第 5 章 · 自动化

import os, shutil

src = "inbox"                 # 待整理目录
for name in os.listdir(src):
    path = os.path.join(src, name)
    if os.path.isfile(path):
        ext = name.split(".")[-1].lower()     # 取扩展名
        target = os.path.join(src, ext)        # 按类型建文件夹
        os.makedirs(target, exist_ok=True)
        shutil.move(path, os.path.join(target, name))
        print("已移动", name, "→", ext + "/")

import os, tempfile, shutil

d = tempfile.mkdtemp()
for n in ["a.txt", "b.txt", "c.txt"]:
    open(os.path.join(d, n), "w").close()

i = 1
for name in sorted(os.listdir(d)):
    if name.endswith(".txt"):
        new = f"笔记_{i}.txt"
        os.rename(os.path.join(d, name), os.path.join(d, new))
        i += 1

print(sorted(os.listdir(d)))
shutil.rmtree(d)

import os, tempfile, shutil
from collections import Counter

d = tempfile.mkdtemp()
for n in ["报告.txt", "图片.png", "数据.csv", "照片.jpg", "笔记.txt"]:
    open(os.path.join(d, n), "w").close()

exts = Counter(n.split(".")[-1].lower() for n in os.listdir(d))
print("按类型统计：", dict(exts))
shutil.rmtree(d)

import re

text = "联系：alice@mail.com，bob@test.org，电话 138-0000-1234"
# 提取所有邮箱
emails = re.findall(r"[\w.-]+@[\w.-]+", text)
print(emails)

# 提取手机号（1 开头，11 位）
phone = re.search(r"1\d{2}-\d{4}-\d{4}", text)
print(phone.group() if phone else "无")

import re
text = "订单时间：2026-09-15 和 2026-10-01，发货 2026/11/20"
dates = re.findall(r"\d{4}[-/]\d{2}[-/]\d{2}", text)
print("找到日期：", dates)

import re
log = "ERROR 10:22:01 磁盘满 | INFO 10:25:03 已恢复 | ERROR 10:30:11 网络断开"
errors = re.findall(r"ERROR (\d{2}:\d{2}:\d{2})", log)
print("ERROR 次数：", len(errors))
print("发生时间：", errors)

import requests

r = requests.get("https://example.com", timeout=5)
print("状态码：", r.status_code)
print("网页长度：", len(r.text))     # r.text 是网页 HTML 文本

# 取 JSON 接口更简单
# data = requests.get("https://api.xxx.com/weather").json()

from urllib.parse import urlencode, quote

base = "https://api.example.com/search"
params = {"q": "Python 自动化", "page": 1}
url = base + "?" + urlencode(params)
print("请求地址：", url)
print("编码后关键词：", quote("Python 自动化"))

import urllib.request, urllib.parse, re

html = "<html><head><title>码上问学</title></head><body>欢迎学习</body></html>"
url = "data:text/html," + urllib.parse.quote(html)
with urllib.request.urlopen(url) as resp:
    page = resp.read().decode("utf-8")

title = re.search(r"<title>(.*?)</title>", page)
print("网页标题：", title.group(1) if title else "无")

from openpyxl import Workbook

wb = Workbook()
ws = wb.active
ws.append(["姓名", "分数"])
ws.append(["张三", 90])
ws.append(["李四", 85])
wb.save("成绩表.xlsx")     # 一键生成 Excel

import csv, io

data = "姓名,分数\n张三,90\n李四,85\n王五,95\n"
rows = list(csv.DictReader(io.StringIO(data)))
total = sum(int(r["分数"]) for r in rows)
print("人数：", len(rows))
print("平均分：", total / len(rows))

from email.message import EmailMessage

msg = EmailMessage()
msg["From"] = "bot@school.com"
msg["To"] = "teacher@school.com"
msg["Subject"] = "每日成绩报告"
msg.set_content("今日已完成 3 份成绩汇总，平均分 90。")

print("收件人：", msg["To"])
print("主题：", msg["Subject"])
print("正文：", msg.get_content().strip())

# 需先安装：pip install pdfplumber
import pdfplumber

with pdfplumber.open("报告.pdf") as pdf:
    text = pdf.pages[0].extract_text()
    print(text)