websiteMonitor/spider/browser/js/load_content.js

//执行JS代码
var ret = {}
var tmp = null

if ("{{.TitleCss}}" != "") {//标题
	tmp = document.querySelector("{{.TitleCss}}")
	if (tmp) ret["title"] = tmp.getAttribute("title") || tmp.innerText
}
if ("{{.PublishUnitCss}}" != "") {//采购单位
	tmp = document.querySelector("{{.PublishUnitCss}}")
	if (tmp) ret["publishUnit"] = tmp.getAttribute("title") || tmp.innerText
}
if ("{{.PublishTimeCss}}" != "") {//发布时间
	tmp = document.querySelector("{{.PublishTimeCss}}")
	if (tmp) ret["publishTime"] = tmp.getAttribute("title") || tmp.innerText
}
if ("{{.ContentCss}}" != "") {//正文内容
	tmp = document.querySelector("{{.ContentCss}}")
	if (tmp) {
		ret["content"] = tmp.innerText
		ret["contentHtml"] = tmp.innerHTML
	}
}
//if("{{.AttachCss}}"!=""){//附件
//	tmp = document.querySelectorAll("{{.AttachCss}} a")
//	let attach=[]
//	if(tmp){
//		tmp.forEach((v,i)=>{
//			attach.push([v.getAttribute("title")||v.innerText,v.href])
//		})
//	}
//	ret["attachLinks"]=attach
//}
    
    
ret['attachLinks']=findFileAttachmentTag();
 
function findFileAttachmentTag(container = document.body) {
    const ns = []
    const extensions = ['pdf', 'doc', 'docx', 'xls', 'xlsx', 'zip', 'rar','PDF','DOC','DOCX','XLS','XLSX','ZIP','RAR']
    const extensionRegex = new RegExp('\\.(' + extensions.join('|') + ')$', 'i');
    const aTagList = container.querySelectorAll('a[href]')
    aTagList.forEach((v, i)=>{
      v.setAttribute('target', '_blank');
      const linkText = v.innerText
      const href = v.href
      const filename = v.download || v.filename  || linkText
      if(extensionRegex.test(linkText.toLowerCase()) || extensionRegex.test(href.toLowerCase())){
        ns.push({
          title :linkText,
          href :v.href,
          filename,
        })
      }
    });
    return ns;
}

ret