day 18 - 2 正则与 re 模块练习

1、爬虫的例子

#爬虫的例子（方法一）
import re
import urllib,request import urlopen

def getPage(url):
    response = urlopen(url)
    return response.read().decode('utf-8')

def parsePage(s):
    ret = re.findall(
        '<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>',s,re.S)
    return ret

def main(num):
    url = 'https://movie.douban.com/top250?start=%s&filter=' % num
    response_html = getPage(url)
    ret = parsePage(response_html)
    print(ret)

count = 0
for i in range(10):   # 10页
    main(count)
    count += 25

# url 从网页上把代码搞下来
# bytes decode ——> utf-8 网页内容就是我的待匹配字符串
# ret = re.findall(正则，带匹配的字符串)  #ret是所有匹配到的内容组成的列表

#爬虫的例子（方法一）
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

1、计算器

#计算下面式子
a = '1 - 2 * ( ( 6 0 -3 0  +(-40/5) * (9-2*5/3 + 7 /3*99/4*2998 +10 * 568/14 )) - (-4*3)/ (16-3*2) )'

import re

def format(new_equation):
    new_equation = new_equation.replace('+-','-')
    new_equation = new_equation.replace('--', '+')
    return new_equation

def cal(val_son):
    '''加减乘除的计算'''
    #print(new_val)
    if '/' in val_son:
        a,b = val_son.split('/')
        return str(float(a)/float(b))
    elif '*' in val_son:
        a,b = val_son.split('*')
        return str(float(a)*float(b))

def no_brackets(val):
    '''去括号'''
    new_val = val.strip('()')
    while True:
        ret = re.search('\d+\.?\d*[*/]-?\d+\.?\d*',new_val) #匹配第一个乘除
        if ret: #说明 表达式中海油乘除法
            val_son = ret.group()  #子表达式
            ret = cal(val_son)
            new_val = new_val.replace(val_son,ret)
            new_val = format(new_val)
        else:
            ret = re.findall('-?\d+\.?\d*',new_val)
            sum =
            for i in ret:
                sum += float(i)
            return str(sum)

def func(new_equation):
    while True:
        val = re.search('\([^()]+\)',new_equation)
        if val:
            val = val.group()
            ret = no_brackets(val)
            new_equation = new_equation.replace(val,ret)
            new_equation = format(new_equation)
        else:
            return no_brackets(new_equation)

a = input("请输入要计算的式子>>>")
new_equation = a.replace(' ','')
print(func(new_equation))