webscraper.io scraper for search results from the Hansard website

hansard_scraper.json

{
    "_id": "hansard",
    "startUrl": [
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22affected%20by%20the%20bill%22&partial=False&page=[1-123]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22consented%20to%20place%22&partial=False&page=[1-33]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22have%20it%20in%20command%20from%22&partial=False&page=[1-35]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22Queen%27s%20consent%20signified%22&partial=False&page=[1-16]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22Prince%20of%20Wales%27s%20consent%20signified%22&partial=False&page=[1-4]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22Queen%27s%20Consent%2C%20on%20behalf%20of%20the%20Crown%2C%20signified%22&partial=False&page=[1-23]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22Prince%20of%20Wales%27s%20consent%2C%20on%20behalf%20of%20the%20Duchy%20of%20Cornwall%2C%20signified%22&partial=False&page=[1-3]",
        "https://hansard.parliament.uk/search/Contributions?startDate=1952-02-06&endDate=2020-11-27&searchTerm=%22consent%20having%20been%20signified%22&partial=False&page=1"
    ],
    "selectors": [
        {
            "id": "row",
            "type": "SelectorElement",
            "parentSelectors": [
                "_root"
            ],
            "selector": ".search-results .card",
            "multiple": true,
            "delay": 0
        },
        {
            "id": "title",
            "type": "SelectorText",
            "parentSelectors": [
                "row"
            ],
            "selector": ".primary-info",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "date",
            "type": "SelectorText",
            "parentSelectors": [
                "row"
            ],
            "selector": ".tertiary-info",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "text",
            "type": "SelectorText",
            "parentSelectors": [
                "row"
            ],
            "selector": ".text",
            "multiple": false,
            "regex": "",
            "delay": 0
        },
        {
            "id": "link",
            "type": "SelectorElementAttribute",
            "parentSelectors": [
                "row"
            ],
            "selector": "_parent_",
            "multiple": false,
            "extractAttribute": "href",
            "delay": 0
        }
    ]
}