2

この質問への回答を私の問題に適応させようとしましたが、うまくいきませんでした。

html コードの例を次に示します。

<div id="provider-region-addresses">
<h3>Contact details</h3>
<h2 class="toggler nohide">Auckland</h2>
    <dl class="clear">
        <dt>More information</dt>
            <dd>North Shore Hospital</dd><dt>Physical address</dt>
                <dd>124 Shakespeare Rd, Takapuna, Auckland 0620</dd><dt>Postal address</dt>
                <dd>Private Bag 93503, Takapuna, Auckland 0740</dd><dt>Postcode</dt>
                <dd>0740</dd><dt>District/town</dt>

                <dd>
                North Shore, Takapuna</dd><dt>Region</dt>
                <dd>Auckland</dd><dt>Phone</dt>
                <dd>(09) 486 8996</dd><dt>Fax</dt>
                <dd>(09) 486 8342</dd><dt>Website</dt>
                <dd><a target="_blank" href="http://www.healthpoint.co.nz/default,61031.sm">http://www.healthpoint.co.nz/default,61031...</a></dd>
    </dl>
    <h2 class="toggler nohide">Auckland</h2>
    <dl class="clear">
        <dt>Physical address</dt>
                <dd>Helensville</dd><dt>Postal address</dt>
                <dd>PO Box 13, Helensville 0840</dd><dt>Postcode</dt>
                <dd>0840</dd><dt>District/town</dt>

                <dd>
                Rodney, Helensville</dd><dt>Region</dt>
                <dd>Auckland</dd><dt>Phone</dt>
                <dd>(09) 420 9450</dd><dt>Fax</dt>
                <dd>(09) 420 7050</dd><dt>Website</dt>
                <dd><a target="_blank" href="http://www.healthpoint.co.nz/default,61031.sm">http://www.healthpoint.co.nz/default,61031...</a></dd>
    </dl>
    <h2 class="toggler nohide">Auckland</h2>
    <dl class="clear">
        <dt>Physical address</dt>
                <dd>Warkworth</dd><dt>Postal address</dt>
                <dd>PO Box 505, Warkworth 0941</dd><dt>Postcode</dt>
                <dd>0941</dd><dt>District/town</dt>

                <dd>
                Rodney, Warkworth</dd><dt>Region</dt>
                <dd>Auckland</dd><dt>Phone</dt>
                <dd>(09) 422 2700</dd><dt>Fax</dt>
                <dd>(09) 422 2709</dd><dt>Website</dt>
                <dd><a target="_blank" href="http://www.healthpoint.co.nz/default,61031.sm">http://www.healthpoint.co.nz/default,61031...</a></dd>
    </dl>
    <h2 class="toggler nohide">Auckland</h2>
    <dl class="clear">
        <dt>More information</dt>
            <dd>Waitakere Hospital</dd><dt>Physical address</dt>
                <dd>55-75 Lincoln Rd, Henderson, Auckland 0610</dd><dt>Postal address</dt>
                <dd>Private Bag 93115, Henderson, Auckland 0650</dd><dt>Postcode</dt>
                <dd>0650</dd><dt>District/town</dt>

                <dd>
                Waitakere, Henderson</dd><dt>Region</dt>
                <dd>Auckland</dd><dt>Phone</dt>
                <dd>(09) 839 0000</dd><dt>Fax</dt>
                <dd>(09) 837 6634</dd><dt>Website</dt>
                <dd><a target="_blank" href="http://www.healthpoint.co.nz/default,61031.sm">http://www.healthpoint.co.nz/default,61031...</a></dd>
    </dl>
    <h2 class="toggler nohide">Auckland</h2>
    <dl class="clear">
        <dt>More information</dt>
            <dd>Hibiscus Coast Community Health Centre</dd><dt>Physical address</dt>
                <dd>136 Whangaparaoa Rd, Red Beach 0932</dd><dt>Postcode</dt>
                <dd>0932</dd><dt>District/town</dt>

                <dd>
                Rodney, Red Beach</dd><dt>Region</dt>
                <dd>Auckland</dd><dt>Phone</dt>
                <dd>(09) 427 0300</dd><dt>Fax</dt>
                <dd>(09) 427 0391</dd><dt>Website</dt>
                <dd><a target="_blank" href="http://www.healthpoint.co.nz/default,61031.sm">http://www.healthpoint.co.nz/default,61031...</a></dd>
    </dl>
    </div>

もう一度検索

これが私のクモです。

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from webhealth.items1 import WebhealthItem1

class WebhealthSpider(BaseSpider):

name = "webhealth_content1"

download_delay = 5

allowed_domains = ["webhealth.co.nz"]
start_urls = [
    "http://auckland.webhealth.co.nz/provider/service/view/914136/"
    ]

def parse(self, response):
    hxs = HtmlXPathSelector(response)
    results = hxs.select('//*[@id="content"]/div[1]')
    items1 = []
    for result in results:
        item = WebhealthItem1()
        item['url'] = result.select('//dl/a/@href').extract()
        item['practice'] = result.select('//h1/text()').extract()
        item['hours'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Contact hours")]/following-sibling::dd[1]/text()').extract())
        item['more_hours'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"More information")]/following-sibling::dd[1]/text()').extract())
        item['physical_address'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Physical address")]/following-sibling::dd[1]/text()').extract())
        item['postal_address'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Postal address")]/following-sibling::dd[1]/text()').extract())
        item['postcode'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Postcode")]/following-sibling::dd[1]/text()').extract())
        item['district_town'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"District/town")]/following-sibling::dd[1]/text()').extract())
        item['region'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Region")]/following-sibling::dd[1]/text()').extract())
        item['phone'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Phone")]/following-sibling::dd[1]/text()').extract())
        item['website'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Website")]/following-sibling::dd[1]/a/@href').extract())
        item['email'] = map(unicode.strip, result.select('//div/dl/dt[contains(text(),"Email")]/following-sibling::dd[1]/a/text()').extract())
        items1.append(item)
    return items1

//h1/text()ここから、名前フィールドに対応する値を使用して、リスト項目を個別の行に解析するにはどうすればよいですか? 現在、各 Xpath アイテムのリストをすべて 1 つのセルに取得しています。Xpathを宣言する方法と関係がありますか?

ありがとう

4

1 に答える 1

4

まず、あなたはresults = hxs.select('//*[@id="content"]/div[1]')そう使っています

    results = hxs.select('//*[@id="content"]/div[1]')
    for result in results:
        ...

divの最初の子divである 1 つだけでループします<div id="content" class="clear">

あなたが必要とするのは、<dl class="clear">...</dl>これ内のすべてをループすることです//*[@id="content"]/div[1]（おそらく、で維持する方が簡単でしょう//*[@id="content"]/div[@class="content"]）

        results = hxs.select('//*[@id="content"]/div[@class="content"]/div/dl')

次に、各ループ反復で、絶対 XPath 式を使用しています ( //div...)

result.select('//div/dl/dt[contains(text(), "...")]/following-sibling::dd[1]/text()')

これにより、ドキュメント ルート ノードから始まるテキスト コンテンツに一致する後続のすべて が選択されます。dddt

詳細については、 Scrapyドキュメントのこのセクションを参照してください。

相対 XPath 式を使用する必要resultがありdlます。dt[contains(text(),"Contact hours")]/following-sibling::dd[1]/text()./dt[contains(text(), "Contact hours")]/following-sibling::dd[1]/text()

ただし、「practice」フィールドでは絶対 XPath 式を引き続き使用//h1/text()できますが、変数practiceを一度設定して、各WebhealthItem1()インスタンスで使用することもできます。

        ...
        practice = hxs.select('//h1/text()').extract()
        for result in results:
            item = WebhealthItem1()
            ...
            item['practice'] = practice

これらの変更により、スパイダーは次のようになります。

from scrapy.spider import BaseSpider
from scrapy.selector import HtmlXPathSelector
from webhealth.items1 import WebhealthItem1

class WebhealthSpider(BaseSpider):

    name = "webhealth_content1"

    download_delay = 5

    allowed_domains = ["webhealth.co.nz"]
    start_urls = [
        "http://auckland.webhealth.co.nz/provider/service/view/914136/"
        ]

    def parse(self, response):
        hxs = HtmlXPathSelector(response)

        practice = hxs.select('//h1/text()').extract()
        items1 = []

        results = hxs.select('//*[@id="content"]/div[@class="content"]/div/dl')
        for result in results:
            item = WebhealthItem1()
            #item['url'] = result.select('//dl/a/@href').extract()
            item['practice'] = practice
            item['hours'] = map(unicode.strip,
                result.select('dt[contains(.," Contact hours")]/following-sibling::dd[1]/text()').extract())
            item['more_hours'] = map(unicode.strip,
                result.select('dt[contains(., "More information")]/following-sibling::dd[1]/text()').extract())
            item['physical_address'] = map(unicode.strip,
                result.select('dt[contains(., "Physical address")]/following-sibling::dd[1]/text()').extract())
            item['postal_address'] = map(unicode.strip,
                result.select('dt[contains(., "Postal address")]/following-sibling::dd[1]/text()').extract())
            item['postcode'] = map(unicode.strip,
                result.select('dt[contains(., "Postcode")]/following-sibling::dd[1]/text()').extract())
            item['district_town'] = map(unicode.strip,
                result.select('dt[contains(., "District/town")]/following-sibling::dd[1]/text()').extract())
            item['region'] = map(unicode.strip,
                result.select('dt[contains(., "Region")]/following-sibling::dd[1]/text()').extract())
            item['phone'] = map(unicode.strip,
                result.select('dt[contains(., "Phone")]/following-sibling::dd[1]/text()').extract())
            item['website'] = map(unicode.strip,
                result.select('dt[contains(., "Website")]/following-sibling::dd[1]/a/@href').extract())
            item['email'] = map(unicode.strip,
                result.select('dt[contains(., "Email")]/following-sibling::dd[1]/a/text()').extract())
            items1.append(item)
        return items1

このコードを使用して Cloud9 IDE プロジェクトも作成しました。https://c9.io/redapple/so_19309960で遊ぶことができます。

于 2013-10-11T07:06:15.817 に答える