官方示例源码
<html>
<head>
<base href='http://example.com/' />
<title>Example website</title>
</head>
<body>
<div id='images'>
<a href='image1.html'>Name: My image 1 <br /><img src='image1_thumb.jpg' /></a>
<a href='image2.html'>Name: My image 2 <br /><img src='image2_thumb.jpg' /></a>
<a href='image3.html'>Name: My image 3 <br /><img src='image3_thumb.jpg' /></a>
<a href='image4.html'>Name: My image 4 <br /><img src='image4_thumb.jpg' /></a>
<a href='image5.html'>Name: My image 5 <br /><img src='image5_thumb.jpg' /></a>
</div>
</body>
</html>
# scrapy shell http://doc.scrapy.org/en/latest/_static/selectors-sample1.html
>>> response.xpath('//title/text()')
[<Selector (text) xpath=//title/text()>]
>>> response.css('title::text')
[<Selector (text) xpath=//title/text()>]
>>> response.css('title::text').extract()
[u'Example website']
>>> response.xpath('//title/text()').extract()
[u'Example website']
>>> response.xpath('//base/@href').extract()
[u'http://example.com/']
>>> response.css('base::attr(href)').extract()
[u'http://example.com/']
>>> response.xpath('//a[contains(@href, "image")]/@href').extract()
[u'image1.html',
u'image2.html',
u'image3.html',
u'image4.html',
u'image5.html']
>>> response.css('a[href*=image]::attr(href)').extract()
[u'image1.html',
u'image2.html',
u'image3.html',
u'image4.html',
u'image5.html']
>>> response.xpath('//a/@href')]').extract()
['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.xpath('//div[@>'<a href='image1.html'>Name: My image 1 <br /><img src='image1_thumb.jpg' /></a>'
相关文章：