AlexMathew/scrapple

View on GitHub
examples/nba.json

Summary

Maintainability
Test Coverage
{
    "project_name": "nba",
    "selector_type": "xpath",
    "scraping": {
        "url": "http://espn.go.com/nba/teams",
        "data": [
            {
                "field": "",
                "selector": "",
                "attr": "",
                "default": "",
                "connector": ""
            }
        ],
        "next": [
            {
                "follow_link": "//*[@class='mod-content']//a[3]",
                "scraping": {
                    "data": [
                        {
                            "field": "team",
                            "selector": "//h2",
                            "attr": "text",
                            "default": "<no_team>",
                            "connector": ""
                        }
                    ],
                    "next": [
                        {
                            "follow_link": "//*[@class='mod-content']/table[1]//tr[@class!='colhead']//a",
                            "scraping": {
                                "data": [
                                    {
                                        "field": "name",
                                        "selector": "//h1",
                                        "attr": "text",
                                        "default": "<no_name>",
                                        "connector": ""
                                    },
                                    {
                                        "field": "headshot_link",
                                        "selector": "//*[@class='main-headshot']/img",
                                        "attr": "src",
                                        "default": "<no_image>",
                                        "connector": ""
                                    },
                                    {
                                        "field": "number & position",
                                        "selector": "//ul[@class='general-info']/li[1]",
                                        "attr": "text",
                                        "default": "<00> #<GFC>",
                                        "connector": ""
                                    }                                               
                                ],
                                "table": [
                                    {
                                        "table_type": "rows",
                                        "header": "//div[@class='player-stats']//table//th",
                                        "prefix": "season_",
                                        "suffix": "",
                                        "selector": "//div[@class='player-stats']//table//tr[1]/td",
                                        "attr": "text",
                                        "default": "",
                                        "connector": ""
                                    },
                                    {
                                        "table_type": "rows",
                                        "header": "//div[@class='player-stats']//table//th",
                                        "prefix": "career_",
                                        "suffix": "",
                                        "selector": "//div[@class='player-stats']//table//tr[@class='career']/td",
                                        "attr": "text",
                                        "default": "",
                                        "connector": ""
                                    }
                                ]
                            }
                        }
                    ]                   
                }
            }
        ]
    }
}