#1 //與/
#2 text
#3、extract與extract_first:從selector物件中解出內容
#4、屬性：xpath的屬性加字首@
#4、巢狀查詢
#5、設定預設值
#4、按照屬性查詢
#5、按照屬性模糊查詢
#6、正則表示式
#7、xpath相對路徑
#8、帶變數的xpath

response.selector.css()
response.selector.xpath()
可簡寫為
response.css()
response.xpath()

#1 //與/
response.xpath('//body/a/')#
response.css('div a::text')

 
>>> response.xpath('//body/a') #開頭的//代表從整篇文件中尋找,body之後的/代表body的兒子
[]
>>> response.xpath('//body//a') #開頭的//代表從整篇文件中尋找,body之後的//代表body的子子孫孫
[<Selector xpath='//body//a' data='<a href="image1.html">Name: My image 1 <'>, <Selector xpath='//body//a' data='<a href="image2.html">Name: My image 2 <
 
'>, <Selector xpath='//body//a' data='<a href="
image3.html">Name: My image 3 <'>, <Selector xpath='//body//a' data='<a href="image4.html">Name: My image 4 <'>, <Selector xpath='//body//a' data='<a href="image5.html">Name: My image 5 <'>]

#2 text
>>> response.xpath('
 
//body//a/text()')
>>> response.css('body a::text')

#3、extract與extract_first:從selector物件中解出內容
>>> response.xpath('//div/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('div 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('//div/a/text()').extract_first()
'Name: My image 1 '
>>> response.css('div a::text').extract_first()
'Name: My image 1 '

#4、屬性：xpath的屬性加字首@
>>> response.xpath('//div/a/@href').extract_first()
'image1.html'
>>> response.css('div a::attr(href)').extract_first()
'image1.html'

#4、巢狀查詢
>>> response.xpath('//div').css('a').xpath('@href').extract_first()
'image1.html'

#5、設定預設值
>>> response.xpath('//div[@id="xxx"]').extract_first(default="not found")
'not found'

#4、按照屬性查詢
response.xpath('//div[@id="images"]/a[@href="image3.html"]/text()').extract()
response.css('#images a[@href="image3.html"]/text()').extract()

#5、按照屬性模糊查詢
response.xpath('//a[contains(@href,"image")]/@href').extract()
response.css('a[href*="image"]::attr(href)').extract()

response.xpath('//a[contains(@href,"image")]/img/@src').extract()
response.css('a[href*="imag"] img::attr(src)').extract()

response.xpath('//*[@href="image1.html"]')
response.css('*[href="image1.html"]')

#6、正則表示式
response.xpath('//a/text()').re(r'Name: (.*)')
response.xpath('//a/text()').re_first(r'Name: (.*)')

#7、xpath相對路徑
>>> res=response.xpath('//a[contains(@href,"3")]')[0]
>>> res.xpath('img')
[<Selector xpath='img' data='<img src="image3_thumb.jpg">'>]
>>> res.xpath('./img')
[<Selector xpath='./img' data='<img src="image3_thumb.jpg">'>]
>>> res.xpath('.//img')
[<Selector xpath='.//img' data='<img src="image3_thumb.jpg">'>]
>>> res.xpath('//img') #這就是從頭開始掃描
[<Selector xpath='//img' data='<img src="image1_thumb.jpg">'>, <Selector xpath='//img' data='<img src="image2_thumb.jpg">'>, <Selector xpath='//img' data='<img src="image3_thumb.jpg">'>, <Selector xpa
th='//img' data='<img src="image4_thumb.jpg">'>, <Selector xpath='//img' data='<img src="image5_thumb.jpg">'>]

#8、帶變數的xpath
>>> response.xpath('//div[@id=$xxx]/a/text()',xxx='images').extract_first()
'Name: My image 1 '
>>> response.xpath('//div[count(a)=$yyy]/@id',yyy=5).extract_first() #求有5個a標籤的div的id
'images'

https://docs.scrapy.org/en/latest/topics/selectors.html