Scrapy-Xpath 实例

Refer to :https://doc.scrapy.org/en/latest/topics/selectors.html#topics-selectors

>>> from scrapy import Selector
>>> doc = u"""
... <div>
...     <ul>
...         <li class="item-0"><a href="link1.html">first item</a></li>
...         <li class="item-1"><a href="link2.html">second item</a></li>
...         <li class="item-inactive"><a href="link3.html">third item</a></li>
...         <li class="item-1"><a href="link4.html">fourth item</a></li>
...         <li class="item-0"><a href="link5.html">fifth item</a></li>
...     </ul>
... </div>
... """
>>> sel = Selector(text=doc, type="html")
>>> sel.xpath('//li//@href').getall()
['link1.html', 'link2.html', 'link3.html', 'link4.html', 'link5.html']
>>> sel.xpath('//li[re:test(@class, "item-\d$")]//@href').getall()
['link1.html', 'link2.html', 'link4.html', 'link5.html']
>>>

****************************************************************************************

>>> response.xpath("//a/@href").getall()
['image1.html', 'image2.html', 'image3.html', 'image4.html', 'image5.html']

****************************************************************************************

>>> response.xpath('//a[contains(@href, "image")]/text()').re(r'Name:\s*(.*)')
['My image 1',
 'My image 2',
 'My image 3',
 'My image 4',
 'My image 5']

****************************************************************************************

>>> response.xpath('//a[contains(@href, "image")]/text()').re_first(r'Name:\s*(.*)')
'My image 1'
****************************************************************************************
Get and extract_first

>>> response.css('a::attr(href)').get()
'image1.html'
>>> response.css('a::attr(href)').extract_first()
'image1.html'

****************************************************************************************

>>> response.css('a::attr(href)').getall()
['image1.html', 'image2.html', 'image3.html', 'image4.html', 'image5.html']
>>> response.css('a::attr(href)').extract()
['image1.html', 'image2.html', 'image3.html', 'image4.html', 'image5.html']

****************************************************************************************

>>> response.css('a::attr(href)')[0].get()
'image1.html'
>>> response.css('a::attr(href)')[0].extract()
'image1.html'

****************************************************************************************
CSS 模糊匹配class

>>> from scrapy import Selector
>>> sel = Selector(text='<div class="hero shout"><time datetime="2014-07-23 19:00">Special date</time></div>')
>>> sel.css('.shout').xpath('./time/@datetime').getall()
['2014-07-23 19:00']

****************************************************************************************

>>> from scrapy import Selector
>>> sel = Selector(text="""
....:     <ul class="list">
....:         <li>1</li>
....:         <li>2</li>
....:         <li>3</li>
....:     </ul>
....:     <ul class="list">
....:         <li>4</li>
....:         <li>5</li>
....:         <li>6</li>
....:     </ul>""")
>>> xp = lambda x: sel.xpath(x).getall()

>>> xp("//li[1]")
['<li>1</li>', '<li>4</li>']

>>> xp("(//li)[1]")
['<li>1</li>']

****************************************************************************************

['<a href="#">Click here to go to the <strong>Next Page</strong></a>']
>>> sel.xpath("string(//a[1])").getall() # convert it to string
['Click here to go to the Next Page']

>>> sel.xpath("//a[contains(.//text(), 'Next Page')]").getall()
[]

>>> sel.xpath("//a[contains(., 'Next Page')]").getall()
['<a href="#">Click here to go to the <strong>Next Page</strong></a>']

***************************************************************************************

<p class="foo bar-baz">First</p>
<p class="foo">Second</p>
<p class="bar">Third</p>
<p>Fourth</p>

>>> response.xpath('//p[has-class("foo")]')
[<Selector xpath='//p[has-class("foo")]' data='<p class="foo bar-baz">First</p>'>,
 <Selector xpath='//p[has-class("foo")]' data='<p class="foo">Second</p>'>]
>>> response.xpath('//p[has-class("foo", "bar-baz")]')
[<Selector xpath='//p[has-class("foo", "bar-baz")]' data='<p class="foo bar-baz">First</p>'>]
>>> response.xpath('//p[has-class("foo", "bar")]')
[]