from scrapy.selector import Selector htmlText="A1B1<c>C1</c><d>D<e>E</e></d>B2<c>C2</c>" selector=Selector(text=htmlText) s=selector.xpath("//a/preceding-sibling::*") print(s.extract()) s=selector.xpath("//b/preceding-sibling::*[position()=1]") print(s.extract()) s=selector.xpath("//b[position()=2]/preceding-sibling::*") print(s.extract()) ___________________________________________________________________ print(s.extract()) 程序结果： [] ["A1", "<d>D<e>E</e></d>"] ["A1", "B1", "<c>C1</c>", "<d>D<e>E</e></d>"] ["<d>D<e>E</e></d>"]
A、s=selector.xpath("//b[position()=1]/preceding-sibling::*[position()=2]")
B、s=selector.xpath("//b[position=1]/preceding-sibling::*[position=2]")
C、s=selector.xpath("//b[position=2]/preceding-sibling::*[position=1]")
D、s=selector.xpath("//b[position()=2]/preceding-sibling::*[position()=1]")
A.selector
B.xpath("//a/preceding-sibling::*")
C.extract())
D.xpath("//b/preceding-sibling::*[position()=1]")
E.extract())
F.xpath("//b[position()=2]/preceding-sibling::*")
G.extract())
H.extract())
I.xpath("//b[position()=1]/preceding-sibling::*[position()=2]")
J.xpath("//b[position=1]/preceding-sibling::*[position=2]")
K.xpath("//b[position=2]/preceding-sibling::*[position=1]")
L.xpath("//b[position()=2]/preceding-sibling::*[position()=1]")
