cd scientific-databases/clinicaltrials-database/scripts
python3 query_clinicaltrials.py

import requests

url = "https://clinicaltrials.gov/api/v2/studies"
params = {
    "query.cond": "breast cancer",
    "filter.overallStatus": "RECRUITING",
    "pageSize": 10
}

response = requests.get(url, params=params)
data = response.json()

print(f"Found {data['totalCount']} trials")

import requests

nct_id = "NCT04852770"
url = f"https://clinicaltrials.gov/api/v2/studies/{nct_id}"

response = requests.get(url)
study = response.json()

undefined

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    condition="type 2 diabetes",
    status="RECRUITING",
    page_size=20,
    sort="LastUpdatePostDate:desc"
)

print(f"Found {results['totalCount']} recruiting diabetes trials")
for study in results['studies']:
    protocol = study['protocolSection']
    nct_id = protocol['identificationModule']['nctId']
    title = protocol['identificationModule']['briefTitle']
    print(f"{nct_id}: {title}")

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    intervention="Pembrolizumab",
    status=["RECRUITING", "ACTIVE_NOT_RECRUITING"],
    page_size=50
)

**Common use cases:**
- Drug development tracking
- Competitive intelligence for pharmaceutical companies
- Treatment option research for clinicians

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    condition="cancer",
    location="New York",
    status="RECRUITING",
    page_size=100
)

**Common use cases:**
- Patient referrals to local trials
- Geographic trial distribution analysis
- Site selection for new trials

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    sponsor="National Cancer Institute",
    page_size=100
)

**Common use cases:**
- Tracking institutional research portfolios
- Analyzing funding organization priorities
- Identifying collaboration opportunities

from scripts.query_clinicaltrials import search_studies

results = search_studies(
    condition="alzheimer disease",
    status="COMPLETED",
    sort="LastUpdatePostDate:desc",
    page_size=50
)

undefined

from scripts.query_clinicaltrials import get_study_details

study = get_study_details("NCT04852770")
eligibility = study['protocolSection']['eligibilityModule']

print(f"Eligible Ages: {eligibility.get('minimumAge')} - {eligibility.get('maximumAge')}")
print(f"Eligible Sex: {eligibility.get('sex')}")
print(f"\nInclusion Criteria:")
print(eligibility.get('eligibilityCriteria'))

from scripts.query_clinicaltrials import get_study_details

study = get_study_details("NCT04852770")
contacts_module = study['protocolSection']['contactsLocationsModule']

undefined

from scripts.query_clinicaltrials import search_with_all_results

**Example: Manual pagination with control**

```python
from scripts.query_clinicaltrials import search_studies

all_studies = []
page_token = None
max_pages = 10  # Limit to avoid excessive requests

for page in range(max_pages):
    results = search_studies(
        condition="cancer",
        page_size=1000,  # Max page size
        page_token=page_token
    )

    all_studies.extend(results['studies'])

    # Check for next page
    page_token = results.get('pageToken')
    if not page_token:
        break

print(f"Retrieved {len(all_studies)} studies across {page + 1} pages")

from scripts.query_clinicaltrials import search_studies

**Note:** CSV format returns a string instead of JSON dictionary.

from scripts.query_clinicaltrials import get_study_details, extract_study_summary

undefined

from scripts.query_clinicaltrials import search_studies

undefined

python3 scripts/query_clinicaltrials.py

import time
import requests

def search_with_rate_limit(params):
    try:
        response = requests.get("https://clinicaltrials.gov/api/v2/studies", params=params)
        response.raise_for_status()
        return response.json()
    except requests.exceptions.HTTPError as e:
        if e.response.status_code == 429:
            print("Rate limited. Waiting 60 seconds...")
            time.sleep(60)
            return search_with_rate_limit(params)  # Retry
        raise

import requests

try:
    response = requests.get(url, params=params, timeout=30)
    response.raise_for_status()
    data = response.json()
except requests.exceptions.HTTPError as e:
    print(f"HTTP error: {e.response.status_code}")
except requests.exceptions.RequestException as e:
    print(f"Request failed: {e}")
except ValueError as e:
    print(f"JSON decode error: {e}")

undefined

undefined