day 18 - 2 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

#待完成
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) )'