# EasyTutorGuide — ETL Chapter 18: REST API extraction
# Run: python3 ch-18.py
# These examples use only Python standard library.
# JavaScript examples in the HTML are verified using Node.js and are not part of this Python file.

# EXAMPLE 1: Extract CSV, transform types, and summarize
import csv, io
csv_text = "id,amount,status\na,18,paid\nb,4,pending\nc,1,paid\n"
rows = list(csv.DictReader(io.StringIO(csv_text)))
paid = [{"id":r["id"],"amount":int(r["amount"])} for r in rows if r["status"] == "paid"]
print("extracted:", len(rows))
print("paid:", paid)
print("total:", sum(r["amount"] for r in paid))


# EXAMPLE 2: Deduplicate by a stable business key
events = [{"id":"a","value":18},{"id":"b","value":4},{"id":"a","value":1}]
latest = {row["id"]: row["value"] for row in events}
print("deduplicated:", sorted(latest.items()))
print("distinct IDs:", len(latest))


# EXAMPLE 3: Reject invalid source values explicitly
raw = ["18", "unknown", "4", "", "1"]
valid, rejected = [], []
for item in raw:
    try: valid.append(int(item))
    except ValueError: rejected.append(item)
print("valid:", valid)
print("rejected:", rejected)
print("sum:", sum(valid))