import re
s = 'helloworld hellobeijing'
ret = re.findall('hello\S+',s)
print(ret)
['helloworld', 'hellobeijing']

import re
# re.search
ret = re.search('h..','hello hello world')
print(ret) # 输出结果：<_sre.SRE_Match object; span=(0, 3), match='hel'>
ret1 = re.search('h..','hello hello world').group()
print(ret1) # 输出结果：hel 只输出第一个符合条件的结果

# re.match
ret = re.match('asd','asdhskdjfksji')
print(ret) # 输出结果：<_sre.SRE_Match object; span=(0, 3), match='asd'>返回的是一个对象。
ret1 = re.match('asd','asdhskdjfasdksjiasd').group()
print(ret1) # 输出结果：asd 调用.group()方法，只返回匹配的第一个结果。

# re.search
s = 'helloworld hellobeijing'
ret = re.search('hellob\S+',s)
print(ret)
<re.Match object; span=(11, 23), match='hellobeijing'>

# re.match
s = 'helloworld hellobeijing'
ret = re.match('hellob\S+',s)
print(ret)
None

import re
s = 'helloworld hellobeijing'
ret = re.split('hello',s)
print(ret)
['', 'world ', 'beijing']

import re
s = 'helloworld hellobeijing'
ret = re.sub('hello','goodbye',s)
print(ret)
goodbyeworld goodbyebeijing

import re
pattern = re.compile('he.{3}')
pattern.match(s)
<re.Match object; span=(0, 5), match='hello'>

import re

s = 'i love python very much'
pat = 'python' 
r = re.search(pat,s)
print(r.span()) #(7,13)

s = '山东省潍坊市青州第1中学高三1班'
pat = '1'
r = re.finditer(pat,s)
for i in r:
    print(i)

# <re.Match object; span=(9, 10), match='1'>
# <re.Match object; span=(14, 15), match='1'>

s = '一共20行代码运行时间13.59s'
pat = r'\d+' # +表示匹配数字(\d表示数字的通用字符)1次或多次
r = re.findall(pat,s)
print(r)
# ['20', '13', '59']

s = '一共20行代码运行时间13.59s'
pat = r'\d+\.?\d+' # ?表示匹配小数点(\.)0次或1次
r = re.findall(pat,s)
print(r)
# ['20', '13.59']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'^[emrt]' # 查找以
r = re.findall(pat,s)
print(r)
# [],因为字符串的开头是字符`T`，不在emrt匹配范围内，所以返回为空

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'^[emrt]' # 查找以
r = re.compile(pat,re.I).search(s)
print(r)
# <re.Match object; span=(0, 1), match='T'> 表明字符串的开头在匹配列表中

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'\s[a-zA-Z]+'  
r = re.findall(pat,s)
print(r) #[' module', ' provides', ' regular', ' expression', ' matching', ' operations', ' similar', ' to', ' those', ' found', ' in', ' Perl']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'\s([a-zA-Z]+)'  
r = re.findall(pat,s)
print(r) #['module', 'provides', 'regular', 'expression', 'matching', 'operations', 'similar', 'to', 'those', 'found', 'in', 'Perl']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'\s?([a-zA-Z]+)'  
r = re.findall(pat,s)
print(r) #['This', 'module', 'provides', 'regular', 'expression', 'matching', 'operations', 'similar', 'to', 'those', 'found', 'in', 'Perl']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'\s+'  
r = re.split(pat,s)
print(r) # ['This', 'module', 'provides', 'regular', 'expression', 'matching', 'operations', 'similar', 'to', 'those', 'found', 'in', 'Perl']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'\s?([mt][a-zA-Z]*)' # 查找以
r = re.findall(pat,s)
print(r) # ['module', 'matching', 'tions', 'milar', 'to', 'those']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'^([mt][a-zA-Z]*)\s' # 查找以
r = re.compile(pat,re.I).findall(s)
print(r) # ['This']

s = 'This module provides regular expression matching operations similar to those found in Perl'
pat = r'\s+'  
r = re.split(pat,s)
res = [i for i in r if re.match(r'[mMtT]',i)] 
print(res) # ['This', 'module', 'matching', 'to', 'those']

content='<h>ddedadsad</h><div>graph</div>bb<div>math</div>cc'
pat=re.compile(r"<div>(.*)</div>")  #贪婪模式
m=pat.findall(content)
print(m) # ['graph</div>bb<div>math']

content='<h>ddedadsad</h><div>graph</div>bb<div>math</div>cc'
pat=re.compile(r"<div>(.*?)</div>")  #贪婪模式
m=pat.findall(content)
print(m) # ['graph', 'math']

content = 'graph math,,english;chemistry' # 这种
pat=re.compile(r"[\s\,\;]+")  #贪婪模式
m=pat.split(content)
print(m) # ['graph', 'math', 'english', 'chemistry']

content="hello 12345, hello 456321"    
pat=re.compile(r'\d+') #要替换的部分
m=pat.sub("666",content)
print(m) # hello 666, hello 666

import re
from urllib import request

#爬虫爬取百度首页内容
data=request.urlopen("http://www.baidu.com/").read().decode()

#分析网页,确定正则表达式
pat=r'<title>(.*?)</title>'

result=re.search(pat,data)
print(result) <re.Match object; span=(1358, 1382), match='<title>百度一下，你就知道</title>'>

result.group() # 百度一下，你就知道

. 匹配任意字符  
^ 匹配字符串始位置 
$ 匹配字符串中结束的位置 
* 前面的原子重复0次1次多次 
? 前面的原子重复一次或者0次 
+ 前面的原子重复一次或多次
{n} 前面的原子出现了 n 次
{n,} 前面的原子至少出现 n 次
{n,m} 前面的原子出现次数介于 n-m 之间
( ) 分组,需要输出的部分

\s  匹配空白字符 
\w  匹配任意字母/数字/下划线 
\W  和小写 w 相反，匹配任意字母/数字/下划线以外的字符
\d  匹配十进制数字
\D  匹配除了十进制数以外的值 
[0-9]  匹配一个0-9之间的数字
[a-z]  匹配小写英文字母
[A-Z]  匹配大写英文字母

# 18和15位身份证
(^[1-9]\d{5}(18|19|20)\d{2}((0[1-9])|(10|11|12))(([0-2][1-9])|10|20|30|31)\d{3}[0-9Xx]$)|(^[1-9]\d{5}\d{2}((0[1-9])|(10|11|12))(([0-2][1-9])|10|20|30|31)\d{2}$)

# 以非--开头字符 
--odps sql 
--********************************************************************--
--author:数据开发
--苗宇晨
--create time:2020-08-14 17:47:09
--华东日报补充需求
--********************************************************************--
-- create table  hopson_datawoks.app_rp_district_daily_supply_d (
--    company_id string comment '项目ID',
--    districtid string comment '区域ID',
--    company_name string comment '项目名称',
--    district_name STRING COMMENT '区域名称',
--    organize_id string comment '组织编码',
--    organize_name string comment '组织名称',
--    businessproperty_id STRING comment '业务线编码',
--    businessproperty string comment '事业线类型',
--    summary_type string comment '交易类型',
--    trans_num DOUBLE COMMENT '交易比数',
--    index_values DOUBLE COMMENT '交易金额',
--    actual_index_values DOUBLE COMMENT '实际交易金额'
-- ) PARTITIONED  BY (dt string); 
-- ALTER table hopson_datawoks.app_rp_district_daily_supply_d CHANGE  id  businessproperty_id string ;
INSERT OVERWRITE TABLE hopson_datawoks.app_rp_district_daily_supply_d PARTITION(dt)
select t3.companyid,
       t3.districtid,
       t3.companyname,
       t3.districtname,
       t3.organize_name,
       t2.businessproperty,
       max(t1.summary_type) summary_type,
       sum(t1.trans_num) trans_num,
       sum(t1.index_values)/100 index_values,
       sum(t1.actual_index_values)/100 actual_index_values,       
       t3.organize_id,
       t2.id as businessproperty_id,
       '${bdp.system.bizdate}' as dt
  from(select companyid,districtid,companyname,organize_id, organize_name,districtname,1 as flag
  from hopson_datawoks.dim_company_district_d
 where dt='${bdp.system.bizdate}' 
   and organize_id is not null
   and districtid is not null 
   ) t3
  left join(
select id, businessproperty,1 as flag
  from hopson_datawoks.dim_hilifeandshop_businessproperty_cored_all) t2  on t3.flag=t2.flag
  left join(
select company_id, business_line_type, summary_type, 
    sum(case when summary_type= '增值业务支付' then trans_num when summary_type='增值业务退款' then -trans_num end) trans_num , 
    sum(case when summary_type= '增值业务支付' then index_values when summary_type='增值业务退款' then -index_values end) index_values, 
    sum(case when summary_type= '增值业务支付' then actual_index_values when summary_type='增值业务退款' then -actual_index_values end) actual_index_values
  from hopson_datawoks.dws_platform_info_summary_d
 where (summary_type= '增值业务支付'  or  summary_type ='增值业务退款')      
   and dt= '${bdp.system.bizdate}'
 GROUP BY company_id,  business_line_type,summary_type) t1
  on t1.company_id= t3.companyid and t1.business_line_type=t2.id 
 GROUP BY t3.companyid,
       t3.districtid,
       t3.companyname,
       t3.districtname,
       t3.organize_id,
       t3.organize_name,
       t2.id,
       t2.businessproperty
      ;


   --动态补数
--    INSERT OVERWRITE TABLE hopson_datawoks.app_rp_district_daily_supply_d PARTITION(dt)
--    select t3.companyid,
--        t3.districtid,
--        t3.companyname,
--        t3.districtname,
--        t3.organize_name,
--        t2.businessproperty,
--        t1.summary_type,
--        t1.trans_num,
--        t1.index_values,
--        t1.actual_index_values,
--        t4.dt
--   from(select companyid,districtid,companyname, organize_name,districtname,1 as flag
--   from hopson_datawoks.dim_company_district_d
--  where dt=20200816 
--    and organize_id is not null
--    and districtid is not null 
--    ) t3
--   left join(
-- select id, businessproperty,1 as flag
--   from hopson_datawoks.dim_hilifeandshop_businessproperty_cored_all) t2  on t3.flag=t2.flag
--   left join (select date_id as dt , 1 as flag from hopson_datawoks.dim_time where date_id>= 20200101 and date_id<=20200817) t4 on t4.flag=t3.flag
--   left join(
--       select company_id, districtid, district_name, company_name, business_line_type,summary_type, trans_num, index_values, actual_index_values,dt
--   from hopson_datawoks.dws_platform_info_summary_d
--  where  length(business_line_type)!= 0) t1 on t1.company_id= t3.companyid and t1.business_line_type=t2.id and t1.dt=t4.dt
--  where t3.districtname='华东区域' and t4.dt =20200816 
--  GROUP BY t3.companyid,
--        t3.districtid,
--        t3.companyname,
--        t3.districtname,
--        t3.organize_name,
--        t2.businessproperty,
--        t1.summary_type,
--        t1.trans_num,
--        t1.index_values,
--        t1.actual_index_values,
--        t4.dt;