import pubchempy as pcp
compounds = pcp.get_compounds('aspirin', 'name')
compound = compounds[0]

compound = pcp.Compound.from_cid(2244)  # Aspirin

compound = pcp.get_compounds('CC(=O)OC1=CC=CC=C1C(=O)O', 'smiles')[0]

compound = pcp.get_compounds('InChI=1S/C9H8O4/...', 'inchi')[0]

compounds = pcp.get_compounds('C9H8O4', 'formula')

undefined

import pubchempy as pcp

**Get Specific Properties**:
```python

**Batch Property Retrieval**:
```python
import pandas as pd

compound_names = ['aspirin', 'ibuprofen', 'paracetamol']
all_properties = []

for name in compound_names:
    props = pcp.get_properties(
        ['MolecularFormula', 'MolecularWeight', 'XLogP'],
        name,
        'name'
    )
    all_properties.extend(props)

df = pd.DataFrame(all_properties)

import pubchempy as pcp

**Note**: Similarity searches are asynchronous for large queries and may take 15-30 seconds to complete. PubChemPy handles the asynchronous pattern automatically.

import pubchempy as pcp

**Common Substructures**:
- Benzene ring: `c1ccccc1`
- Pyridine: `c1ccncc1`
- Phenol: `c1ccc(O)cc1`
- Carboxylic acid: `C(=O)O`

import pubchempy as pcp

compound = pcp.get_compounds('aspirin', 'name')[0]

undefined

import pubchempy as pcp

undefined

import pubchempy as pcp

synonyms_data = pcp.get_synonyms('aspirin', 'name')

if synonyms_data:
    cid = synonyms_data[0]['CID']
    synonyms = synonyms_data[0]['Synonym']

    print(f"CID {cid} has {len(synonyms)} synonyms:")
    for syn in synonyms[:10]:  # First 10
        print(f"  - {syn}")

import requests
import json

**For more complex bioactivity queries**, use the `scripts/bioactivity_query.py` helper script which provides:
- Bioassay summaries with activity outcome filtering
- Assay target identification
- Search for compounds by biological target
- Active compound lists for specific assays

import requests

cid = 2244
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug_view/data/compound/{cid}/JSON"

response = requests.get(url)
if response.status_code == 200:
    annotations = response.json()
    # Contains extensive data including:
    # - Chemical and Physical Properties
    # - Drug and Medication Information
    # - Pharmacology and Biochemistry
    # - Safety and Hazards
    # - Toxicity
    # - Literature references
    # - Patents

undefined

undefined

uv pip install pubchempy

uv pip install requests

uv pip install pandas

from scripts.compound_search import search_by_name, get_compound_properties

undefined

from scripts.bioactivity_query import get_bioassay_summary, summarize_bioactivities

undefined

from pubchempy import BadRequestError, NotFoundError, TimeoutError

try:
    compound = pcp.get_compounds('query', 'name')[0]
except NotFoundError:
    print("Compound not found")
except BadRequestError:
    print("Invalid request format")
except TimeoutError:
    print("Request timed out - try reducing scope")
except IndexError:
    print("No results returned")

import pubchempy as pcp

undefined

import pubchempy as pcp

def check_drug_likeness(compound_name):
    compound = pcp.get_compounds(compound_name, 'name')[0]

    # Lipinski's Rule of Five
    rules = {
        'MW <= 500': compound.molecular_weight <= 500,
        'LogP <= 5': compound.xlogp <= 5 if compound.xlogp else None,
        'HBD <= 5': compound.h_bond_donor_count <= 5,
        'HBA <= 10': compound.h_bond_acceptor_count <= 10
    }

    violations = sum(1 for v in rules.values() if v is False)
    return rules, violations

rules, violations = check_drug_likeness('aspirin')
print(f"Lipinski violations: {violations}")

import pubchempy as pcp

undefined

import pubchempy as pcp
import pandas as pd

compound_list = ['aspirin', 'ibuprofen', 'naproxen', 'celecoxib']

properties_list = []
for name in compound_list:
    try:
        compound = pcp.get_compounds(name, 'name')[0]
        properties_list.append({
            'Name': name,
            'CID': compound.cid,
            'Formula': compound.molecular_formula,
            'MW': compound.molecular_weight,
            'LogP': compound.xlogp,
            'TPSA': compound.tpsa,
            'HBD': compound.h_bond_donor_count,
            'HBA': compound.h_bond_acceptor_count
        })
    except Exception as e:
        print(f"Error processing {name}: {e}")

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

import pubchempy as pcp

undefined