Dailymed Database

pip install requests pandas matplotlib

import requests

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

# Search drug labels by name
r = requests.get(f"{BASE}/spls.json", params={"drug_name": "metformin", "pagesize": 5})
r.raise_for_status()
data = r.json()
print(f"Total labels found: {data['metadata']['total_elements']}")
for spl in data["data"][:3]:
    print(f"  {spl['title']!r:60s}  setid={spl['setid']}")

import requests
import pandas as pd

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def search_spls(drug_name, pagesize=20, page=1):
    """Search DailyMed SPLs by drug name. Returns list of label summaries."""
    r = requests.get(f"{BASE}/spls.json",
                     params={"drug_name": drug_name, "pagesize": pagesize, "page": page},
                     timeout=15)
    r.raise_for_status()
    return r.json()

result = search_spls("atorvastatin", pagesize=10)
meta = result["metadata"]
print(f"Search: 'atorvastatin' → {meta['total_elements']} labels across {meta['total_pages']} pages")

df = pd.DataFrame(result["data"])
print(df[["setid", "title", "published_date"]].to_string(index=False))
# setid                                  title                                   published_date
# 8f6c7c7c-...  ATORVASTATIN CALCIUM tablet                               2024-03-15
# a4b7d3e1-...  ATORVASTATIN CALCIUM tablet, film coated                  2023-11-20

import requests

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def get_spl(setid):
    """Retrieve full SPL document by set ID. Returns label metadata and XML/JSON."""
    r = requests.get(f"{BASE}/spls/{setid}.json", timeout=20)
    r.raise_for_status()
    return r.json()

# Use a known set ID from search results
setid = "8f6c7c7c-1f7f-4f1a-af86-8b2eef2a8b2c"   # example atorvastatin label
label = get_spl(setid)
data = label["data"]

print(f"Title: {data.get('title')}")
print(f"Set ID: {data.get('setid')}")
print(f"Published: {data.get('published_date')}")
print(f"Version: {data.get('version')}")

# Access structured sections
if "sections" in data:
    sections = data["sections"]
    print(f"\nLabel sections ({len(sections)} total):")
    for sec in sections[:5]:
        print(f"  [{sec.get('loinc_code', 'N/A')}] {sec.get('title', 'Untitled')}")

import requests

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def search_by_ndc(ndc_code):
    """Find SPL by NDC code (formatted as XXXXX-XXXX-XX or without dashes)."""
    r = requests.get(f"{BASE}/spls.json",
                     params={"ndc": ndc_code},
                     timeout=15)
    r.raise_for_status()
    return r.json()

# NDC for Lipitor 10mg (atorvastatin)
result = search_by_ndc("0071-0155-23")
if result["data"]:
    spl = result["data"][0]
    print(f"Drug: {spl['title']}")
    print(f"Set ID: {spl['setid']}")
    print(f"Published: {spl['published_date']}")
else:
    print("No label found for this NDC")

import requests
import pandas as pd

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def get_packaging(setid):
    """Retrieve packaging information for a label (NDC codes, dosage forms, quantities)."""
    r = requests.get(f"{BASE}/spls/{setid}/packaging.json", timeout=15)
    r.raise_for_status()
    return r.json()

setid = "8f6c7c7c-1f7f-4f1a-af86-8b2eef2a8b2c"   # example setid
pkg = get_packaging(setid)

if pkg["data"]:
    packages = pkg["data"]
    print(f"Packaging variants: {len(packages)}")
    df = pd.DataFrame(packages)
    # Common fields: ndc, dosage_form, route, marketing_status
    for col in ["ndc", "dosage_form", "route", "marketing_status"]:
        if col in df.columns:
            print(f"\n{col.upper()}:")
            print(df[col].value_counts().head(5))

import requests
import time

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def get_spls_by_rxcui(rxcui):
    """Get all SPLs associated with an RxCUI. Returns list of set IDs and titles."""
    r = requests.get(f"{BASE}/rxcuis/{rxcui}/spls.json", timeout=15)
    r.raise_for_status()
    return r.json()

# RxCUI for atorvastatin: 83367
rxcui = "83367"
result = get_spls_by_rxcui(rxcui)
print(f"SPLs for RxCUI {rxcui} (atorvastatin):")
for spl in result["data"][:5]:
    print(f"  {spl['setid']} | {spl['title'][:70]}")
print(f"  Total: {result['metadata']['total_elements']} labels")

import requests

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def search_drug_names(query, pagesize=20):
    """Search the DailyMed drug name index for name normalization."""
    r = requests.get(f"{BASE}/drugnames.json",
                     params={"drug_name": query, "pagesize": pagesize},
                     timeout=15)
    r.raise_for_status()
    return r.json()

result = search_drug_names("metformin")
print(f"Drug name matches for 'metformin': {result['metadata']['total_elements']}")
for entry in result["data"][:8]:
    print(f"  {entry['drug_name']}")
# METFORMIN HYDROCHLORIDE
# METFORMIN HYDROCHLORIDE AND SITAGLIPTIN PHOSPHATE
# METFORMIN HYDROCHLORIDE AND SAXAGLIPTIN

import requests
import time
import pandas as pd

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

# LOINC codes for common SPL sections
SECTION_LOINC = {
    "34067-9": "Indications and Usage",
    "34068-7": "Dosage and Administration",
    "34071-1": "Warnings",
    "34084-4": "Adverse Reactions",
    "34070-3": "Contraindications",
    "43685-7": "Warnings and Precautions",
}

def get_label_sections(setid):
    """Extract structured sections from an SPL by set ID."""
    r = requests.get(f"{BASE}/spls/{setid}.json", timeout=20)
    r.raise_for_status()
    data = r.json()["data"]
    sections = {}
    for sec in data.get("sections", []):
        loinc = sec.get("loinc_code")
        if loinc in SECTION_LOINC:
            sections[SECTION_LOINC[loinc]] = sec.get("text", "")
    return sections

# Get indications for two statin labels
statins = [
    ("Atorvastatin", "8f6c7c7c-1f7f-4f1a-af86-8b2eef2a8b2c"),
    ("Rosuvastatin", "a3b2c4d5-1234-5678-abcd-ef0123456789"),   # example
]
records = []
for drug_name, setid in statins:
    try:
        sections = get_label_sections(setid)
        records.append({"drug": drug_name, "indications_length": len(sections.get("Indications and Usage", ""))})
    except Exception as e:
        print(f"Warning: {drug_name} failed — {e}")
    time.sleep(0.3)

df = pd.DataFrame(records)
print(df.to_string(index=False))

import requests
import time
import pandas as pd

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def search_spls(drug_name, pagesize=50):
    r = requests.get(f"{BASE}/spls.json",
                     params={"drug_name": drug_name, "pagesize": pagesize},
                     timeout=15)
    r.raise_for_status()
    return r.json()

def get_packaging(setid):
    r = requests.get(f"{BASE}/spls/{setid}/packaging.json", timeout=15)
    r.raise_for_status()
    return r.json()

# Search for all metformin labels
result = search_spls("metformin", pagesize=20)
labels = result["data"]
print(f"Found {len(labels)} metformin labels")

rows = []
for label in labels[:10]:   # limit for demo
    setid = label["setid"]
    try:
        pkg = get_packaging(setid)
        for item in pkg["data"][:2]:
            rows.append({
                "title": label["title"][:60],
                "setid": setid,
                "ndc": item.get("ndc"),
                "dosage_form": item.get("dosage_form"),
                "route": item.get("route"),
                "marketing_status": item.get("marketing_status"),
                "published_date": label.get("published_date"),
            })
    except Exception as e:
        print(f"Skipping {setid}: {e}")
    time.sleep(0.3)

df = pd.DataFrame(rows)
print(f"\nFormulations with packaging data: {len(df)}")
print(df[["title", "dosage_form", "route", "marketing_status"]].drop_duplicates().to_string(index=False))
df.to_csv("metformin_formulations.csv", index=False)
print("\nSaved: metformin_formulations.csv")

import requests
import time
import pandas as pd

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

TARGET_SECTIONS = {
    "34071-1": "Warnings",
    "43685-7": "Warnings_and_Precautions",
    "34084-4": "Adverse_Reactions",
    "34070-3": "Contraindications",
}

def search_and_get_sections(drug_name, max_labels=5):
    """Search for labels and extract safety-relevant sections."""
    search_r = requests.get(f"{BASE}/spls.json",
                            params={"drug_name": drug_name, "pagesize": max_labels},
                            timeout=15)
    search_r.raise_for_status()
    labels = search_r.json()["data"][:max_labels]

    records = []
    for label in labels:
        setid = label["setid"]
        try:
            label_r = requests.get(f"{BASE}/spls/{setid}.json", timeout=20)
            label_r.raise_for_status()
            spl_data = label_r.json()["data"]

            row = {"drug_name": drug_name, "title": label["title"][:80], "setid": setid}
            for loinc, col in TARGET_SECTIONS.items():
                text = ""
                for sec in spl_data.get("sections", []):
                    if sec.get("loinc_code") == loinc:
                        text = sec.get("text", "")[:500]   # first 500 chars
                        break
                row[col] = text
            records.append(row)
        except Exception as e:
            print(f"  Skipping {setid}: {e}")
        time.sleep(0.3)

    return pd.DataFrame(records)

# Compare safety sections across ACE inhibitor labels
drugs = ["lisinopril", "enalapril"]
all_records = []
for drug in drugs:
    print(f"Processing: {drug}")
    df = search_and_get_sections(drug, max_labels=3)
    all_records.append(df)

combined = pd.concat(all_records, ignore_index=True)
print(f"\nExtracted safety sections: {len(combined)} labels")
print(combined[["drug_name", "title"]].to_string(index=False))
combined.to_csv("ace_inhibitor_safety_sections.csv", index=False)
print("Saved: ace_inhibitor_safety_sections.csv")

import requests
import time
import pandas as pd
import matplotlib.pyplot as plt

BASE = "https://dailymed.nlm.nih.gov/dailymed/services/v2"

def count_labels(drug_name):
    """Return total SPL count for a drug name."""
    r = requests.get(f"{BASE}/spls.json",
                     params={"drug_name": drug_name, "pagesize": 1},
                     timeout=15)
    r.raise_for_status()
    return r.json()["metadata"]["total_elements"]

# Count labels for common statins
statins = {
    "atorvastatin": "Atorvastatin",
    "rosuvastatin": "Rosuvastatin",
    "simvastatin": "Simvastatin",
    "pravastatin": "Pravastatin",
    "lovastatin": "Lovastatin",
    "fluvastatin": "Fluvastatin",
    "pitavastatin": "Pitavastatin",
}

counts = {}
for query, label in statins.items():
    try:
        counts[label] = count_labels(query)
        print(f"  {label}: {counts[label]} labels")
    except Exception as e:
        print(f"  {label}: error — {e}")
    time.sleep(0.3)

# Visualization
df = pd.DataFrame(list(counts.items()), columns=["Drug", "Label_Count"])
df = df.sort_values("Label_Count", ascending=True)

fig, ax = plt.subplots(figsize=(9, 5))
bars = ax.barh(df["Drug"], df["Label_Count"], color="#2196F3", edgecolor="white")
ax.bar_label(bars, fmt="%d", padding=4, fontsize=9)
ax.set_xlabel("Number of DailyMed SPL Entries")
ax.set_title("DailyMed: FDA Drug Label Count by Statin\n(includes brand + generic formulations)")
ax.set_xlim(0, df["Label_Count"].max() * 1.15)
plt.tight_layout()
plt.savefig("statin_label_counts.png", dpi=150, bbox_inches="tight")
print(f"Saved: statin_label_counts.png  (total labels: {df['Label_Count'].sum()})")