作业3

作业3：
import re

1、非负整数

[99,100,-100,-1,90]

numbers = [99,100,-100,-1,90,0,1,]

p1 = re.compile(r’^\d+$’)

2、匹配正整数

p1 = re.compile(r’¹\d*$’)

3、非正整数

p1 = re.compile(’^(0|-\d+)$’)

for i in numbers:

result = p1.search(str(i))

print(result)

4、qq邮箱：

qq号5位—14

content = ‘aaaaa2506905772@qq.comaa:2019-12-20,abbbcc13345678911agc,2018-09-11’
p2 = re.compile(r’[1-9]\d{4,13}@qq.com’)

print(p2.search(content).group())

5、匹配11位电话号码

1 3-9

p3 = re.compile(r’1[3-9]\d{9}’)
print(p3.search(content).group())

6、匹配日期：

2019-12-19

content = ‘Aaaaaa2506905772@qq.comaa:2019-12-20,abbbcc13345678911agc,2018-09-11’
p4 = re.compile(r’[1-9]\d{3}-(1[0-2]|0?[1-9])-(3[0-1]|[1-2]\d|0?[1-9])’)
m = p4.search(content)

print(m.group())

print(p4.search(content,m.end()+1))

7、长度为8-10的用户密码：

开头字母：必须大写，每一位可以是数字，字母，_

p5 = re.compile(r’[A-Z]\w{7,9}’)
print(p5.search(content))
猫眼其他字段做出来。

import re,json

import requests
def write_to_json(infos):
    with open('movie.json','w',encoding='utf-8') as fp :
        json.dump(infos,fp)
#解析页面内容
def parse_page(html_str):
    #测试页面内容是否能拿到
    # print(html_str)
    #正则筛选页面的原则：一步步缩小匹配范围。
    dl_p = re.compile(r'<dl class="board-wrapper">(.*?)</dl>',re.S)
    dl_content = dl_p.search(html_str).group()
    dd_p = re.compile(r'<dd>(.*?)</dd>',re.S)
    dd_list = dd_p.findall(dl_content)
    # print(dd_list)
    '''
    电影名称
    主演
    上映时间评分
    详情url
   
    '''
    for dd in dd_list:
        name_p = re.compile(r'" title="(.*?)" class="',re.S)
        name = name_p.search(dd).group(1)
        # print(name)
        actor_p = re.compile(r'<p class="star">(.*?)</p>',re.S)
        actor = actor_p.search(dd).group(1).strip()
        # print(actor)
        #设置爬取数据
        item = {}
        item['name'] =name
        item['actor'] = actor
        print(item)
        infos.append(item)
        #保存到json文件

# 
# 一个方法干一件事
def main():
    #确定基础url
    base_url = 'https://maoyan.com/board/4?offset=%s'
    headers= {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',

    }
    for i in range(10):
        # print(base_url %i*10)
        response = requests.get(base_url %(i*10),headers=headers)
        parse_page(response.text)
if __name__ == '__main__':
    # infos = []
    # main()#提取数据，将数据添加到infos中
    #将数据写入文件
    # write_to_json(infos)
    #从movie.json文件中读出电影数据

    infos = json.load(open('movie.json','r'))
    for item in infos:
        print(item)

股吧：
1，字段
阅读
评论
标题
作者
更新时间
详情页
2.10页内容保存到json文件。

import requests,re,json
#判空校验
def get_match(match,number):
    if match:
        return match.group(number)
    return ''
def write_to_json(infos):
    with open('guba.json','w',encoding='utf-8') as fp:
        json.dump(infos,fp)

def parse_page(html_str):
    # print(html_str)
    ul_p = re.compile(r' <ul class="newlist"(.*?)</ul>',re.S)
    ul_content = get_match(ul_p.search(html_str),0)
    li_p = re.compile(r'<li>(.*?)</li>', re.S)
    li_contents = li_p.findall(ul_content)
    # print(li_content)
    for li in li_contents:
        #阅读
        infos_p = re.compile(r'<cite>(.*?)</cite>',re.S)
        infos = infos_p.findall(li)
        if len(infos)==2:
            read_num = infos[0].strip()
            comment_num = infos[1].strip()
            title_p = re.compile(r'" title="(.*?)" class=',re.S)
            title = get_match(title_p.search(li),1)
            # print(title)
            href_p = re.compile(r' <a href="(.*?)" title="',re.S)
            href = get_match(href_p.search(li),1)
            # print(href)
            href = 'http://guba.eastmoney.com'+href
            item = {}
            item['read_num'] =read_num
            item['comment_num'] =comment_num
            item['title'] =title
            item['href'] =href
            print(item)
            infos.append(item)

def main():
    base_url = 'http://guba.eastmoney.com/default,99_%s.html'
    headers= {
        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36',
    }
    for page in range(1,13):
        response = requests.get(base_url %page ,headers= headers)
        parse_page(response.text)

if __name__ == '__main__':
    infos = []
    main()
    write_to_json(infos)

未完待续…

---

1. 1-9 ↩︎