clear    // 避免变量与用户变量冲突

	tempfile            ///
	         lxh_BlogTitle    ///
	         catID_dta        ///
			 CatIDnew_data    ///
			 catSort          ///
			 Final_data       ///
			 outcome          ///
			 mycovs1          ///
			 


	*------------------------------------------------------------------------*
	***正则表达式抽取网址 标题 分类标签等***
	
	qui{	
		local URL "https://www.lianxh.cn/blogs.html" 

		tempfile  html_text   HTML_text_dta   catID_dta
		
		capture copy `"`URL'"' "`html_text'.txt", replace   
		local times = 0
		while _rc ~= 0 {
			local times = `times' + 1
			sleep 1000
			cap copy `"`URL'"' "`html_text'.txt", replace
			if `times' > 10 {
				disp as error "Internet speeds is too low to get the data"
				exit 601
			}
		}
	}
	
		infix strL v 1-1000 using "`html_text'.txt", clear
		save "`HTML_text_dta'", replace

		keep in 1/1000
        local date: disp %dCYND date("`c(current_date)'","DMY")
        local month = substr("`date'",5,2)
        local day   = substr("`date'",7,2)
        local key   ="`month'"+"/"+"`day'"
        keep if index(v[_n+4], "<span>04/28</span>") 

		*- 抽取原始链接
		local regex    = `"(?<="><a href=")(.*)(?=")"' 
		* 以 「"><a href="」开头，「"」结尾的字符串 
		gen BlogURL     = ustrregexs(0) if ustrregexm(v, `"`regex'"')
		replace BlogURL = "https://www.lianxh.cn" + BlogURL if BlogURL!=""
		
		*- 抽取标题
		local regex   = `"(?<=html">)(.+)(?=</a></h3>)"'
		gen BlogTitle = ustrregexs(0) if ustrregexm(v, `"`regex'"')
		
		*- 抽取分类标签
		local regex = `"(<span>)(\D.*)(?:</span>)"'  
		gen CatName = ustrregexs(2) if ustrregexm(v, `"`regex'"')	
		drop if ustrregexm(CatName, "(data\[item\])")
		keep if (BlogURL !="" | CatName!="")
		replace CatName = CatName[_n+1] if CatName==""
		keep if BlogTitle !=""
		drop v
		drop if ustrregexm(BlogTitle, "(data\[item\])")
		format BlogTitle %-60s
		gen id = _n         // 推文发表时间序号
		save "`lxh_BlogTitle'", replace 	
		rename BlogURL 链接
		rename BlogTitle 名称
		rename CatName 分类


		gen 格式=链接+"++"+名称+"++"+分类+"++"+"连享会"+"++"+"专题"
		keep 名称  链接 分类 格式
		br
		
		*dingwei 名称,c("☝ Stata Journal 来啦！随便看  ")
		*local n=r(row_n)
		*drop in 1/`n'
		*list 名称 if strmatch(分类,"*专题*")