re

#!/usr/bin/env python
# -*- coding:utf-8 -*-
# Author:woshinidaye

import re
import csv
# #findall 匹配字符串中所有符合正则表达式的内容；
# list = re.findall(r'\d+','我的电话号码是133123123123，女朋友的电话是45678')  #返回的是列表，列表效率很低
# print(list)


# #re.finditer()   #匹配字符串中所有符合正则表达式的内容，返回的是迭代器，这个效率很OK；从迭代器中拿到内容需要.group()
# list2 = re.finditer(r'\d+','我的电话号码是133123123123，女朋友的电话是45678')
# #print(list2,type(list2)) #<callable_iterator object at 0x00000187F8921940> <class 'callable_iterator'>
# for i in list2:
#     print(i.group())

# #re.search          返回match对象，需要.group一下，search全文检索，检索到一个就结束程序
# sear = re.search(r'\d+','我的电话号码是133123123123，女朋友的电话是45678')
# print(sear.group())

# #re.match是从头开始匹配，可以理解为r'^d+'
# mat = re.match(r'\d+','我的电话号码是133123123123，女朋友的电话是45678')
# print(mat)

#预加载正则表达式,正则很长
# obj = re.compile(r'\d+')
# # obj.findall()
# # obj.search()
# test = obj.finditer('我的电话号码是133123123123，女朋友的电话是45678')
# for i in test:
#     print(i.group())
# # obj.match()


#   (?P<id>正则表达式)   可以从正则表达式中匹配到的内容中，进一步提取内容，

ss = '''
<div class='歌手'><span id='1'>林俊杰</div>
<div class='演员'><span id='2'>不知道</div>
<div class='话剧'><span id='3'>乱说</div>
<div class='小品'><span id='4'>啥也不说</div>
'''
# ss本身就是一串有规律的字符串，想把id和name拿出来比较困难，所以，需要用正则表达式匹配成一个一个的元素，
# aa = re.compile(r"<div class='.*?'><span id='(?P<id>\d+)'>(?P<name>.*?)</div>",re.S) #flags=re.S 让.匹配换行符
# # print(type(aa))
# bb = aa.finditer(ss)
# for it in bb:
#     print(it.group('id'),it.group("name"))



# 实战示例1
# 请求一下豆瓣电影top250
#查看页面页数的加载方式：发现是    服务器渲染；
#拿到页面源代码；
#通过re提取有效信息
# import re,requests
# for n in range(0,250,25):
#     # url = 'https://movie.douban.com/top250?start=%s&filter='%n
#     # url = 'https://movie.douban.com/top250?start={0}&filter='.format(n)
#     url = f'https://movie.douban.com/top250?start={n}&filter='
#     # print(url)
#     header = {
#          "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/95.0.4638.69 Safari/537.36"
#      }
#
#     result = requests.get(url,headers=header)
#     page = result.text
#     # with open('1114','w+',encoding='utf-8') as f :              #获取页面源代码
#     #     f.write(result.text)
#     # print(result.text)
#
#     # 解析数据
#
#     obj =  re.compile(r'<li>.*?<div class="item">.*?<span class="title">(?P<title>.*?)</span>'
#                       r'.*?<p class="">(?P<actor>.*?)<br>.*?</span>.*?property="v:averag'
#                       r'e">(?P<score>.*?)</span>',re.S)
#     enenn = obj.finditer(page)
#     f = open('top250.csv','a+',encoding='utf-8',newline='')
#     csvwriter = csv.writer(f)
#     for i in enenn:
#         # print(i.group('title'))
#         # print(i.group('actor').strip())
#         dic = i.groupdict()
#         dic['title'] = dic['title'].strip()
#         dic['actor'] = dic['actor'].strip()
#         # print(dic)
#         csvwriter.writerow(dic.values())
# f.close()
# print('=====done===')