Initial commit: HBR 文章爬蟲專案

- Scrapy 爬蟲框架,爬取 HBR 繁體中文文章
- Flask Web 應用程式,提供文章查詢介面
- SQL Server 資料庫整合
- 自動化排程與郵件通知功能

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
2025-12-03 17:19:56 +08:00
commit f524713cb6
35 changed files with 6719 additions and 0 deletions

72
send_mail.py Normal file
View File

@@ -0,0 +1,72 @@
# send_mail.py
import os, smtplib, sys, mimetypes
from datetime import datetime, timezone, timedelta
from email.message import EmailMessage
# 讀環境變數(請在 crontab 或 GitHub Actions secrets 設定)
# 如果未設定,則跳過郵件發送功能
GMAIL_USER = os.environ.get("GMAIL_USERNAME") # 例如yourname@gmail.com
GMAIL_PASS = os.environ.get("GMAIL_APP_PASSWORD") # 16碼 App Password非一般登入密碼
TO = os.environ.get("MAIL_TO", "kaeruzak@gmail.com")
# 檢查是否啟用郵件功能
ENABLE_MAIL = GMAIL_USER and GMAIL_PASS
# 參數CSV 路徑(預設 ./hbr_articles.csv
csv_path = sys.argv[1] if len(sys.argv) > 1 else "hbr_articles.csv"
if not os.path.exists(csv_path):
print(f"[WARN] CSV not found: {csv_path}")
sys.exit(0)
# 如果未啟用郵件功能,僅顯示資訊並退出
if not ENABLE_MAIL:
print("[INFO] Gmail SMTP 未設定,跳過郵件發送功能")
print(f"[INFO] CSV 檔案已產生: {csv_path}")
print("[INFO] 如需啟用郵件功能,請設定以下環境變數:")
print(" - GMAIL_USERNAME")
print(" - GMAIL_APP_PASSWORD")
print(" - MAIL_TO (可選,預設: kaeruzak@gmail.com)")
sys.exit(0)
# 產生台北時間日期字串
tz = timezone(timedelta(hours=8))
date_str = datetime.now(tz).strftime("%Y-%m-%d %H:%M")
# 組信
msg = EmailMessage()
msg["Subject"] = f"[HBRTW 每週爬取] 文章清單 CSV - {date_str}"
msg["From"] = GMAIL_USER
msg["To"] = TO
msg.set_content(f"""您好,
附件為本週 HBR Taiwan 最新/熱門文章彙整CSV
產生時間:{date_str}Asia/Taipei
若您需要改排程或加上上傳雲端,回覆此信即可。
""")
# 夾帶 CSV
ctype, encoding = mimetypes.guess_type(csv_path)
if ctype is None or encoding is not None:
ctype = "application/octet-stream"
maintype, subtype = ctype.split("/", 1)
with open(csv_path, "rb") as f:
msg.add_attachment(f.read(),
maintype=maintype,
subtype=subtype,
filename=os.path.basename(csv_path))
# 寄送郵件
try:
with smtplib.SMTP_SSL("smtp.gmail.com", 465) as smtp:
smtp.login(GMAIL_USER, GMAIL_PASS)
smtp.send_message(msg)
print(f"[OK] Mail sent to {TO}")
except smtplib.SMTPAuthenticationError as e:
print(f"[ERROR] Gmail 認證失敗: {e}")
print("請確認:")
print(" 1. GMAIL_USERNAME 是否正確")
print(" 2. GMAIL_APP_PASSWORD 是否為有效的 App Password16碼")
print(" 3. 是否已啟用 Gmail 的兩步驟驗證")
sys.exit(1)
except Exception as e:
print(f"[ERROR] 郵件發送失敗: {e}")
sys.exit(1)