面试 https://github.com/taizilongxu/interview_python
http://www.cnblogs.com/alex3714/articles/5885096.html alex
http://www.cnblogs.com/wupeiqi/articles/5433925.html 吴佩其
http://www.cnblogs.com/wupeiqi/articles/6144178.html form组件
http://www.cnblogs.com/wupeiqi/articles/5433893.html 目录http://www.cnblogs.com/wupeiqi/articles/4938499.html 吴佩其 目录
https://www.liaoxuefeng.com/wiki/0014316089557264a6b348958f449949df42a6d3a2e542c000/0014317852443934a86aa5bb5ea47fbbd5f35282b331335000 廖雪峰
介绍、基本语法、流程控制
列表、字典、集合
函数、递归、内置函数
迭代器、装饰器、软件开发规范
常用模块学习
面向对象编程
面向对象编程进阶
Socket编程
html+css+js
第十天---协程
多进程+协程网络爬虫
1 from multiprocessing import Pool 2 from gevent import monkey; monkey.patch_all() 3 import gevent 4 # -*- coding=utf-8 -*- 5 from urllib import request 6 from multiprocessing import Process 7 import gevent,time 8 from gevent import monkey 9 monkey.patch_all()10 import sys11 def fetch(url):12 try:13 # s = request.Session()14 # r = s.get(url, timeout=1) # 在这里抓取页面15 resp = request.urlopen(url)16 data = resp.read()17 except Exception as e:18 print(e)19 return ''20 def process_start(url_list):21 tasks = []22 for url in url_list:23 tasks.append(gevent.spawn(fetch, url))24 gevent.joinall(tasks) # 使用协程来执行25 def task_start(filepath, flag=8): # 每10W条url启动一个进程26 with open(filepath, 'r') as reader: # 从给定的文件中读取url27 url = reader.readline().strip()28 url_list = [] # 这个list用于存放协程任务29 i = 0 # 计数器，记录添加了多少个url到协程队列30 while url != '':31 i += 132 url_list.append(url) # 每次读取出url，将url添加到队列33 if i == flag: # 一定数量的url就启动一个进程并执行34 p = Process(target=process_start, args=(url_list,))35 p.start()36 url_list = [] # 重置url队列37 i = 0 # 重置计数器38 url = reader.readline().strip()39 if url_list: # 若退出循环后任务队列里还有url剩余40 p = Process(target=process_start, args=(url_list,)) # 把剩余的url全都放到最后这个进程来执行41 p.start()42 if __name__ == '__main__':43 print("time",time.time())44 task_start('./testData.txt') # 读取指定文件 io多路复用： (协程)当程序遇到io操作，如从网络接收数据或者从磁盘读数据，这个过程需要磁盘或者网络很长时间的返回，所以程序就切换，就不占用cpu。进程申请打开一个文件，操作系统返回一个文件描述符，操作系统通过文件描述符操作文件对象（文件句柄）。
如网络：socket.recv等于调用操作系统去监听并等待数据，数据返回后，先到内核空间，然后复制到用户空间。
正式因为这两个阶段，linux系统产生了下面五种网络模式的方案。
- 阻塞 I/O（blocking IO）- 非阻塞 I/O（nonblocking IO）- I/O 多路复用（ IO multiplexing）- 信号驱动 I/O（ signal driven IO）- 异步 I/O（asynchronous IO）注：由于signal driven IO在实际中并不常用，所以我这只提及剩下的四种IO Model。
第十天---twisted---redis---rabbitmq
windows下redis安装 https://www.cnblogs.com/jaign/articles/7920588.html
windows下rabbitmq安装 http://blog.csdn.net/hzw19920329/article/details/53156015from sqlalchemy import create_engine
http://www.cnblogs.com/alex3714/articles/5248247.html
第十一天 sqlalchemy
一对多
1 from sqlalchemy.ext.declarative import declarative_base 2 from sqlalchemy import Column, Integer, String, ForeignKey,func,Table 3 from sqlalchemy.orm import sessionmaker, relationship 4 Base = declarative_base() #生成一个SqlORM 基类 5 mima = '!Saiyun12#$' 6 Host2Group = Table('host_2_group',Base.metadata, 7 Column('host_id',ForeignKey('hosts.id'),primary_key=True), 8 Column('goup_id',ForeignKey('group.id'),primary_key=True), 9 )10 engine = create_engine("mysql+pymysql://root:%s@localhost/testdb" % mima,encoding='utf-8', echo=True)11 class Host(Base):12 __tablename__ = 'hosts'13 id = Column(Integer,primary_key=True,autoincrement=True)14 hostname = Column(String(64),unique=True,nullable=False)15 ip_addr = Column(String(128),unique=True,nullable=False)16 port = Column(Integer,default=22)17 group_id = Column(Integer,ForeignKey('group.id'))18 group = relationship("Group",backref='host_list')19 class Group(Base):20 __tablename__ = 'group'21 id = Column(Integer,primary_key=True)22 name = Column(String(64),unique=True,nullable=False)23 Base.metadata.create_all(engine) #创建所有表结构24 if __name__ == '__main__':25 SessionCls = sessionmaker(bind=engine) #创建与数据库的会话session class ,注意,这里返回给session的是个class,不是实例26 session = SessionCls()27 objs = session.query(Host,func.count(Group.name)).join(Host.group).group_by(Group.name).all() #join操作28 print("---->",objs)29 session.commit() # 提交30 ''' obj对应的原声sql31 SELECT hosts.id AS hosts_id, hosts.hostname AS hosts_hostname, hosts.ip_addr AS hosts_ip_addr, hosts.port AS hosts_port, 32 hosts.group_id AS hosts_group_id, count(`group`.name) AS count_1 33 FROM hosts INNER JOIN `group` ON `group`.id = hosts.group_id GROUP BY `group`.name34 ####select * from hosts right join testdb.group on hosts.group_id = testdb.group.id35 ''' 多对多
1 from sqlalchemy import create_engine 2 from sqlalchemy.ext.declarative import declarative_base 3 from sqlalchemy import Column, Integer, String, ForeignKey,func,Table 4 from sqlalchemy.orm import sessionmaker, relationship 5 Base = declarative_base() #生成一个SqlORM 基类 6 mima = '!Saiyun12#$' 7 Host2Group = Table('host_2_group',Base.metadata, 8 Column('host_id',ForeignKey('hosts.id'),primary_key=True), 9 Column('goup_id',ForeignKey('group.id'),primary_key=True),10 )11 engine = create_engine("mysql+pymysql://root:%s@localhost/testdb" % mima,encoding='utf-8', echo=True)12 class Host(Base):13 __tablename__ = 'hosts'14 id = Column(Integer,primary_key=True,autoincrement=True)15 hostname = Column(String(64),unique=True,nullable=False)16 ip_addr = Column(String(128),unique=True,nullable=False)17 port = Column(Integer,default=22)18 groups = relationship('Group',secondary=Host2Group,backref='host_list')19 # group_id = Column(Integer,ForeignKey('group.id'))20 # group = relationship("Group",backref='host_list')21 class Group(Base):22 __tablename__ = 'group'23 id = Column(Integer,primary_key=True)24 name = Column(String(64),unique=True,nullable=False)25 Base.metadata.create_all(engine) #创建所有表结构26 if __name__ == '__main__':27 SessionCls = sessionmaker(bind=engine) #创建与数据库的会话session class ,注意,这里返回给session的是个class,不是实例28 session = SessionCls()29 # g1= Group(name='g1')30 # g2 = Group(name='g2')31 # g3 = Group(name='g3')32 # g4 = Group(name='g4')33 # session.add_all([g1,g2,g3,g4])34 # h1 = Host(hostname='h1',ip_addr='192.168.1.56',port=1000)35 # h2 = Host(hostname='h2', ip_addr='192.168.1.57', port=1002)36 # h3 = Host(hostname='h3', ip_addr='192.168.1.58', port=1003)37 # session.add_all([h1,h2,h3])38 groups=session.query(Group).all()39 h1 = session.query(Host).filter(Host.hostname=='h1').first()40 h1.groups = groups #为已经存在的host和group表创建多对多关系41 42 # objs = session.query(Host,func.count(Group.name)).join(Host.group).group_by(Group.name).all() #join操作43 # print("---->",objs)44 session.commit() # 提交 nihaohelloworld