时间戳

首页 > 解决方案 > 如何在两个字符串之间进行grep？

html - 如何在两个字符串之间进行grep？

问题描述

我有一个文本文件：

<span class="html-tag">&lt;script&gt;</span></td></tr><tr><td class="line-number" value="1431"></td><td class="line-content">            var awbManifests = {"requestId":"16d1-4451-9b12-f61a87e9cd11","errorMessage":null,"errorCode":null,"success":true,"content":[{"id":"5ec8-444e-9d5b-f7487ce592c2","storeId":"10001","createdDate":1541923869937,"createdBy":"asdf","updatedDate":1541968417296,"updatedBy":"dsa","type":"airwaybill","value":"5468468464568466","logisticTrackingID":"5468468464568466","senderName":"dasdf","senderAddress":"Batuceper","receiverName":"ATIK","receiverAddress":"JL. SRIKATON BARAT\n","manifestList":[{"logisticProviderCode":"asd","blibliAirwayBillNumber":"5468468464568466","status":"DEPARTED FROM TRANSIT [GATEWAY JAKARTA]","timestamp":1541976677000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"RECEIVED AT ORIGIN GATEWAY [GATEWAY JAKARTA]","timestamp":1541976343000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"PROCESSED AT SORTING CENTER [JAKARTA]","timestamp":1541968348000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"RECEIVED AT SORTING CENTER [JAKARTA]","timestamp":1541960930000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"SHIPMENT RECEIVED BY asdf COUNTER OFFICER AT [JAKARTA]","timestamp":1541926728000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]}]}],"pageMetaData":null};</td></tr><tr><td class="line-number" value="1432"></td><td class="line-content">            var ordersTracking = [{"orderItemId":"53000116530","product":null,"shipment":"asdf","airwaybillNumber":"5468468464568466","receiver":null,"receivedDate":null,"relation":null,"status":"Valid","productType":"Regular","eligibleForFeedback":false,"feedback":null,"invalidAWBJiraNumber":"","mismatchAWBJiraNumber":"","isAirwayBillValid":true,"mismatchAirwayBill":false}];

我想从var awbManifests =第一个;符号开始得到结果，所以输出应该只是这样的 JSON 格式：

{"requestId":"16d1-4451-9b12-f61a87e9cd11","errorMessage":null,"errorCode":null,"success":true,"content":[{"id":"5ec8-444e-9d5b-f7487ce592c2","storeId":"10001","createdDate":1541923869937,"createdBy":"asdf","updatedDate":1541968417296,"updatedBy":"dsa","type":"airwaybill","value":"5468468464568466","logisticTrackingID":"5468468464568466","senderName":"dasdf","senderAddress":"Batuceper","receiverName":"ATIK","receiverAddress":"JL. SRIKATON BARAT\n","manifestList":[{"logisticProviderCode":"asd","blibliAirwayBillNumber":"5468468464568466","status":"DEPARTED FROM TRANSIT [GATEWAY JAKARTA]","timestamp":1541976677000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"RECEIVED AT ORIGIN GATEWAY [GATEWAY JAKARTA]","timestamp":1541976343000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"PROCESSED AT SORTING CENTER [JAKARTA]","timestamp":1541968348000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"RECEIVED AT SORTING CENTER [JAKARTA]","timestamp":1541960930000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]},{"logisticProviderCode":"asdf","blibliAirwayBillNumber":"5468468464568466","status":"SHIPMENT RECEIVED BY asdf COUNTER OFFICER AT [JAKARTA]","timestamp":1541926728000,"additionalInfo":[{"label":"Third Party Tracking ID","value":null,"type":"STRING","description":"Third Party Tracking ID"}]}]}],"pageMetaData":null}

到目前为止，我只能这样做，但这个命令并没有 grep 所有的 json 字符串：

grep -o -P '(?<=var awbManifests = ).*(?=pageMetaData)' test.html

我如何解决它 ？

标签： htmljsonbashgrep

解决方案

请不要使用正则表达式来解析 html。如果你问我，你最好使用可以解析 HTML/XML和JSON 的工具，比如。

解析相关的<td>元素节点：

xidel -s input.htm -e '//td[@value="1431"]/following-sibling::td'
 var awbManifests = {"requestId":"16d1-4451-9b12-f61a87e9cd11",[...],"pageMetaData":null};

隔离 JSON：

xidel -s input.htm -e '
  //td[@value="1431"]/substring-before(substring-after(following-sibling::td,"awbManifests = "),";")
'
#or
xidel -s input.htm -e '
  //td[@value="1431"]/extract(following-sibling::td,"awbManifests = (.+);",1)
'
{"requestId":"16d1-4451-9b12-f61a87e9cd11",[...],"pageMetaData":null}

解析 JSON：

xidel -s input.htm -e '
  json(
    //td[@value="1431"]/substring-before(substring-after(following-sibling::td,"awbManifests = "),";")
  )
'
{
  "requestId": "16d1-4451-9b12-f61a87e9cd11",
  "errorMessage": null,
  "errorCode": null,
  "success": true,
  "content": [...],
  "pageMetaData": null
}

推荐阅读