Synthetic Vitreous Fibers (Group - e.g., Glass wool)", "cas": "65997-17-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=908&tid=185" },
-      {"name": "1,1,1-Trichloroethane", "cas": "71-55-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=432&tid=76" },
-      {"name": "1,1,2,2-Tetrachloroethane", "cas": "79-34-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=801&tid=156" },
-      {"name": "1,1,2-Trichloroethane", "cas": "79-00-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=796&tid=155" },
-      {"name": "1,2,3-Trichloropropane", "cas": "96-18-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=912&tid=186" },
-      {"name": "2,4,6-Trinitrotoluene (TNT)", "cas": "118-96-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=677&tid=125" },
-      {"name": "Tetrachloroethylene (PERC)", "cas": "127-18-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=265&tid=48" },
-      {"name": "Tetryl", "cas": "479-45-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1019&tid=216" },
-      {"name": "Thallium (elemental)", "cas": "7440-28-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=309&tid=49" },
-      {"name": "Thorium (elemental)", "cas": "7440-29-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=660&tid=121" },
-      {"name": "Tin and Compounds (Tin - elemental)", "cas": "7440-31-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=543&tid=98" },
-      {"name": "Titanium Tetrachloride", "cas": "7550-45-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=664&tid=122" },
-      {"name": "Toluene", "cas": "108-88-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=161&tid=29" },
-      {"name": "Toluene Diisocyanate / Methylenediphenyl Diisocyanate (TDI mixture)", "cas": "26471-62-5", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245" },
-      {"name": "Toluene Diisocyanate / Methylenediphenyl Diisocyanate (2,4-TDI)", "cas": "584-84-9", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245" },
-      {"name": "Toluene Diisocyanate / Methylenediphenyl Diisocyanate (2,6-TDI)", "cas": "91-08-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245" },
-      {"name": "Toluene Diisocyanate / Methylenediphenyl Diisocyanate (MDI)", "cas": "101-68-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245" },
-      {"name": "Total Petroleum Hydrocarbons (TPH) (Mixture)", "cas": "N/A", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=424&tid=75" },
-      {"name": "Toxaphene (mixture)", "cas": "8001-35-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=548&tid=99" },
-      {"name": "S,S,S-Tributyl Phosphorotrithioate (Tribufos)", "cas": "78-48-8", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1487&tid=292" },
-      {"name": "Trichlorobenzenes (1,2,3-)", "cas": "87-61-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1168&tid=255" },
-      {"name": "Trichlorobenzenes (1,2,4-)", "cas": "120-82-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1168&tid=255" },
-      {"name": "Trichlorobenzenes (1,3,5-)", "cas": "108-70-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1168&tid=255" },
-      {"name": "Trichloroethylene (TCE)", "cas": "79-01-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=173&tid=30" },
-      {"name": "Tungsten (elemental)", "cas": "7440-33-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=806&tid=157" },
-      {"name": "Uranium (elemental)", "cas": "7440-61-1", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=440&tid=77" },
-      {"name": "Used Mineral-based Crankcase Oil (Mixture)", "cas": "64742-65-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=667&tid=123" },
-      {"name": "Vanadium (elemental)", "cas": "7440-62-2", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=276&tid=50" },
-      {"name": "Vinyl Acetate", "cas": "0108-05-04", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=671&tid=124" },
-      {"name": "Vinyl Chloride", "cas": "75-01-4", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=282&tid=51" },
-      {"name": "White Phosphorus (elemental)", "cas": "7723-14-0", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=285&tid=52" },
-      {"name": "Xylenes (Mixture)", "cas": "1330-20-7", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53" },
-      {"name": "Xylenes (o-Xylene)", "cas": "95-47-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53" },
-      {"name": "Xylenes (m-Xylene)", "cas": "108-38-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53" },
-      {"name": "Xylenes (p-Xylene)", "cas": "106-42-3", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53" },
-      {"name": "Zinc (elemental)", "cas": "7440-66-6", "url": "https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=302&tid=54" }
-    # --- SNIP ---
-    # Paste the full list exactly as provided in the generated file I based this on.
 ]
-_CAS_RE = re.compile(r"^\d{2,7}-\d{2}-\d$")
-def _norm(s: str) -> str:
-    return re.sub(r"\s+", " ", (s or "").strip()).lower()
-def is_cas(s: str) -> bool:
-    return bool(_CAS_RE.match((s or "").strip()))
-def _coerce_item(item: Any) -> Optional[Dict[str, str]]:
-    """
-    Defensive parsing: if your pasted list contains any malformed entries,
-    we skip them instead of crashing.
-    """
-    if not isinstance(item, dict):
-        return None
-    name = (item.get("name") or "").strip()
-    cas = (item.get("cas") or "").strip()
-    url = (item.get("url") or "").strip()
-    if not name and not cas and not url:
-        return None
-    return {"name": name or "ToxProfile", "cas": cas, "url": url}
-def search(query: str, cas: Optional[str] = None, limit: int = 8) -> Dict[str, Any]:
-    """
-    Search the local toxprofile index.
-    Behavior:
-    1) If resolved CAS exists -> try exact CAS match.
-    2) If query itself is CAS -> try exact CAS match.
-    3) If no CAS matches -> fall back to case-insensitive substring name match.
-    4) Always cap results at `limit` (default 8).
-    """
     q = (query or "").strip()
-    cas_q = (cas or "").strip()
-    items: List[Dict[str, str]] = []
-    for raw in TOXPROFILES:
-        item = _coerce_item(raw)
-        if item:
-            items.append(item)
-    matches: List[Dict[str, str]] = []
-    # CAS-first
-    cas_key = cas_q if is_cas(cas_q) else (q if is_cas(q) else "")
-    if cas_key:
-        for item in items:
-            if (item.get("cas") or "").strip() == cas_key:
-                matches.append(item)
-    # Name fallback
-    if not matches and q:
-        qn = _norm(q)
-        for item in items:
-            if qn and qn in _norm(item.get("name") or ""):
-                matches.append(item)
-    # Stable ordering: exact name match first
-    if matches and q:
-        qn = _norm(q)
-        matches.sort(key=lambda m: 0 if _norm(m.get("name", "")) == qn else 1)
-    total = len(matches)
-    return {
-        "ok": True,
-        "query": q,
-        "cas": cas_key or (cas_q if is_cas(cas_q) else ""),
-        "total": total,
-        "matches": matches[: max(0, int(limit))],
-    }

 from __future__ import annotations
 import re
+from typing import List, Dict, Any
+CDC_TOXPROFILES: List[Dict[str, str]] = [
+    {'name': 'Acetone', 'cas': '67-64-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=5&tid=1'},
+    {'name': 'Acrolein', 'cas': '107-02-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=557&tid=102'},
+    {'name': 'Acrylamide', 'cas': '79-06-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1112&tid=236'},
+    {'name': 'Acrylonitrile', 'cas': '107-13-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=447&tid=78'},
+    {'name': 'Aldrin', 'cas': '309-00-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=317&tid=56'},
+    {'name': 'Aluminum', 'cas': '7429-90-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=191&tid=34'},
+    {'name': 'Americium', 'cas': '7440-35-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=811&tid=158'},
+    {'name': 'Ammonia', 'cas': '7664-41-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=11&tid=2'},
+    {'name': 'Antimony', 'cas': '7440-36-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=332&tid=58'},
+    {'name': 'Arsenic', 'cas': '7440-38-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=22&tid=3'},
+    {'name': 'Asbestos', 'cas': '1332-21-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=30&tid=4'},
+    {'name': 'Atrazine', 'cas': '1912-24-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=338&tid=59'},
+    {'name': '1,3-Butadiene', 'cas': '106-99-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=459&tid=81'},
+    {'name': '1-Bromopropane', 'cas': 'NA', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1471&tid=285'},
+    {'name': '2,3-Benzofuran', 'cas': '271-89-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=915&tid=187'},
+    {'name': '2-Butanone', 'cas': '78-93-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=343&tid=60'},
+    {'name': '2-Butoxyethanol', 'cas': '111-76-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=347&tid=61'},
+    {'name': '2-Butoxyethanol Acetate', 'cas': '112-07-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=347&tid=61'},
+    {'name': 'Barium', 'cas': '7440-39-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=327&tid=57'},
+    {'name': 'Benzene', 'cas': '71-43-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=40&tid=14'},
+    {'name': 'Benzidine', 'cas': '92-87-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=569&tid=105'},
+    {'name': 'Beryllium', 'cas': '7440-41-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1441&tid=33'},
+    {'name': 'Bis(2-chloroethyl) Ether (BCEE)', 'cas': '111-44-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=817&tid=159'},
+    {'name': 'Bis(chloromethyl) Ether', 'cas': '542-88-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=919&tid=188'},
+    {'name': 'Boron', 'cas': '7440-42-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=453&tid=80'},
+    {'name': 'Bromodichloromethane', 'cas': '75-27-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=708&tid=127'},
+    {'name': 'Bromoform', 'cas': '75-25-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=713&tid=128'},
+    {'name': 'Dibromochloromethane', 'cas': '124-48-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=713&tid=128'},
+    {'name': 'Bromomethane', 'cas': '74-83-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=822&tid=160'},
+    {'name': 'Cadmium', 'cas': '7440-43-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=48&tid=15'},
+    {'name': 'Carbon Disulfide', 'cas': '782-182-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=474&tid=84'},
+    {'name': 'Carbon Monoxide', 'cas': '630-08-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1145&tid=253'},
+    {'name': 'Carbon Tetrachloride', 'cas': '56-23-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=196&tid=35'},
+    {'name': 'Cesium', 'cas': '7440-46-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=578&tid=107'},
+    {'name': 'Chlordane', 'cas': '12789-03-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=355&tid=62'},
+    {'name': 'Chlordecone', 'cas': '143-50-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1190&tid=276'},
+    {'name': 'Chlorfenvinphos', 'cas': '470-90-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=932&tid=193'},
+    {'name': 'Chlorinated Dibenzo-p-dioxins (CDDs)', 'cas': 'NA', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=366&tid=63'},
+    {'name': 'Chlorine', 'cas': '7782-50-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1079&tid=36'},
+    {'name': 'Chlorine Dioxide', 'cas': '10049-04-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=582&tid=108'},
+    {'name': 'Chlorite', 'cas': '7758-19-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=582&tid=108'},
+    {'name': 'Chlorobenzene', 'cas': '108-90-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=489&tid=87'},
+    {'name': 'Chlorodibenzofurans (CDFs)', 'cas': 'NA', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=938&tid=194'},
+    {'name': 'Chloroethane', 'cas': '75-00-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=827&tid=161'},
+    {'name': 'Chloroform', 'cas': '67-66-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=53&tid=16'},
+    {'name': 'Chloromethane', 'cas': '74-87-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=587&tid=109'},
+    {'name': 'Chlorophenols', 'cas': '58-90-2, 88-06-2, 95-57-8, 95-95-4, 106-48-9, 120-83-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=941&tid=195'},
+    {'name': 'Chlorpyrifos', 'cas': '2921-88-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=495&tid=88'},
+    {'name': 'Chromium', 'cas': '7440-47-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=62&tid=17'},
+    {'name': 'Cobalt', 'cas': '7440-48-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=373&tid=64'},
+    {'name': 'Copper', 'cas': '7440-50-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=206&tid=37'},
+    {'name': 'Wood Creosote', 'cas': '8021-39-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=66&tid=18'},
+    {'name': 'Coal Tar Creosote', 'cas': '8001-58-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=66&tid=18'},
+    {'name': 'Coal Tar', 'cas': '8007-45-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=66&tid=18'},
+    {'name': 'Cresols', 'cas': '1319-77-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=946&tid=196'},
+    {'name': 'Cyanide', 'cas': '74-90-8; 143-33-9; 151-50-8; 592-01-8; 544-92-3; 506-61-6; 460-19-5; 506-77-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=72&tid=19'},
+    {'name': '1,1-Dichloroethane', 'cas': '75-34-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=718&tid=129'},
+    {'name': '1,1-Dichloroethene', 'cas': '75-35-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=722&tid=130'},
+    {'name': '1,2-Dibromo-3-chloropropane', 'cas': '96-12-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=852&tid=166'},
+    {'name': '1,2-Dibromoethane', 'cas': '106-93-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=726&tid=131'},
+    {'name': '1,2-Dichloroethane', 'cas': '107-06-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=592&tid=110'},
+    {'name': '1,2-Dichloropropane', 'cas': '78-87-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=831&tid=162'},
+    {'name': '1,2-Diphenylhydrazine', 'cas': '122-66-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=952&tid=198'},
+    {'name': '1,3-Dinitrobenzene', 'cas': '99-65-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=842&tid=164'},
+    {'name': '1,3,5-Trinitrobenzene', 'cas': '99-35-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=842&tid=164'},
+    {'name': '1,4 Dioxane', 'cas': '123-91-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=955&tid=199'},
+    {'name': '2,4-Dichlorophenoxyacetic Acid (2,4-D)', 'cas': 'NA', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1481&tid=288'},
+    {'name': "3,3'-Dichlorobenzidine", 'cas': '91-94-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=959&tid=200'},
+    {'name': 'DDT', 'cas': '50-29-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=81&tid=20'},
+    {'name': 'DDE', 'cas': '72-55-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=81&tid=20'},
+    {'name': 'DDD', 'cas': '72-54-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=81&tid=20'},
+    {'name': 'DEET (N,N-diethyl-meta-toluamide)', 'cas': 'NA', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1451&tid=201'},
+    {'name': 'Di(2-Ethylhexyl)Phthalate (DEHP)', 'cas': '117-81-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=684&tid=65'},
+    {'name': 'Di-n-butyl Phthalate', 'cas': '84-74-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=859&tid=167'},
+    {'name': 'Di-n-octylphthalate (DNOP)', 'cas': '117-84-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=973&tid=204'},
+    {'name': 'Diazinon', 'cas': '333-41-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=512&tid=90'},
+    {'name': '1,2-Dichlorobenzene', 'cas': '95-50-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=704&tid=126'},
+    {'name': '1,3-Dichlorobenzene', 'cas': '541-73-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=704&tid=126'},
+    {'name': '1,4-Dichlorobenzene', 'cas': '106-46-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=704&tid=126'},
+    {'name': 'Dichloropropenes', 'cas': '26952-23-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=836&tid=163'},
+    {'name': 'Dichlorvos', 'cas': '62-73-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=597&tid=111'},
+    {'name': 'Diethyl phthalate', 'cas': '84-66-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=603&tid=112'},
+    {'name': 'Diisopropyl Methylphosphonate (DIMP)', 'cas': '1445-75-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=969&tid=203'},
+    {'name': 'Dinitrocresols (4,6-DNOC)', 'cas': '534-52-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1025&tid=218'},
+    {'name': 'Dinitrophenols (2,4-DNP)', 'cas': '51-28-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=729&tid=132'},
+    {'name': 'Dinitrotoluenes (2,4-)', 'cas': '121-14-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165'},
+    {'name': 'Dinitrotoluenes (2,6-)', 'cas': '606-20-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165'},
+    {'name': 'Dinitrotoluenes (Mixture)', 'cas': '25321-14-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165'},
+    {'name': 'Dinitrotoluenes (Other isomers)', 'cas': '', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=847&tid=165'},
+    {'name': 'Disulfoton', 'cas': '0298-04-04', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=978&tid=205'},
+    {'name': 'Dieldrin', 'cas': '60-57-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=317&tid=56'},
+    {'name': 'Endosulfan (mixture)', 'cas': '115-29-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=609&tid=113'},
+    {'name': 'Endosulfan (alpha-isomer)', 'cas': '959-98-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=609&tid=113'},
+    {'name': 'Endosulfan (beta-isomer)', 'cas': '33213-65-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=609&tid=113'},
+    {'name': 'Endrin', 'cas': '72-20-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=617&tid=114'},
+    {'name': 'Ethion', 'cas': '0563-12-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=983&tid=206'},
+    {'name': 'Ethylbenzene', 'cas': '100-41-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=383&tid=66'},
+    {'name': 'Ethylene Glycol', 'cas': '107-21-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=86&tid=21'},
+    {'name': 'Ethylene Oxide', 'cas': '75-21-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=734&tid=133'},
+    {'name': 'Fluorides, Hydrogen Fluoride, and Fluorine', 'cas': '7664-39-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=212&tid=38'},
+    {'name': 'Fluorides, Hydrogen Fluoride, and Fluorine', 'cas': '7782-41-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=212&tid=38'},
+    {'name': 'Fluorides, Hydrogen Fluoride, and Fluorine', 'cas': '7681-49-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=212&tid=38'},
+    {'name': 'Formaldehyde', 'cas': '50-00-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=220&tid=39'},
+    {'name': 'Fuel Oils / Kerosene (Kerosene/Fuel Oil #1)', 'cas': '8008-20-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91'},
+    {'name': 'Fuel Oils / Kerosene (Fuel Oil #2)', 'cas': '68476-30-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91'},
+    {'name': 'Fuel Oils / Kerosene (Fuel Oil #3)', 'cas': '70892-10-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91'},
+    {'name': 'Fuel Oils / Kerosene (Fuel Oil #4)', 'cas': '68476-34-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91'},
+    {'name': 'Fuel Oils / Kerosene (Fuel Oil #5)', 'cas': '68476-31-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=516&tid=91'},
+    {'name': 'Gasoline, Automotive (mixture)', 'cas': '8006-61-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=468&tid=83'},
+    {'name': 'Glutaraldehyde', 'cas': '111-30-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1467&tid=284'},
+    {'name': 'Glyphosate', 'cas': '1071-83-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1488&tid=293'},
+    {'name': 'Guthion (Azinphos-methyl)', 'cas': '86-50-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1037&tid=207'},
+    {'name': '2-Hexanone', 'cas': '591-78-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=738&tid=134'},
+    {'name': 'Heptachlor/Heptachlor Epoxide', 'cas': '76-44-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=746&tid=135'},
+    {'name': 'Heptachlor/Heptachlor Epoxide', 'cas': '1024-57-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=746&tid=135'},
+    {'name': 'Hexachlorobenzene', 'cas': '118-74-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=627&tid=115'},
+    {'name': 'Hexachlorobutadiene', 'cas': '87-68-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=865&tid=168'},
+    {'name': 'Hexachlorocyclohexane (HCH) (Technical Grade)', 'cas': '608-73-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138'},
+    {'name': 'Hexachlorocyclohexane (HCH) (alpha-isomer)', 'cas': '319-84-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138'},
+    {'name': 'Hexachlorocyclohexane (HCH) (beta-isomer)', 'cas': '319-85-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138'},
+    {'name': 'Hexachlorocyclohexane (HCH) (gamma-isomer/Lindane)', 'cas': '58-89-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138'},
+    {'name': 'Hexachlorocyclohexane (HCH) (delta-isomer)', 'cas': '319-86-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=754&tid=138'},
+    {'name': 'Hexachlorocyclopentadiene (HCCPD)', 'cas': '77-47-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=992&tid=208'},
+    {'name': 'Hexachloroethane', 'cas': '67-72-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=870&tid=169'},
+    {'name': 'Hexamethylene Diisocyanate (HDI)', 'cas': '822-06-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=874&tid=170'},
+    {'name': 'HMX (Octogen)', 'cas': '2691-41-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=877&tid=171'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '55957-10-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '68937-40-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '50815-84-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '55962-27-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '66594-31-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '63848-94-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '107028-44-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydraulic Fluids (Mineral oil base example)', 'cas': '28777-70-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=757&tid=141'},
+    {'name': 'Hydrazines (Hydrazine)', 'cas': '0302-01-02', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=502&tid=89'},
+    {'name': 'Hydrazines (1,1-Dimethylhydrazine)', 'cas': '57-14-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=502&tid=89'},
+    {'name': 'Hydrazines (1,2-Dimethylhydrazine)', 'cas': '540-73-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=502&tid=89'},
+    {'name': 'Hydrogen Sulfide', 'cas': '7783-06-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=389&tid=67'},
+    {'name': 'Carbonyl Sulfide', 'cas': '463-58-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=389&tid=67'},
+    {'name': 'n-Hexane', 'cas': '110-54-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=393&tid=68'},
+    {'name': 'Iodine (elemental)', 'cas': '7553-56-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=479&tid=85'},
+    {'name': 'Ionizing Radiation', 'cas': 'N/A', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=484&tid=86'},
+    {'name': 'Isophorone', 'cas': '78-59-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=763&tid=148'},
+    {'name': 'Jet Fuels JP-4 and JP-7 (Mixture)', 'cas': '50815-00-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=768&tid=149'},
+    {'name': 'JP-5, JP-8, and Jet A (Kerosene base)', 'cas': '8008-20-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=773&tid=150'},
+    {'name': 'Lead (elemental)', 'cas': '7439-92-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=96&tid=22'},
+    {'name': "4,4'-Methylenebis(2-Chloroaniline) (MBOCA)", 'cas': '101-14-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=997&tid=209'},
+    {'name': "4,4'-Methylenedianiline", 'cas': '101-77-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1001&tid=210'},
+    {'name': 'Malathion', 'cas': '121-75-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=522&tid=92'},
+    {'name': 'Manganese (elemental)', 'cas': '7439-96-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=102&tid=23'},
+    {'name': 'Mercury (elemental)', 'cas': '7439-97-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=115&tid=24'},
+    {'name': 'Methoxychlor', 'cas': '72-43-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=778&tid=151'},
+    {'name': 'Methyl Mercaptan', 'cas': '74-93-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=224&tid=40'},
+    {'name': 'Methyl Parathion', 'cas': '298-00-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=636&tid=117'},
+    {'name': 'Methyl tert-Butyl Ether (MTBE)', 'cas': '1634-04-04', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=228&tid=41'},
+    {'name': 'Methylene Chloride', 'cas': '75-09-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=234&tid=42'},
+    {'name': 'Mirex', 'cas': '2385-85-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1190&tid=276'},
+    {'name': 'Chlordecone', 'cas': '143-50-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1190&tid=276'},
+    {'name': 'Molybdenum (elemental)', 'cas': '7439-98-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1482&tid=289'},
+    {'name': 'n-Nitrosodi-n-propylamine', 'cas': '621-64-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1005&tid=211'},
+    {'name': 'N-Nitrosodimethylamine (NDMA)', 'cas': '62-75-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=884&tid=173'},
+    {'name': 'n-Nitrosodiphenylamine', 'cas': '86-30-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1009&tid=212'},
+    {'name': 'Naphthalene, 1-Methylnaphthalene, 2-Methylnaphthalene', 'cas': '91-20-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=240&tid=43'},
+    {'name': 'Naphthalene, 1-Methylnaphthalene, 2-Methylnaphthalene', 'cas': '90-12-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=240&tid=43'},
+    {'name': 'Naphthalene, 1-Methylnaphthalene, 2-Methylnaphthalene', 'cas': '91-57-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=240&tid=43'},
+    {'name': 'Nickel (elemental)', 'cas': '7440-02-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=245&tid=44'},
+    {'name': 'Nitrate and Nitrite (Nitrate ion)', 'cas': '14797-55-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1452&tid=258'},
+    {'name': 'Nitrate and Nitrite (Nitrite ion)', 'cas': '14797-65-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1452&tid=258'},
+    {'name': 'Nitrobenzene', 'cas': '98-95-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=532&tid=95'},
+    {'name': 'Nitrophenols (Group - e.g., 2-Nitrophenol)', 'cas': '88-75-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=880&tid=172'},
+    {'name': 'Nitrophenols (Group - e.g., 4-Nitrophenol)', 'cas': '0100-02-07', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=880&tid=172'},
+    {'name': 'Otto Fuel II and its Components (Mixture)', 'cas': '6423-43-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=781&tid=152'},
+    {'name': 'Parathion', 'cas': '56-38-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1425&tid=246'},
+    {'name': 'Pentachlorophenol', 'cas': '87-86-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=402&tid=70'},
+    {'name': 'Perchlorates (Group - e.g., Ammonium)', 'cas': '7790-98-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=895&tid=181'},
+    {'name': 'Perchlorates (Group - e.g., Potassium)', 'cas': '7778-74-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=895&tid=181'},
+    {'name': 'Perfluoroalkyls (Group - e.g., PFOA)', 'cas': '335-67-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1117&tid=237'},
+    {'name': 'Perfluoroalkyls (Group - e.g., PFOS)', 'cas': '1763-23-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1117&tid=237'},
+    {'name': 'Phenol', 'cas': '108-95-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=148&tid=27'},
+    {'name': 'Phosphate Ester Flame Retardants (Group - e.g., TBP)', 'cas': '126-73-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1119&tid=239'},
+    {'name': 'Phosphate Ester Flame Retardants (Group - e.g., TDCPP)', 'cas': '13674-87-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1119&tid=239'},
+    {'name': 'Phosphorus, White (elemental)', 'cas': '7723-14-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=285&tid=52'},
+    {'name': 'Plutonium (elemental)', 'cas': '2023631', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=648&tid=119'},
+    {'name': 'Polybrominated Biphenyls (PBBs) (Group - e.g., Hexa-)', 'cas': '12584439', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=529&tid=94'},
+    {'name': 'Polybrominated Diphenyl Ethers (PBDEs) (Group - e.g., Deca-)', 'cas': '1163-19-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=901&tid=183'},
+    {'name': 'Polybrominated Diphenyl Ethers (PBDEs) (Group - Penta- mixture)', 'cas': '32534-81-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=901&tid=183'},
+    {'name': 'Polybrominated Diphenyl Ethers (PBDEs) (Group - Octa- mixture)', 'cas': '32536-52-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=901&tid=183'},
+    {'name': 'Polychlorinated Biphenyls (PCBs) (Mixture)', 'cas': '1336-36-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=142&tid=26'},
+    {'name': 'Polycyclic Aromatic Hydrocarbons (PAHs) (Group - e.g., BaP)', 'cas': '50-32-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=122&tid=25'},
+    {'name': 'Polycyclic Aromatic Hydrocarbons (PAHs) (Group - e.g., Naphthalene)', 'cas': '91-20-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=122&tid=25'},
+    {'name': 'Propylene Glycol', 'cas': '57-55-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1122&tid=240'},
+    {'name': 'Pyrethrins and Pyrethroids (Pyrethrins mixture)', 'cas': '8003-34-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=787&tid=153'},
+    {'name': 'Pyrethrins and Pyrethroids (e.g., Permethrin)', 'cas': '52645-53-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=787&tid=153'},
+    {'name': 'Pyridine', 'cas': '110-86-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=535&tid=96'},
+    {'name': 'Radiation, Ionizing', 'cas': 'N/A', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=484&tid=86'},
+    {'name': 'Radium (elemental)', 'cas': '7440-14-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=791&tid=154'},
+    {'name': 'Radon (elemental)', 'cas': '10043-92-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=407&tid=71'},
+    {'name': 'RDX (Cyclonite)', 'cas': '121-82-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=412&tid=72'},
+    {'name': 'Selenium (elemental)', 'cas': '7782-49-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=153&tid=28'},
+    {'name': 'Silica (Silicon Dioxide)', 'cas': '7631-86-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1483&tid=290'},
+    {'name': 'Silica (Crystalline - Quartz)', 'cas': '14808-60-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1483&tid=290'},
+    {'name': 'Silver (elemental)', 'cas': '7440-22-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=539&tid=97'},
+    {'name': 'Stoddard Solvent (mixture)', 'cas': '8052-41-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=416&tid=73'},
+    {'name': 'Strontium (elemental)', 'cas': '7440-24-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=656&tid=120'},
+    {'name': 'Styrene', 'cas': '100-42-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=421&tid=74'},
+    {'name': 'Sulfur Dioxide', 'cas': '2025884', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=253&tid=46'},
+    {'name': 'Sulfur Mustard', 'cas': '505-60-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=905&tid=184'},
+    {'name': 'Sulfur Trioxide & Sulfuric Acid', 'cas': '2025949', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=256&tid=47'},
+    {'name': 'Sulfur Trioxide & Sulfuric Acid', 'cas': '7664-93-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=256&tid=47'},
+    {'name': 'Synthetic Vitreous Fibers (Group - e.g., Glass wool)', 'cas': '65997-17-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=908&tid=185'},
+    {'name': '1,1,1-Trichloroethane', 'cas': '71-55-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=432&tid=76'},
+    {'name': '1,1,2,2-Tetrachloroethane', 'cas': '79-34-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=801&tid=156'},
+    {'name': '1,1,2-Trichloroethane', 'cas': '79-00-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=796&tid=155'},
+    {'name': '1,2,3-Trichloropropane', 'cas': '96-18-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=912&tid=186'},
+    {'name': '2,4,6-Trinitrotoluene (TNT)', 'cas': '118-96-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=677&tid=125'},
+    {'name': 'Tetrachloroethylene (PERC)', 'cas': '127-18-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=265&tid=48'},
+    {'name': 'Tetryl', 'cas': '479-45-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1019&tid=216'},
+    {'name': 'Thallium (elemental)', 'cas': '7440-28-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=309&tid=49'},
+    {'name': 'Thorium (elemental)', 'cas': '7440-29-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=660&tid=121'},
+    {'name': 'Tin and Compounds (Tin - elemental)', 'cas': '7440-31-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=543&tid=98'},
+    {'name': 'Titanium Tetrachloride', 'cas': '7550-45-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=664&tid=122'},
+    {'name': 'Toluene', 'cas': '108-88-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=161&tid=29'},
+    {'name': 'Toluene Diisocyanate / Methylenediphenyl Diisocyanate (TDI mixture)', 'cas': '26471-62-5', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245'},
+    {'name': 'Toluene Diisocyanate / Methylenediphenyl Diisocyanate (2,4-TDI)', 'cas': '584-84-9', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245'},
+    {'name': 'Toluene Diisocyanate / Methylenediphenyl Diisocyanate (2,6-TDI)', 'cas': '91-08-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245'},
+    {'name': 'Toluene Diisocyanate / Methylenediphenyl Diisocyanate (MDI)', 'cas': '101-68-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1453&tid=245'},
+    {'name': 'Total Petroleum Hydrocarbons (TPH) (Mixture)', 'cas': 'N/A', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=424&tid=75'},
+    {'name': 'Toxaphene (mixture)', 'cas': '8001-35-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=548&tid=99'},
+    {'name': 'S,S,S-Tributyl Phosphorotrithioate (Tribufos)', 'cas': '78-48-8', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1487&tid=292'},
+    {'name': 'Trichlorobenzenes (1,2,3-)', 'cas': '87-61-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1168&tid=255'},
+    {'name': 'Trichlorobenzenes (1,2,4-)', 'cas': '120-82-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1168&tid=255'},
+    {'name': 'Trichlorobenzenes (1,3,5-)', 'cas': '108-70-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=1168&tid=255'},
+    {'name': 'Trichloroethylene (TCE)', 'cas': '79-01-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=173&tid=30'},
+    {'name': 'Tungsten (elemental)', 'cas': '7440-33-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=806&tid=157'},
+    {'name': 'Uranium (elemental)', 'cas': '7440-61-1', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=440&tid=77'},
+    {'name': 'Used Mineral-based Crankcase Oil (Mixture)', 'cas': '64742-65-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=667&tid=123'},
+    {'name': 'Vanadium (elemental)', 'cas': '7440-62-2', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=276&tid=50'},
+    {'name': 'Vinyl Acetate', 'cas': '0108-05-04', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=671&tid=124'},
+    {'name': 'Vinyl Chloride', 'cas': '75-01-4', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=282&tid=51'},
+    {'name': 'White Phosphorus (elemental)', 'cas': '7723-14-0', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=285&tid=52'},
+    {'name': 'Xylenes (Mixture)', 'cas': '1330-20-7', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53'},
+    {'name': 'Xylenes (o-Xylene)', 'cas': '95-47-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53'},
+    {'name': 'Xylenes (m-Xylene)', 'cas': '108-38-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53'},
+    {'name': 'Xylenes (p-Xylene)', 'cas': '106-42-3', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=296&tid=53'},
+    {'name': 'Zinc (elemental)', 'cas': '7440-66-6', 'url': 'https://wwwn.cdc.gov/TSP/ToxProfiles/ToxProfiles.aspx?id=302&tid=54'},
 ]
+def _is_cas(value: str) -> bool:
+    v = (value or "").strip()
+    return bool(re.match(r"^\d{2,7}-\d{2}-\d$", v))
+def lookup(query: str):
+    """Return matching CDC toxprofiles. CAS exact match, name substring otherwise."""
+    return search(query)
+def search(query: str):
     q = (query or "").strip()
+    if not q:
+        return []
+    q_low = q.lower()
+    if _is_cas(q):
+        return [it for it in CDC_TOXPROFILES if (it.get("cas") or "").strip() == q]
+    return [it for it in CDC_TOXPROFILES if q_low in (it.get("name") or "").lower()]
+def toxprofile_for(query: str):
+    """Return a single match if unique; otherwise list of matches."""
+    matches = search(query)
+    if not matches:
+        return None
+    if len(matches) == 1:
+        return matches[0]
+    return matches

core/sources/ctx.py CHANGED Viewed

@@ -1,15 +1,13 @@
-import os
 import re
 from typing import Any, Dict, List, Optional
 from urllib.parse import quote
 import httpx
-# Matches production worker default
-CTX_BASE_URL = os.getenv("CTX_BASE_URL", "https://comptox.epa.gov/ctx-api")
-CTX_API_KEY = os.getenv("CTX_API_KEY") or os.getenv("COMPTOX_API_KEY") or os.getenv("CTX_KEY")
 CAS_RE = re.compile(r"^\d{2,7}-\d{2}-\d$")
 def is_cas(s: str) -> bool:
@@ -46,10 +44,10 @@ def _as_rows(data: Any) -> List[Any]:
 async def _ctx_get(path: str, http: httpx.AsyncClient, params: Dict[str, Any] | None = None) -> Any:
-    url = CTX_BASE_URL.rstrip("/") + path
     headers = {"accept": "application/json"}
-    if CTX_API_KEY:
-        headers["x-api-key"] = CTX_API_KEY
     r = await http.get(url, params=params, headers=headers, timeout=25.0, follow_redirects=True)
     r.raise_for_status()
@@ -60,18 +58,64 @@ async def _ctx_get(path: str, http: httpx.AsyncClient, params: Dict[str, Any] |
         return {"raw": r.text}
-async def resolve_dtxsid(query: str, http: httpx.AsyncClient) -> Optional[str]:
-    q = (query or "").strip()
     if not q:
         return None
     chem_tries = [
-        ("/chemical/search", {"casrn": q}),
         ("/chemical/search", {"name": q}),
-        (f"/chemical/search/by-cas/{quote(q)}", None),
-        (f"/chemical/search/by-name/{quote(q)}", None),
     ]
     for path, params in chem_tries:
         try:
             data = await _ctx_get(path, http, params=params)
@@ -86,7 +130,6 @@ async def resolve_dtxsid(query: str, http: httpx.AsyncClient) -> Optional[str]:
         ("/hazard/genetox/summary/search", {"name": q}),
         (f"/hazard/genetox/summary/search/by-name/{quote(q)}", None),
     ]
     for path, params in haz_tries:
         try:
             data = await _ctx_get(path, http, params=params)
@@ -100,13 +143,90 @@ async def resolve_dtxsid(query: str, http: httpx.AsyncClient) -> Optional[str]:
     return None
 def dashboard_search_url(query: str) -> str:
     q = quote((query or "").strip())
-    return f"https://comptox.epa.gov/dashboard/chemical/search?query={q}"
 def dashboard_details_url(dtxsid: str) -> str:
-    return f"https://comptox.epa.gov/dashboard/chemical/details/{quote((dtxsid or '').strip())}"
 async def fetch_ctx_genetox(cas_or_query: str, http: httpx.AsyncClient) -> Dict[str, Any]:

 import re
 from typing import Any, Dict, List, Optional
 from urllib.parse import quote
 import httpx
+from core.config import settings
 CAS_RE = re.compile(r"^\d{2,7}-\d{2}-\d$")
+DTXSID_RE = re.compile(r"DTXSID\\d{7,}")
 def is_cas(s: str) -> bool:
 async def _ctx_get(path: str, http: httpx.AsyncClient, params: Dict[str, Any] | None = None) -> Any:
+    url = settings.ctx_base_url.rstrip("/") + path
     headers = {"accept": "application/json"}
+    if settings.ctx_api_key:
+        headers["x-api-key"] = settings.ctx_api_key
     r = await http.get(url, params=params, headers=headers, timeout=25.0, follow_redirects=True)
     r.raise_for_status()
         return {"raw": r.text}
+async def _resolve_from_cas(cas: str, http: httpx.AsyncClient) -> Optional[str]:
+    clean = (cas or "").strip()
+    if not clean:
+        return None
+    chem_tries = [
+        (f"/chemical/identifiers/by-cas/{quote(clean)}", None),
+        (f"/chemical/identifiers/search/by-cas/{quote(clean)}", None),
+        ("/chemical/identifiers", {"cas": clean}),
+        ("/chemical/search/equal", {"word": clean}),
+        ("/chemical/search/contains", {"word": clean}),
+        ("/chemical/search", {"matchType": "equal", "word": clean}),
+        ("/chemical/search", {"matchType": "contains", "word": clean}),
+        ("/chemical/search", {"casrn": clean}),
+    ]
+    for path, params in chem_tries:
+        try:
+            data = await _ctx_get(path, http, params=params)
+            rows = _as_rows(data)
+            dtxsid = _pick_dtxsid(rows)
+            if dtxsid:
+                return dtxsid
+        except Exception:
+            pass
+    haz_tries = [
+        ("/hazard/genetox/summary/search", {"cas": clean}),
+        (f"/hazard/genetox/summary/search/by-cas/{quote(clean)}", None),
+    ]
+    for path, params in haz_tries:
+        try:
+            data = await _ctx_get(path, http, params=params)
+            rows = _as_rows(data)
+            dtxsid = _pick_dtxsid(rows)
+            if dtxsid:
+                return dtxsid
+        except Exception:
+            pass
+    return None
+async def _resolve_from_name(name: str, http: httpx.AsyncClient) -> Optional[str]:
+    q = (name or "").strip()
     if not q:
         return None
     chem_tries = [
+        (f"/chemical/identifiers/by-name/{quote(q)}", None),
+        (f"/chemical/identifiers/search/by-name/{quote(q)}", None),
+        ("/chemical/identifiers", {"name": q}),
+        ("/chemical/search/equal", {"word": q}),
+        ("/chemical/search/contains", {"word": q}),
+        ("/chemical/search", {"matchType": "equal", "word": q}),
+        ("/chemical/search", {"matchType": "contains", "word": q}),
         ("/chemical/search", {"name": q}),
     ]
     for path, params in chem_tries:
         try:
             data = await _ctx_get(path, http, params=params)
         ("/hazard/genetox/summary/search", {"name": q}),
         (f"/hazard/genetox/summary/search/by-name/{quote(q)}", None),
     ]
     for path, params in haz_tries:
         try:
             data = await _ctx_get(path, http, params=params)
     return None
+async def _resolve_dtxsid_via_pubchem(term: str, http: httpx.AsyncClient) -> Optional[str]:
+    q = (term or "").strip()
+    if not q:
+        return None
+    try:
+        cid_url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{quote(q)}/cids/JSON"
+        r1 = await http.get(cid_url, timeout=20)
+        if r1.status_code >= 400:
+            return None
+        j1 = r1.json()
+        cid_list = (j1.get("IdentifierList") or {}).get("CID") or []
+        if not cid_list:
+            return None
+        cid = cid_list[0]
+        view_url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON"
+        r2 = await http.get(view_url, timeout=25)
+        if r2.status_code >= 400:
+            return None
+        text = r2.text
+        m = DTXSID_RE.search(text)
+        return m.group(0) if m else None
+    except Exception:
+        return None
+async def _resolve_dtxsid_via_dashboard(term: str, http: httpx.AsyncClient) -> Optional[str]:
+    q = (term or "").strip()
+    if not q:
+        return None
+    targets = [
+        f"https://comptox.epa.gov/dashboard/dsstoxdb/results?search={quote(q)}",
+        f"https://comptox.epa.gov/dashboard/dsstoxdb/chemical/details?search={quote(q)}",
+    ]
+    for url in targets:
+        try:
+            r = await http.get(
+                url,
+                timeout=20,
+                headers={
+                    "accept": "text/html,application/xhtml+xml",
+                    "user-agent": "Mozilla/5.0",
+                },
+            )
+            if r.status_code >= 400:
+                continue
+            m = DTXSID_RE.search(r.text)
+            if m:
+                return m.group(0)
+        except Exception:
+            pass
+    return None
+async def resolve_dtxsid(query: str, http: httpx.AsyncClient) -> Optional[str]:
+    q = (query or "").strip()
+    if not q:
+        return None
+    if is_cas(q):
+        dtxsid = await _resolve_from_cas(q, http)
+        if dtxsid:
+            return dtxsid
+    else:
+        dtxsid = await _resolve_from_name(q, http)
+        if dtxsid:
+            return dtxsid
+    # Fallbacks: PubChem -> Dashboard
+    via_pc = await _resolve_dtxsid_via_pubchem(q, http)
+    if via_pc:
+        return via_pc
+    return await _resolve_dtxsid_via_dashboard(q, http)
 def dashboard_search_url(query: str) -> str:
     q = quote((query or "").strip())
+    return f"https://comptox.epa.gov/dashboard/dsstoxdb/results?search={q}"
 def dashboard_details_url(dtxsid: str) -> str:
+    q = quote((dtxsid or "").strip())
+    return f"https://comptox.epa.gov/dashboard/dsstoxdb/results?search={q}"
 async def fetch_ctx_genetox(cas_or_query: str, http: httpx.AsyncClient) -> Dict[str, Any]:

core/sources/ntp.py CHANGED Viewed

@@ -7,6 +7,7 @@ import httpx
 REPORTS_URL = "https://ntp.niehs.nih.gov/publications/reports"
 BASE = "https://ntp.niehs.nih.gov"
 TR_RE = re.compile(r"\bTR-?(\d{3,4})\b", re.IGNORECASE)
 HREF_RE = re.compile(r"href=[\"']([^\"']+)[\"']", re.IGNORECASE)
@@ -120,7 +121,52 @@ async def search_technical_reports(query: str, http: httpx.AsyncClient, limit: i
             break
     if not nums:
-        return {"ok": True, "query": q, "items": []}
     items: List[Dict[str, Any]] = []
     for num in nums:

 REPORTS_URL = "https://ntp.niehs.nih.gov/publications/reports"
 BASE = "https://ntp.niehs.nih.gov"
+INDEX_URL = "https://ntp.niehs.nih.gov/data/tr"
 TR_RE = re.compile(r"\bTR-?(\d{3,4})\b", re.IGNORECASE)
 HREF_RE = re.compile(r"href=[\"']([^\"']+)[\"']", re.IGNORECASE)
             break
     if not nums:
+        # Fallback: scan the TR index page (data/tr)
+        try:
+            r2 = await http.get(INDEX_URL, timeout=25, follow_redirects=True)
+            if r2.status_code >= 400:
+                return {"ok": True, "query": q, "items": []}
+            idx_html = r2.text
+        except Exception:
+            return {"ok": True, "query": q, "items": []}
+        idx_lines = idx_html.splitlines()
+        items: List[Dict[str, Any]] = []
+        seen = set()
+        for i, line in enumerate(idx_lines):
+            if not TR_RE.search(line):
+                continue
+            block = " ".join(idx_lines[i : i + 6])
+            block_text = _strip_tags(block)
+            if q_low not in block_text.lower():
+                continue
+            m = TR_RE.search(block_text)
+            if not m:
+                continue
+            num = m.group(1)
+            if num in seen:
+                continue
+            seen.add(num)
+            # Derive a best-effort title from the block text
+            title = re.sub(TR_RE, "", block_text).strip()
+            title = re.sub(r"\\b\\d{2,7}-\\d{2}-\\d\\b", "", title).strip()
+            items.append(
+                {
+                    "num": num,
+                    "tr": f"TR-{num}",
+                    "report_page": INDEX_URL,
+                    "title": title,
+                    "year": None,
+                    "pdf": None,
+                }
+            )
+            if len(items) >= max(1, int(limit)):
+                break
+        return {"ok": True, "query": q, "items": items}
     items: List[Dict[str, Any]] = []
     for num in nums:

core/sources/pubchem.py CHANGED Viewed

@@ -1,220 +1,209 @@
-# core/sources/pubchem.py
-from __future__ import annotations
 import re
 from typing import Any, Dict, List, Optional
 from urllib.parse import quote
 import httpx
 CAS_RE = re.compile(r"^\d{2,7}-\d{2}-\d$")
-def _is_cas(s: str) -> bool:
     return bool(CAS_RE.match((s or "").strip()))
-def _safe_first(x: Any) -> Any:
-    if isinstance(x, list):
-        return x[0] if x else None
-    if isinstance(x, dict):
-        return x
-    return None
-def _fmt_info_value(value: Any) -> str:
-    """
-    Mirrors your production index.html fmtInfoValue():
-      - StringWithMarkup -> join strings
-      - primitive string/number -> stringify
-      - otherwise JSON-ish fallback
-    """
     if value is None:
-        return "Not available"
     if isinstance(value, dict):
-        swm = value.get("StringWithMarkup")
-        if isinstance(swm, list):
-            parts = []
-            for item in swm:
-                if isinstance(item, dict) and isinstance(item.get("String"), str):
-                    parts.append(item["String"])
-            if parts:
-                return " ".join(parts).strip() or "Not available"
-        if "String" in value and isinstance(value["String"], str):
-            return value["String"]
         if "Number" in value:
-            return str(value["Number"])
-    if isinstance(value, (str, int, float)):
-        return str(value)
-    try:
-        return str(value)
-    except Exception:
-        return "Not available"
-def _scan_hazards(sections: Any) -> List[Dict[str, str]]:
-    """
-    Mirrors your production scanHazards():
-      pick ONLY:
-        - "ghs hazard statements"
-        - "echa c&l notifications summary"
-    (You explicitly asked to keep only these blocks.)
     """
-    items: List[Dict[str, str]] = []
-    if not isinstance(sections, list):
-        return items
-    for sec in sections:
-        if not isinstance(sec, dict):
             continue
-        info_list = sec.get("Information")
-        if isinstance(info_list, list):
-            for info in info_list:
-                if not isinstance(info, dict):
-                    continue
-                name = info.get("Name")
-                if not isinstance(name, str) or not name.strip():
-                    continue
-                ln = name.lower()
-                if ("ghs hazard statements" in ln) or ("echa c&l notifications summary" in ln):
-                    items.append(
-                        {
-                            "name": name.strip(),
-                            "value": _fmt_info_value(info.get("Value")),
-                        }
-                    )
-        child = sec.get("Section")
-        if isinstance(child, list):
-            items.extend(_scan_hazards(child))
-    return items
-async def _cid_from_query(query: str, http: httpx.AsyncClient) -> Optional[int]:
-    q = (query or "").strip()
-    if not q:
-        return None
-    url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{quote(q)}/cids/JSON"
-    r = await http.get(url, timeout=30)
-    if r.status_code != 200:
         return None
-    js = r.json()
-    cids = js.get("IdentifierList", {}).get("CID", [])
-    first = _safe_first(cids)
-    return int(first) if isinstance(first, int) else None
 async def _props_from_cid(cid: int, http: httpx.AsyncClient) -> Dict[str, Any]:
     url = (
-        "https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/"
-        f"{cid}/property/MolecularFormula,MolecularWeight,CanonicalSMILES,IUPACName/JSON"
     )
-    r = await http.get(url, timeout=30)
     r.raise_for_status()
     js = r.json()
-    props = js.get("PropertyTable", {}).get("Properties", None)
-    first = _safe_first(props)
-    return first if isinstance(first, dict) else {}
-async def _synonyms_from_cid(cid: int, http: httpx.AsyncClient) -> List[str]:
-    url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/synonyms/JSON"
-    r = await http.get(url, timeout=30)
-    if r.status_code != 200:
-        return []
-    js = r.json()
-    info = _safe_first(js.get("InformationList", {}).get("Information", []))
-    syns = info.get("Synonym", []) if isinstance(info, dict) else []
-    return [s for s in syns if isinstance(s, str)]
-async def _pug_view_from_cid(cid: int, http: httpx.AsyncClient) -> Dict[str, Any]:
-    url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON"
-    r = await http.get(url, timeout=30)
-    if r.status_code != 200:
-        return {}
-    try:
-        return r.json()
-    except Exception:
-        return {}
 async def pubchem_by_query(query: str, http: httpx.AsyncClient) -> Dict[str, Any]:
-    """
-    Returns a dict aligned to app.py renderers:
-      ok, query, cid, resolved_cas, props, structure_png_url, compound_url,
-      ghs_paragraphs (list[str]), echa_summary (str), raw (dict)
     """
     q = (query or "").strip()
     if not q:
-        return {"ok": False, "error": "Empty query."}
     cid = await _cid_from_query(q, http)
     if not cid:
-        return {"ok": False, "error": "No PubChem CID found for query.", "query": q}
-    # properties (IUPAC, formula, MW, SMILES)
-    props: Dict[str, Any] = {}
-    props_json: Dict[str, Any] = {}
-    try:
-        props = await _props_from_cid(cid, http)
-        props_json = {"PropertyTable": {"Properties": [props]}} if props else {}
-    except Exception as e:
-        props = {}
-        props_json = {"error": str(e)}
-    # synonyms -> resolve CAS from synonym list
-    syns: List[str] = []
-    syn_json: Dict[str, Any] = {}
-    resolved_cas: Optional[str] = None
-    try:
-        syns = await _synonyms_from_cid(cid, http)
-        syn_json = {"synonyms": syns}
-        for s in syns:
-            if _is_cas(s):
-                resolved_cas = s
-                break
-    except Exception as e:
-        syn_json = {"error": str(e)}
-    # hazards via PUG-View (production-equivalent scan)
-    view_json = await _pug_view_from_cid(cid, http)
-    hazard_items = []
-    try:
-        sections = view_json.get("Record", {}).get("Section", [])
-        hazard_items = _scan_hazards(sections)
-    except Exception:
-        hazard_items = []
-    # Build display blocks exactly as strings (avoid the "char-per-line" join bug)
-    ghs_paragraphs: List[str] = []
-    echa_summary = ""
-    for it in hazard_items:
-        nm = it.get("name", "")
-        val = it.get("value", "")
-        if not nm:
             continue
-        if "ghs hazard statements" in nm.lower():
-            ghs_paragraphs.append(f"{nm}: {val}".strip())
-        if "echa c&l notifications summary" in nm.lower():
-            echa_summary = f"{nm}: {val}".strip()
-    out = {
         "ok": True,
         "query": q,
         "cid": cid,
         "resolved_cas": resolved_cas,
         "props": props,
-        "structure_png_url": f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/PNG?record_type=2d",
-        "compound_url": f"https://pubchem.ncbi.nlm.nih.gov/compound/{cid}",
-        "ghs_paragraphs": ghs_paragraphs,  # list[str]
-        "echa_summary": echa_summary,  # str
-        "raw": {
-            "props_json": props_json,
-            "synonyms_json": syn_json,
-            "pug_view_json": view_json,
-        },
     }
-    return out

+import html
 import re
 from typing import Any, Dict, List, Optional
 from urllib.parse import quote
 import httpx
+PUBCHEM_REST = "https://pubchem.ncbi.nlm.nih.gov/rest/pug"
+PUBCHEM_VIEW = "https://pubchem.ncbi.nlm.nih.gov/rest/pug_view"
 CAS_RE = re.compile(r"^\d{2,7}-\d{2}-\d$")
+def is_cas(s: str) -> bool:
     return bool(CAS_RE.match((s or "").strip()))
+def _first_cas_in_text(text: str) -> Optional[str]:
+    if not text:
+        return None
+    m = re.search(r"\b\d{2,7}-\d{2}-\d\b", text)
+    return m.group(0) if m else None
+def _fmt_value(value: Any) -> str:
+    """Port of production `fmtInfoValue()` for PubChem PUG-View values."""
     if value is None:
+        return ""
+    # PUG-View Value is usually a dict
     if isinstance(value, dict):
+        if "StringWithMarkup" in value and isinstance(value["StringWithMarkup"], list):
+            parts: List[str] = []
+            for item in value["StringWithMarkup"]:
+                if isinstance(item, dict) and item.get("String"):
+                    parts.append(str(item["String"]))
+                elif isinstance(item, str):
+                    parts.append(item)
+            return html.unescape("".join(parts)).strip()
+        if "String" in value:
+            return html.unescape(str(value["String"])).strip()
         if "Number" in value:
+            return str(value["Number"])  # already numeric
+        if "Boolean" in value:
+            return str(value["Boolean"])
+        if "Date" in value:
+            return str(value["Date"])
+    # Fallback
+    return html.unescape(str(value)).strip()
+def _scan_hazards(section: Dict[str, Any], out: List[Dict[str, str]]):
+    """Recursively scan PubChem PUG-View sections for hazard-related info.
+    Mirrors production `scanHazards()` semantics.
     """
+    info_list = section.get("Information") or []
+    for info in info_list:
+        name = (info.get("Name") or "").strip()
+        low = name.lower()
+        if (
+            "ghs hazard statements" in low
+            or "echa c&l notifications summary" in low
+            or "carcinogenicity" in low
+            or "mutagenicity" in low
+            or "genotoxicity" in low
+            or "toxic" in low
+            or "hazard" in low
+        ):
+            text = _fmt_value(info.get("Value"))
+            if text:
+                out.append({"name": name or "Hazard information", "text": text})
+    for sub in section.get("Section") or []:
+        _scan_hazards(sub, out)
+def _extract_synonyms(record: Dict[str, Any]) -> List[str]:
+    """Best-effort extraction of synonyms list from PubChem PUG-View record."""
+    if not record:
+        return []
+    def walk(sec: Dict[str, Any], acc: List[str]):
+        # Synonyms often appear under Names and Identifiers
+        if (sec.get("TOCHeading") or "").lower() == "synonyms":
+            for info in sec.get("Information") or []:
+                val = info.get("Value")
+                if isinstance(val, dict) and isinstance(val.get("StringWithMarkup"), list):
+                    for item in val["StringWithMarkup"]:
+                        if isinstance(item, dict) and item.get("String"):
+                            acc.append(str(item["String"]))
+        for sub in sec.get("Section") or []:
+            walk(sub, acc)
+    out: List[str] = []
+    for top in record.get("Section") or []:
+        walk(top, out)
+    # De-dupe preserve order
+    seen = set()
+    uniq: List[str] = []
+    for s in out:
+        s = s.strip()
+        if not s:
+            continue
+        if s.lower() in seen:
             continue
+        seen.add(s.lower())
+        uniq.append(s)
+    return uniq
+def _structure_png_url(cid: int) -> str:
+    return f"{PUBCHEM_REST}/compound/cid/{cid}/PNG?record_type=2d"
+def _compound_url(cid: int) -> str:
+    return f"https://pubchem.ncbi.nlm.nih.gov/compound/{cid}"
+def _safe_first(items: Any) -> Optional[Any]:
+    if isinstance(items, list) and items:
+        return items[0]
+    return None
+async def _cid_from_query(q: str, http: httpx.AsyncClient) -> Optional[int]:
+    url = f"{PUBCHEM_REST}/compound/name/{quote(q)}/cids/JSON"
+    try:
+        r = await http.get(url, timeout=20)
+        r.raise_for_status()
+        js = r.json()
+        cid = _safe_first(js.get("IdentifierList", {}).get("CID"))
+        return int(cid) if cid is not None else None
+    except Exception:
         return None
 async def _props_from_cid(cid: int, http: httpx.AsyncClient) -> Dict[str, Any]:
+    # Request all props production needs.
     url = (
+        f"{PUBCHEM_REST}/compound/cid/{cid}/property/"
+        "MolecularFormula,MolecularWeight,CanonicalSMILES,IUPACName/JSON"
     )
+    r = await http.get(url, timeout=20)
     r.raise_for_status()
     js = r.json()
+    props = _safe_first(js.get("PropertyTable", {}).get("Properties"))
+    return props or {}
+async def _view_record(cid: int, http: httpx.AsyncClient) -> Dict[str, Any]:
+    url = f"{PUBCHEM_VIEW}/data/compound/{cid}/JSON"
+    r = await http.get(url, timeout=25)
+    r.raise_for_status()
+    return r.json()
 async def pubchem_by_query(query: str, http: httpx.AsyncClient) -> Dict[str, Any]:
+    """Query PubChem by CAS or name.
+    Returns a dict compatible with app.py renderers.
     """
     q = (query or "").strip()
     if not q:
+        return {"ok": False, "error": "Empty query"}
     cid = await _cid_from_query(q, http)
     if not cid:
+        return {"ok": False, "error": "No PubChem CID found"}
+    props = await _props_from_cid(cid, http)
+    record_json = await _view_record(cid, http)
+    record = record_json.get("Record") or {}
+    synonyms = _extract_synonyms(record)
+    resolved_cas = None
+    if is_cas(q):
+        resolved_cas = q
+    else:
+        resolved_cas = _first_cas_in_text("\n".join(synonyms))
+    hazards: List[Dict[str, str]] = []
+    for top in record.get("Section") or []:
+        _scan_hazards(top, hazards)
+    # De-dupe hazards by (name, text)
+    seen = set()
+    uniq_haz: List[Dict[str, str]] = []
+    for h in hazards:
+        key = (h.get("name", "").lower(), h.get("text", "").strip())
+        if key in seen:
             continue
+        seen.add(key)
+        uniq_haz.append(h)
+    return {
         "ok": True,
         "query": q,
         "cid": cid,
         "resolved_cas": resolved_cas,
         "props": props,
+        "structure_png": _structure_png_url(cid),
+        "url": _compound_url(cid),
+        "synonyms": synonyms[:50],
+        "hazards": uniq_haz,
     }

core/sources/scholar.py CHANGED Viewed

@@ -1,7 +1,11 @@
-import httpx
-from urllib.parse import quote
 def scholar_link(query: str) -> str:
-    return "https://scholar.google.com/scholar?q=" + quote(
-        f"{query} genotoxicity mutagenicity carcinogenicity", safe=""
-    )

+from __future__ import annotations
+from urllib.parse import quote_plus
 def scholar_link(query: str) -> str:
+    q = (query or "").strip()
+    if not q:
+        return ""
+    # Mirror JS behavior: add a genotoxicity hint.
+    return f"https://scholar.google.com/scholar?q={quote_plus(q + ' genotoxicity')}"