方法一。有如下值集合 [11,22,33,44,55,66,77,88,99,90...],将所有大于 66 的值保存至字典的第一个key中,将小于 66 的值保存至第二个key的值中。
即: {'k1': 大于66 , 'k2': 小于66}
values = [11, 22, 33,44,55,66,77,88,99,90] my_dict = {} for value in values:
if value>66:
if my_dict.has_key('k1'):
my_dict['k1'].append(value)
else:
my_dict['k1'] = [value]
else:
if my_dict.has_key('k2'):
my_dict['k2'].append(value)
else:
my_dict['k2'] = [value]
方法二。from collections import defaultdict values = [11, 22, 33,44,55,66,77,88,99,90] my_dict = defaultdict(list) for value in values:
if value>66:
my_dict['k1'].append(value)
else:
my_dict['k2'].append(value)
三。defaultdict 的用法
from collections import defaultdict
dd = defaultdict(lambda: 'N/A')
dd['key1'] = 'abc'
dd['key1'] # key1存在
'abc'
dd['key2'] # key2不存在,返回默认值
'N/A'
defaultdict
#如下,每个小字典的name对应股票名字,shares对应多少股,price对应股票的价格
portfolio = [
{'name': 'IBM', 'shares': 100, 'price': 91.1},
{'name': 'AAPL', 'shares': 50, 'price': 543.22},
{'name': 'FB', 'shares': 200, 'price': 21.09},
{'name': 'HPQ', 'shares': 35, 'price': 31.75},
{'name': 'YHOO', 'shares': 45, 'price': 16.35},
{'name': 'ACME', 'shares': 75, 'price': 115.65}]
#1.计算购买每支股票的总价?
ret = map(lambda dic:{dic['name']:round(dic['share']*dic['price'],2)},portfolio)
print(list(ret))
#2.用filter过滤出,单价大于100的股票有哪些?
#方法一
ret = filter(lambda dic:True if dic['price'] > 100 else False,portfilio)
print(list(ret))
#方法二
ret = filter(lambda dic:dic['price'] > 100,portfilio)
print(list(ret))
真题一
利用递归函数找二分法
def find(l,aim,start = 0,end = None):
end = len(l) if end is None else end
mid_index = (end - start)//2 + start
if start <= end:
if l[mid_index] < aim:
return find(l,aim,start = mid_index+1,end = end)
elif l[mid_index] > aim:
return find(l,aim,start = start,end = mid_index-1)
else:
return mid_index
else:
return '找不到这个值'
ret = find(l,55)
print(ret)
利用递归函数找二分法******
import re ret=re.findall(r"\d+","1-2*(60+(-40.35/5)-(-4*3))")
print(ret) #['1', '2', '60', '40', '35', '5', '4', '3']
ret=re.findall(r"-?\d+\.\d*|(-?\d+)","1-2*(60+(-40.35/5)-(-4*3))")
print(ret) #['1', '-2', '60', '', '5', '-4', '3']
ret.remove("")
print(ret) #['1', '-2', '60', '5', '-4', '3']
匹配整数
1、 匹配一段文本中的每行的邮箱
http://blog.csdn.net/make164492212/article/details/51656638 2、 匹配一段文本中的每行的时间字符串,比如:‘1990-07-12’; 分别取出1年的12个月(^(0?[1-9]|1[0-2])$)、
一个月的31天:^((0?[1-9])|((1|2)[0-9])|30|31)$ 3、 匹配qq号。(腾讯QQ号从10000开始) [1,9][0,9]{4,} 4、 匹配一个浮点数。 ^(-?\d+)(\.\d+)?$ 或者 -?\d+\.?\d* 5、 匹配汉字。 ^[\u4e00-\u9fa5]{0,}$ 6、 匹配出所有整数
数字匹配
import requests import re
import json def getPage(url): response=requests.get(url)
return response.text def parsePage(s): com=re.compile('<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?<span class="title">(?P<title>.*?)</span>'
'.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>(?P<comment_num>.*?)评价</span>',re.S) ret=com.finditer(s)
for i in ret:
yield {
"id":i.group("id"),
"title":i.group("title"),
"rating_num":i.group("rating_num"),
"comment_num":i.group("comment_num"),
} def main(num): url='https://movie.douban.com/top250?start=%s&filter='%num
response_html=getPage(url)
ret=parsePage(response_html)
print(ret)
f=open("move_info7","a",encoding="utf8") for obj in ret:
print(obj)
data=json.dumps(obj,ensure_ascii=False)
f.write(data+"\n") if __name__ == '__main__':
count=0
for i in range(10):
main(count)
count+=25
爬虫练习
import re
import json
from urllib.request import urlopen def getPage(url):
response = urlopen(url)
return response.read().decode('utf-8') def parsePage(s):
com = re.compile(
'<div class="item">.*?<div class="pic">.*?<em .*?>(?P<id>\d+).*?<span class="title">(?P<title>.*?)</span>'
'.*?<span class="rating_num" .*?>(?P<rating_num>.*?)</span>.*?<span>(?P<comment_num>.*?)评价</span>', re.S) ret = com.finditer(s)
for i in ret:
yield {
"id": i.group("id"),
"title": i.group("title"),
"rating_num": i.group("rating_num"),
"comment_num": i.group("comment_num"),
} def main(num):
url = 'https://movie.douban.com/top250?start=%s&filter=' % num
response_html = getPage(url)
ret = parsePage(response_html)
print(ret)
f = open("move_info7", "a", encoding="utf8") for obj in ret:
print(obj)
data = str(obj)
f.write(data + "\n") count = 0
for i in range(10):
main(count)
count += 25
爬虫练习简化版
flags有很多可选值: re.I(IGNORECASE)忽略大小写,括号内是完整的写法
re.M(MULTILINE)多行模式,改变^和$的行为
re.S(DOTALL)点可以匹配任意字符,包括换行符
re.L(LOCALE)做本地化识别的匹配,表示特殊字符集 \w, \W, \b, \B, \s, \S 依赖于当前环境,不推荐使用
re.U(UNICODE) 使用\w \W \s \S \d \D使用取决于unicode定义的字符属性。在python3中默认使用该flag
re.X(VERBOSE)冗长模式,该模式下pattern字符串可以是多行的,忽略空白字符,并可以添加注释
flags
import re
ret = re.search("<(?P<tag_name>\w+)>\w+</(?P=tag_name)>","<h1>hello</h1>")
#还可以在分组中利用?<name>的形式给分组起名字
#获取的匹配结果可以直接用group('名字')拿到对应的值
print(ret.group('tag_name')) #结果 :h1
print(ret.group()) #结果 :<h1>hello</h1> ret = re.search(r"<(\w+)>\w+</\1>","<h1>hello</h1>")
#如果不给组起名字,也可以用\序号来找到对应的组,表示要找的内容和前面的组内容一致
#获取的匹配结果可以直接用group(序号)拿到对应的值
print(ret.group(1))
print(ret.group()) #结果 :<h1>hello</h1>
匹配标签
import random def v_code(): code = ''
for i in range(5): num=random.randint(0,9)
alf=chr(random.randint(65,90))
add=random.choice([num,alf])
code="".join([code,str(add)]) return code print(v_code()
生成随机验证码
# 练习一:在终端输出如下信息
#
# 小明,10岁,男,上山去砍柴
# 小明,10岁,男,开车去东北
# 小明,10岁,男,最爱大保健
# 老李,90岁,男,上山去砍柴
# 老李,90岁,男,开车去东北
# 老李,90岁,男,最爱大保健
# 老张…
class Person:
def __init__(self,name,age,sex):
self.name = name
self.age = age
self.sex = sex
def shangshan(self):
print('%s%d%s上山砍柴'%(self.name,self.age,self.sex))
def drive(self):
print('%s%d%s开车去东北'%(self.name,self.age,self.sex))
def favorite(self):
print('%s%d%s最爱大保健'%(self.name,self.age,self.sex))
p1 = Person('小明',23,'男')
p2 = Person('老李',32,'男')
Person.shangshan(p1)
p1.shangshan()
Person.drive(p2)
p2.drive()
面向对象练习题
from math import pi
class Arc:
def __init__(self,r):
self.r = r
def area(self):
return pi*(self.r**2)
def perimeter(self):
print(2*self.r*pi)
p1 = Arc(3)
print(p1.area())
p1.perimeter()
print(Arc.area(p1))
Arc.perimeter(p1)
用面向对象求周长和面积
class Carstore(object):
def __init__(self):
self.factory = Factory()
def order(self,car_type):
return self.factory.select_car_by_type(car_type)
class Factory(object):
def select_car_by_type(self,car_type):
if car_type == '索纳塔':
return Suonata()
elif car_type == '名图':
return Mingtu()
elif car_type == 'ix35':
return Ix35()
class Car(object):
def move(self):
print('车在移动。。。')
def music(self):
print('正在播放音乐。。。')
def stop(self):
print('车在停止。。。')
class Suonata(Car):pass
class Mingtu(Car):pass
class Ix35(Car):pass
car_store = Carstore()
car = car_store.order('索纳塔')
car.move()
car.music()
car.stop()
cs店
class Dog:
def __init__(self,name,blood,aggr,kind):
self.name = name
self.hp = blood
self.aggr = aggr
self.kind = kind
def bite(self,person):
person.blood -= self.aggr
class Person:
def __init__(self,name,blood,aggr,sex):
self.name = name
self.blood = blood
self.aggr = aggr
self.sex = sex
def attack(self,dog):
dog.hp -= self.aggr
if dog.hp <= 0:
print('%s is over %s have %s xie'%(dog.name,self.name,self.blood))
else:print('%s dadiao le %s %sdixie'%(self.name,dog.name,dog.hp))
d1 = Dog('jinlaoban',100,10,'taddy')
p1 = Person('laoli',100,10,'nan')
p1.attack(d1)
d1.bite(p1)
人狗大战