Day09 学习笔记

线程同步：互斥锁 Lock

• 多线程访问共享资源时使用互斥锁，保证同一时间只有一个线程进入临界区。

import threading
import time

lock = threading.Lock()

class MyThread(threading.Thread):
    def __init__(self, name, delay):
        threading.Thread.__init__(self)
        self.name = name
        self.delay = delay

    def run(self):
        print "starting", self.name
        lock.acquire()           # 获得锁（进入临界区）
        try:
            count = 5
            while count:
                time.sleep(self.delay)
                print "%s : %s" % (self.name, time.ctime())
                count -= 1
        finally:
            lock.release()       # 释放锁（离开临界区）
        print "exiting", self.name

t1 = MyThread("Thread-1", 1)
t2 = MyThread("Thread-2", 2)
t2.start()
t1.start()
t2.join()
print "exiting main!!!"

可重入锁 RLock（递归锁）

• 一个线程在同一把锁上重复 acquire 时不会被自己阻塞，便于在同一线程内的嵌套调用中复用锁。

import threading
import time

class Worker(object):
    lock = threading.RLock()

    def step1(self):
        if self.lock.acquire():
            try:
                count = 3
                while count:
                    time.sleep(1)
                    print "step1"
                    count -= 1
            finally:
                self.lock.release()

    def step2(self):
        if self.lock.acquire():
            try:
                for _ in range(3):
                    print "step2"
            finally:
                self.lock.release()

    def show(self):
        if self.lock.acquire():
            try:
                self.step1()     # 在同一线程内再次获取同一把锁
                self.step2()
            finally:
                self.lock.release()
        print "Thread-1 over!!!"

    def step3(self, name):
        if self.lock.acquire():
            try:
                print "step3 == %s" % name
            finally:
                self.lock.release()
        print "Thread-2 over!!!"

w = Worker()
t1 = threading.Thread(target=w.show)
t2 = threading.Thread(target=w.step3, args=("tom",))
t1.start()
t2.start()

简单爬虫流程（示例：带请求头抓取页面）

• 构造请求时添加 User-Agent，获取 HTML 后用正则表达式提取字段；解析结果可持久化（如写库）。

import urllib2
import re

headers = {"User-Agent": "Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1)"}
url = "http://example.com/list"

req = urllib2.Request(url, headers=headers)
html = urllib2.urlopen(req).read()

# 示例：提取标题与价格（模式仅演示）
pattern = re.compile(r'<div class="item">.*?<h2>(.*?)</h2>.*?<span class="price">(.*?)</span>', re.S)
items = re.findall(pattern, html)

for title, price in items:
    title = re.sub(r'\s+', ' ', title).strip()
    price = price.strip()
    print title, price

数据入库（示意：插入 Oracle）

• 建表与插入的基本流程（示例字段，仅供参考）：

import cx_Oracle

db = cx_Oracle.connect("user", "password", "127.0.0.1:1521/orcl")
cursor = db.cursor()

cursor.execute(
    """
    CREATE TABLE WEB_DATA(
        title varchar2(200),
        price varchar2(50)
    )
    """
)
db.commit()

rows = [("标题A", "1200"), ("标题B", "800")]
cursor.executemany("INSERT INTO WEB_DATA(title, price) VALUES (:1, :2)", rows)
db.commit()

cursor.close()
db.close()