Thu thập dữ liệu và lập báo cáo bằng Python và AI

import argparse
import csv
import io
from pathlib import Path
from urllib.parse import urlsplit
from urllib.request import Request, urlopen

SAMPLE = "team,hours\nDesign,2\nEngineering,3\nDesign,1\n"

def read_source(url=None):
    if url is None:
        return SAMPLE
    if urlsplit(url).scheme != "https":
        raise ValueError("use an approved HTTPS CSV source")
    request = Request(url, headers={"User-Agent": "TrainingReport/1.0"})
    with urlopen(request, timeout=15) as response:
        data = response.read(100001)
    if len(data) > 100000:
        raise ValueError("source exceeds 100 KB")
    return data.decode("utf-8-sig")

def aggregate(text):
    rows = csv.DictReader(io.StringIO(text))
    if not {"team", "hours"} <= set(rows.fieldnames or []):
        raise ValueError("team and hours columns required")
    totals = {}
    for row in rows:
        team = row["team"].strip()
        hours = int(row["hours"])
        if not team or hours < 0:
            raise ValueError("invalid team or hours")
        totals[team] = totals.get(team, 0) + hours
    return totals

def write_report(totals):
    lines = ["# Training hours", "", "| Team | Hours |", "| --- | ---: |"]
    for team, hours in sorted(totals.items()):
        safe = team.replace("|", "\\|").replace("\n", " ")
        lines.append(f"| {safe} | {hours} |")
    lines += ["", f"Total hours: {sum(totals.values())}"]
    Path("report.md").write_text("\n".join(lines) + "\n", encoding="utf-8")

if __name__ == "__main__":
    parser = argparse.ArgumentParser()
    parser.add_argument("--url")
    args = parser.parse_args()
    totals = aggregate(read_source(args.url))
    write_report(totals)
    print("Total hours:", sum(totals.values()))

python3 report.py