batch-processingbatch-scriptcode-freecrawlerdata-collectionfrontendguihtmlinput-parameterslaymanparametersroboticsrpascraperspidervisualvisualizationvisualprogrammingwebwww
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
215 lines
6.9 KiB
215 lines
6.9 KiB
{
|
|
"id": 60,
|
|
"name": "新web采集任务",
|
|
"url": "https://www.jd.com",
|
|
"links": "https://www.jd.com",
|
|
"create_time": "5/21/2023, 4:26:32 PM",
|
|
"containJudge": false,
|
|
"desc": "https://www.jd.com",
|
|
"inputParameters": [
|
|
{
|
|
"id": 0,
|
|
"name": "urlList_0",
|
|
"nodeId": 1,
|
|
"nodeName": "打开网页",
|
|
"value": "https://www.jd.com",
|
|
"desc": "要采集的网址列表，多行以\\n分开",
|
|
"type": "string",
|
|
"exampleValue": "https://www.jd.com"
|
|
}
|
|
],
|
|
"outputParameters": [
|
|
{
|
|
"id": 0,
|
|
"name": "参数1_文本",
|
|
"desc": "",
|
|
"type": "string",
|
|
"exampleValue": "/手机/数码"
|
|
}
|
|
],
|
|
"graph": [
|
|
{
|
|
"index": 0,
|
|
"id": 0,
|
|
"parentId": 0,
|
|
"type": -1,
|
|
"option": 0,
|
|
"title": "root",
|
|
"sequence": [
|
|
1,
|
|
2
|
|
],
|
|
"parameters": {
|
|
"history": 1,
|
|
"tabIndex": 0,
|
|
"useLoop": false,
|
|
"xpath": "",
|
|
"wait": 0
|
|
},
|
|
"isInLoop": false
|
|
},
|
|
{
|
|
"id": 1,
|
|
"index": 1,
|
|
"parentId": 0,
|
|
"type": 0,
|
|
"option": 1,
|
|
"title": "打开网页",
|
|
"sequence": [],
|
|
"isInLoop": false,
|
|
"position": 0,
|
|
"parameters": {
|
|
"useLoop": false,
|
|
"xpath": "",
|
|
"wait": 0,
|
|
"beforeJS": "",
|
|
"beforeJSWaitTime": 0,
|
|
"afterJS": "",
|
|
"afterJSWaitTime": 0,
|
|
"url": "https://www.jd.com",
|
|
"links": "https://www.jd.com",
|
|
"maxWaitTime": 10,
|
|
"scrollType": 0,
|
|
"scrollCount": 0
|
|
}
|
|
},
|
|
{
|
|
"id": 2,
|
|
"index": 2,
|
|
"parentId": 0,
|
|
"type": 1,
|
|
"option": 8,
|
|
"title": "循环",
|
|
"sequence": [
|
|
3
|
|
],
|
|
"isInLoop": false,
|
|
"position": 1,
|
|
"parameters": {
|
|
"history": 4,
|
|
"tabIndex": -1,
|
|
"useLoop": false,
|
|
"xpath": "/html/body/div[5]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div",
|
|
"wait": 0,
|
|
"beforeJS": "",
|
|
"beforeJSWaitTime": 0,
|
|
"afterJS": "",
|
|
"afterJSWaitTime": 0,
|
|
"scrollType": 0,
|
|
"scrollCount": 0,
|
|
"loopType": "1",
|
|
"pathList": "",
|
|
"textList": "",
|
|
"code": "",
|
|
"waitTime": 0,
|
|
"exitCount": 0,
|
|
"historyWait": 2,
|
|
"breakMode": "1",
|
|
"breakCode": "return window.innerHeight > 500",
|
|
"breakCodeWaitTime": 0,
|
|
"allXPaths": [
|
|
"/html/body/div[5]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]/div[1]",
|
|
"//div[contains(., '/手机/数码')]",
|
|
"//DIV[@class='LeftSide_menu_item__SBMWC LeftSide_text_space__2UhbG ']"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"index": 3,
|
|
"parentId": 2,
|
|
"type": 0,
|
|
"option": 3,
|
|
"title": "提取数据",
|
|
"sequence": [],
|
|
"isInLoop": true,
|
|
"position": 0,
|
|
"parameters": {
|
|
"history": 4,
|
|
"tabIndex": -1,
|
|
"useLoop": false,
|
|
"xpath": "",
|
|
"wait": 0,
|
|
"beforeJS": "",
|
|
"beforeJSWaitTime": 0,
|
|
"afterJS": "",
|
|
"afterJSWaitTime": 0,
|
|
"paras": [
|
|
{
|
|
"nodeType": 0,
|
|
"contentType": 0,
|
|
"relative": true,
|
|
"name": "参数1_文本",
|
|
"desc": "",
|
|
"extractType": 0,
|
|
"relativeXPath": "",
|
|
"allXPaths": "",
|
|
"exampleValues": [
|
|
{
|
|
"num": 0,
|
|
"value": "/手机/数码"
|
|
},
|
|
{
|
|
"num": 1,
|
|
"value": "/家用电器"
|
|
},
|
|
{
|
|
"num": 2,
|
|
"value": "/电脑/办公"
|
|
},
|
|
{
|
|
"num": 3,
|
|
"value": "/家纺/家居/厨具"
|
|
},
|
|
{
|
|
"num": 4,
|
|
"value": "/家具/家装/灯具/工业品"
|
|
},
|
|
{
|
|
"num": 5,
|
|
"value": "/内衣/男装/女装/童装"
|
|
},
|
|
{
|
|
"num": 6,
|
|
"value": "/箱包/钟表/珠宝/女鞋"
|
|
},
|
|
{
|
|
"num": 7,
|
|
"value": "/运动/户外/男鞋"
|
|
},
|
|
{
|
|
"num": 8,
|
|
"value": "/汽车用品/车载电器"
|
|
},
|
|
{
|
|
"num": 9,
|
|
"value": "/母婴/洗护喂养"
|
|
},
|
|
{
|
|
"num": 10,
|
|
"value": "/玩具乐器/宠物生活"
|
|
},
|
|
{
|
|
"num": 11,
|
|
"value": "/家庭清洁/个人护理/计生情趣"
|
|
},
|
|
{
|
|
"num": 12,
|
|
"value": "/图书/童书/文学"
|
|
}
|
|
],
|
|
"default": "",
|
|
"beforeJS": "",
|
|
"beforeJSWaitTime": 0,
|
|
"JS": "",
|
|
"JSWaitTime": 0,
|
|
"afterJS": "",
|
|
"afterJSWaitTime": 0,
|
|
"downloadPic": 0
|
|
}
|
|
],
|
|
"loopType": 1
|
|
}
|
|
}
|
|
]
|
|
}
|