基于python爬虫数据处理(详解)

set @address='中国-山东省-聊城市-莘县';select @address

select length('a'),char_length('a'),length('中'),char_length('中')

set @address='中国-山东省-聊城市-莘县';select @address,replace(@address,'-','') as address_1,length(@address) as len_add1,length(replace(@address,'-','')) as len_add2,length(@address)-length(replace(@address,'-','')) as _count

select max(length(com_industry)-length(replace(com_industry,'-',''))) as _max_countfrom etl1_socom_data

set @address='中国-山东省-聊城市-莘县';select substring_index(@address,'-',1) as china,substring_index(substring_index(@address,'-',2),'-',-1) as province,substring_index(substring_index(@address,'-',3),'-',-1) as city,substring_index(@address,'-',-1) as district

case when then when then else 值 end as 字段名select case when 89>101 then '大于' else '小于' end as betl1_socom_data

select a.*,case when com_district like '%业' or com_district like '%织' or com_district like '%育' then null else com_district end as com_district1,case when com_district like '%业' or com_district like '%织' or com_district like '%育' then concat(com_district,'-',com_industry) else com_industry end as com_industry_total,replace(com_addr,'地 址：','') as com_addr1,replace(com_phone,'电 话：','') as com_phone1,replace(com_fax,'传 真：','') as com_fax1,replace(com_mobile,'手机：','') as com_mobile1,replace(com_url,'网址：','') as com_url1,replace(com_email,'邮箱：','') as com_email1,replace(com_contactor,'联系人：','') as com_contactor1,replace(com_emploies_nums,'公司人数：','') as com_emploies_nums1,replace(com_reg_capital,'注册资金：万','') as com_reg_capital1,replace(com_type,'经济类型：','') as com_type1,replace(com_product,'公司产品：','') as com_product1,replace(com_desc,'公司简介：','') as com_desc1from s_socom_data as a

select a.*,case #行业为''的值 置为空when length(com_industry)=0 then null#其他的取第一个-分隔符之前else substring_index(com_industry,'-',1) end as com_industry1,case when length(com_industry)-length(replace(com_industry,'-',''))=0 then null#'交通运输、仓储和邮政业-' 这种值 行业2 也置为nullwhen length(com_industry)-length(replace(com_industry,'-',''))=1 and length(substring_index(com_industry,'-',-1))=0 then nullwhen length(com_industry)-length(replace(com_industry,'-',''))=1 then substring_index(com_industry,'-',-1)else substring_index(substring_index(com_industry,'-',2),'-',-1)end as com_industry2,case when length(com_industry)-length(replace(com_industry,'-',''))<=1 then nullwhen length(com_industry)-length(replace(com_industry,'-',''))=2 then substring_index(com_industry,'-',-1)else substring_index(substring_index(com_industry,'-',3),'-',-1)end as com_industry3,case when length(com_industry)-length(replace(com_industry,'-',''))<=2 then nullelse substring_index(com_industry,'-',-1)end as com_industry4from etl1_socom_data as a

select count(1) from s_socom_dataunion allselect count(1) from etl1_socom_dataunion allselect count(1) from etl2_socom_data

select * from etl2_socom_data where com_district is null and length(com_industry)-length(replace(com_industry,'-',''))=3