trailhead

Trailhead 用户信息 Web Scraper 抓取脚本

2018-10-26  本文已影响75人  kwyjibo

Trailhead 用户信息 Web Scraper 抓取脚本

{
    "_id": "trailheadprofile",
    "startUrl": [
        "https://trailhead.salesforce.com/en/me/shaoyuea"
    ],
    "selectors": [
        {
            "id": "u_name",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "h1[data-test-user-name=true]",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "u_badges",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "div[data-test-badges-count]",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "u_points",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "div[data-test-points-count]",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "u_trails",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "div[data-test-trails-count]",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "u_work",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": " h2[data-test-user-work-info]",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "data-test-user-bio",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "p[data-test-user-bio]",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "TrailblazerSince",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_created_at\"] + div > span",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_job_title",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_job_title\"] + div > span",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_job_role",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_job_role\"] + div > span",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_relation",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_relation\"] + div > span",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_company",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_company\"] + div > span",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "linkedin",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_linkedin\"] + div > a",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_twitter",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_twitter\"] + div > a",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_google",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_google\"] + div > a",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "user_id",
            "type": "SelectorText",
            "parentSelectors": [
                "_root"
            ],
            "selector": "label[for=\"user_slug\"] + div ",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "u_rank",
            "type": "SelectorImage",
            "parentSelectors": [
                "_root"
            ],
            "selector": "a[data-test-current-rank] img",
            "multiple": false,
            "delay": 0
        }
    ]
}
上一篇 下一篇

猜你喜欢

热点阅读