getOCLCnumber_printbooks

#This Python script retrieves matching OCLC records based on defined parameters and is specifically designed for print books. 
#It is used for Alma brief level 04 records that lack an OCLC number and works with Excel files exported from Alma, using the WorldCat Search API v.2.

import os
import requests
import pandas as pd

# 👇 Set working directory
os.chdir(r"C:/[YOUR FILE DIRECTORY]")

# Input / output files .xlsx format 
input_file = "[input file name]"
output_file = "[output file name]"

# Load Excel
df = pd.read_excel(input_file)

# Prepare results list
results = []

# Your OCLC Access Token
OCLC_TOKEN = "[YOUR OCLC TOKEN]"

# Iterate over each row in the Excel
for _, row in df.iterrows():
    title = str(row["ti:"]).strip() if not pd.isna(row["ti:"]) else ""
    date_published = str(row["datePublished"]).strip() if not pd.isna(row["datePublished"]) else ""
    inLanguage = str(row["In:"]).strip() if not pd.isna(row["In:"]) else ""

    if not title:
        continue

    # Build query string
    query = f'ti:{title}'
    

    url = "https://americas.discovery.api.oclc.org/worldcat/search/v2/bibs"
    params = {
        "q": query,
        "inLanguage": inLanguage,
        "datePublished": date_published,   # ✅ separate param. make sure to update the params depending on your search query needs
        "inCatalogLanguage": "eng",
        "itemSubType": "book-printbook",
        "orderBy": "mostWidelyHeld",
        "limit": 1
    }
    headers = {
        "Accept": "application/json",
        "Authorization": f"Bearer {OCLC_TOKEN}"
    }

    try:
        response = requests.get(url, headers=headers, params=params)
        response.raise_for_status()
        data = response.json()

        oclc_num = ""
        main_titles = ""

        if data.get("numberOfRecords", 0) > 0:
            record = data["bibRecords"][0]

            # ✅ FIXED: identifier is an object, not a list
            oclc_num = record.get("identifier", {}).get("oclcNumber", "")

            if "title" in record and "mainTitles" in record["title"]:
                main_titles = "; ".join([t["text"] for t in record["title"]["mainTitles"]])

        results.append({
            "Local_Title": title,
            "OCLC_Number": oclc_num,
            "OCLC_Title": main_titles
        })

        print(f"✔ {title} → {oclc_num if oclc_num else 'No OCLC#'}")
        print("   URL:", response.url)

    except Exception as e:
        print(f"❌ Error for {title}: {e}")
        results.append({
            "Local_Title": title,
            "OCLC_Number": "",
            "OCLC_Title": ""
        })

# Save results to Excel
out_df = pd.DataFrame(results)
out_df.to_excel(output_file, index=False)

print(f"\n✅ Finished! Results saved to {os.path.join(os.getcwd(), output_file)}")