uspto-database

uspto-database

Overview

The USPTO provides two primary programmatic access points for patent data: the PatentsView API (REST, free, no key required for basic use) for structured queries by inventor, assignee, CPC classification, and keywords; and Google Patents Public Data (BigQuery public dataset) for large-scale analytics across the full patent corpus. Both expose data under the CC0 Public Domain Dedication. This skill covers Python-based access patterns for both, plus basic patent portfolio analytics.

When to Use

• Prior art search: Finding existing patents relevant to a technology before filing or to assess freedom-to-operate.
• Competitor IP landscape analysis: Querying all patents from a specific assignee (company or institution) to map their technology portfolio.
• CPC classification search: Finding patents in a specific technology area using Cooperative Patent Classification codes (e.g., C12N for nucleotides/genetic engineering).
• Inventor network analysis: Identifying prolific inventors in a field and their institutional affiliations.
• Technology trend tracking: Counting patent filings by year and technology category to identify emerging areas.
• Life sciences IP analysis: Searching biotech-specific classifications (A61K for pharmaceuticals, C12N for genetics, G16B for bioinformatics).
• For full-text patent PDF downloads, use the USPTO Bulk Data Storage System (BDSS) or Google Patents direct links.
• Rate limits: PatentsView API allows 45 requests/minute without an API key; request a free key for 45 req/min with higher daily limits.

Prerequisites

• Python packages: requests, pandas, matplotlib
• Optional: google-cloud-bigquery for Google Patents Public Data queries
• Data requirements: No account needed for PatentsView basic queries; Google Cloud account required for BigQuery
• Rate limits: PatentsView — 45 requests/minute (unauthenticated), higher with free API key

pip install requests pandas matplotlib
pip install google-cloud-bigquery  # optional: for BigQuery access

Quick Start

import requests
import pandas as pd

# Search PatentsView API: patents assigned to "Genentech" in CPC class C12N
url = "https://api.patentsview.org/patents/query"
payload = {
    "q": {"_and": [
        {"_contains": {"assignee_organization": "Genentech"}},
        {"_contains": {"cpc_subgroup_id": "C12N"}},
    ]},
    "f": ["patent_number", "patent_title", "patent_date", "assignee_organization"],
    "o": {"per_page": 25},
}
resp = requests.post(url, json=payload)
data = resp.json()
df   = pd.DataFrame(data["patents"])
print(f"Found: {data['total_patent_count']} patents")
print(df[["patent_number", "patent_title", "patent_date"]].head())

Core API

Query Type 1: Search by Assignee (Company / Institution)

Find all patents granted to a specific organization.

import requests
import pandas as pd

def search_by_assignee(assignee_name: str, per_page: int = 100) -> pd.DataFrame:
    url     = "https://api.patentsview.org/patents/query"
    payload = {
        "q": {"_contains": {"assignee_organization": assignee_name}},
        "f": [
            "patent_number", "patent_title", "patent_date",
            "patent_abstract", "assignee_organization", "assignee_country",
        ],
        "o": {"per_page": per_page, "sort": [{"patent_date": "desc"}]},
    }
    resp = requests.post(url, json=payload)
    resp.raise_for_status()
    data = resp.json()
    df   = pd.DataFrame(data.get("patents", []))
    print(f"Assignee '{assignee_name}': {data.get('total_patent_count', 0)} total patents")
    return df

# Example: patents from Broad Institute
df_broad = search_by_assignee("Broad Institute")
print(df_broad[["patent_number", "patent_title", "patent_date"]].head(10))

# Paginate through all results for large portfolios
def search_assignee_all_pages(assignee_name: str, page_size: int = 100) -> pd.DataFrame:
    url  = "https://api.patentsview.org/patents/query"
    all_patents = []
    page = 1
    while True:
        payload = {
            "q": {"_contains": {"assignee_organization": assignee_name}},
            "f": ["patent_number", "patent_title", "patent_date", "cpc_subgroup_id"],
            "o": {"per_page": page_size, "page": page},
        }
        resp = requests.post(url, json=payload)
        data = resp.json()
        patents = data.get("patents", [])
        if not patents:
            break
        all_patents.extend(patents)
        total = data.get("total_patent_count", 0)
        if len(all_patents) >= total:
            break
        page += 1

    df = pd.DataFrame(all_patents)
    print(f"Retrieved {len(df)} patents for '{assignee_name}'")
    return df

Query Type 2: Search by CPC Classification

CPC (Cooperative Patent Classification) codes organize patents by technology. Life sciences codes include C12N (nucleotides/genetics), A61K (pharmaceuticals), and G16B (bioinformatics).

import requests
import pandas as pd

# Search by CPC subgroup: C12N15 (mutation/genetic engineering)
url = "https://api.patentsview.org/patents/query"
payload = {
    "q": {"_begins": {"cpc_subgroup_id": "C12N15"}},
    "f": [
        "patent_number", "patent_title", "patent_date",
        "assignee_organization", "cpc_subgroup_id",
    ],
    "o": {"per_page": 50, "sort": [{"patent_date": "desc"}]},
}
resp = requests.post(url, json=payload)
data = resp.json()
df   = pd.DataFrame(data["patents"])
print(f"C12N15 patents: {data['total_patent_count']}")
print(df[["patent_number", "patent_title", "assignee_organization"]].head(10))

# Common life sciences CPC codes
CPC_LIFE_SCIENCES = {
    "C12N":    "Microorganisms / enzymes / compositions",
    "C12N15":  "Mutation / genetic engineering",
    "C12Q":    "Measuring / testing involving enzymes or microorganisms",
    "A61K":    "Preparations for medical use",
    "A61P":    "Therapeutic activity of chemical compounds",
    "G16B":    "Bioinformatics",
    "G16H":    "Healthcare informatics",
    "C07K":    "Peptides / proteins",
}
for code, desc in CPC_LIFE_SCIENCES.items():
    print(f"  {code:10s}: {desc}")

Query Type 3: Full-Text Keyword Search

Search patent titles and abstracts for specific terms.

import requests
import pandas as pd

def keyword_search(keyword: str, per_page: int = 50) -> pd.DataFrame:
    url = "https://api.patentsview.org/patents/query"
    payload = {
        "q": {"_or": [
            {"_text_any": {"patent_title":    keyword}},
            {"_text_any": {"patent_abstract": keyword}},
        ]},
        "f": [
            "patent_number", "patent_title", "patent_date",
            "patent_abstract", "assignee_organization",
        ],
        "o": {"per_page": per_page, "sort": [{"patent_date": "desc"}]},
    }
    resp = requests.post(url, json=payload)
    resp.raise_for_status()
    data = resp.json()
    df   = pd.DataFrame(data.get("patents", []))
    print(f"Keyword '{keyword}': {data.get('total_patent_count', 0)} patents found")
    return df

# Search for CRISPR-related patents
df_crispr = keyword_search("CRISPR")
print(df_crispr[["patent_number", "patent_title", "patent_date"]].head(10))

Query Type 4: Inventor Search

Find patents by inventor name or retrieve an inventor's full publication history.

import requests
import pandas as pd

# Search by inventor name
url = "https://api.patentsview.org/inventors/query"
payload = {
    "q": {"_and": [
        {"inventor_last_name":  "Doudna"},
        {"inventor_first_name": "Jennifer"},
    ]},
    "f": ["inventor_id", "inventor_first_name", "inventor_last_name",
          "inventor_city", "inventor_state", "inventor_country"],
    "o": {"per_page": 10},
}
resp = requests.post(url, json=payload)
data = resp.json()
print(f"Found {data.get('total_inventor_count', 0)} inventors matching 'Jennifer Doudna'")
for inv in data.get("inventors",