三、Scrapy中选择器用法
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[@id="image"]').css('img::attr(src)').extract()
['image1_thumb.jpg',
'image2_thumb.jpg',
'image3_thumb.jpg',
'image4_thumb.jpg',
'image5_thumb.jpg']
>>> response.xpath('//div[@id="image"]').css('img::attr(src)').extract_first()
'image1_thumb.jpg'
# 默认值，查找不存在的元素，使用默认值
>>> response.xpath('//div[@id="image"]').css('img::attr(data-src)').extract_first(deafult='')
''
>>> response.xpath('//a[contains(@href, "image")]/img/@src').extract()
[u'image1_thumb.jpg',
u'image2_thumb.jpg',
u'image3_thumb.jpg',
u'image4_thumb.jpg',
u'image5_thumb.jpg']
>>> response.css('a[href*=image] img::attr(src)').extract()
[u'image1_thumb.jpg',
u'image2_thumb.jpg',
u'image3_thumb.jpg',
u'image4_thumb.jpg',
u'image5_thumb.jpg']
>>> links = response.xpath('//a[contains(@href, "image")]')
>>> links.extract()
[u'<a href="image1.html">Name: My image 1 <br><img src="image1_thumb.jpg"></a>',
u'<a href="image2.html">Name: My image 2 <br><img src="image2_thumb.jpg"></a>',
u'<a href="image3.html">Name: My image 3 <br><img src="image3_thumb.jpg"></a>',
u'<a href="image4.html">Name: My image 4 <br><img src="image4_thumb.jpg"></a>',
u'<a href="image5.html">Name: My image 5 <br><img src="image5_thumb.jpg"></a>']
>>> for index, link in enumerate(links):
args = (index, link.xpath('@href').extract(), link.xpath('img/@src').extract())
print 'Link number %d points to url %s and image %s' % args
Link number 0 points to url [u'image1.html'] and image [u'image1_thumb.jpg']
Link number 1 points to url [u'image2.html'] and image [u'image2_thumb.jpg']
Link number 2 points to url [u'image3.html'] and image [u'image3_thumb.jpg']
Link number 3 points to url [u'image4.html'] and image [u'image4_thumb.jpg']
Link number 4 points to url [u'image5.html'] and image [u'image5_thumb.jpg']
>>> response.xpath('//a/text()').extract()
['Name:My image 1',
'Name:My image 2',
'Name:My image 3',
'Name:My image 4',
'Name:My image 5']
>>> response.css('a::text').extract()
['Name:My image 1',
'Name:My image 2',
'Name:My image 3',
'Name:My image 4',
'Name:My image 5']
>>> response.xpath('//a[contains(@href, "image")]/@href').extract()
['image1.html',
'image2.html',
'image3.html',
'image4.html',
'image5.html']
>>> response.css('a[href*=image] img::attr(href)').extract()
['image1.html',
'image2.html',
'image3.html',
'image4.html',
'image5.html']
# 使用正则
>>> response.xpath('//a[contains(@href, "image")]/text()').re(r'Name:\s*(.*)')
[u'My image 1',
u'My image 2',
u'My image 3',
u'My image 4',
u'My image 5']
>>> response.xpath('//a[contains(@href, "image")]/text()').re_first(r'Name:\s*(.*)')
'My image 1'
>>> response.xpath('//a/text()').re(r'Name:\s*(.*)')
['My image 1',
'My image 2',
'My image 3',
'My image 4',
'My image 5']
>>> response.xpath('//a/text()').re_first(r'Name:\s*(.*)')
'My image 1'
>>> response.css('a::text').re(r'Name:\s*(.*)')
['My image 1',
'My image 2',
'My image 3',
'My image 4',
'My image 5']
#使用strip()再次处理字符串中的空格,注意跟前面的相比较
re_first('Name:(.*)').strip()
re(r'Name:\s*(.*)')
>>> response.css('a::text').re_first('Name:(.*)').strip()
'My image 1'
# 获取所有的a标签超链接
>>> response.css('a').extract()
['<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>']
>>> response.css('a').extract_first()
'<a href='image1.html'>Name: My image 1 <br /><img src='image1_thumb.jpg' /></a>'
