scrapy之xpath

#xml是网页源码
from scrapy.selector import Selector
s = Selector(text = xml)
# 提取第一个，@表示tag的某个属性
xpath_1 = s.xpath('//dl[@class="xxxxx"]/dd/img/@title').extract_first()
# 提取所有
xpath_2 = s.xpath('//div[@class="xxxxx"]/ul/li/a/@rel').extract()
# 多个条件，text()表示tag的文本
xpath_3 = s.xpath('//div[@class="xxxxx" and @id="yyyyy"]/div[@class="xxxxx"]/p/text()').extract()
# 匹配任意tag
xpath_4 = s.xpath('//div[@class="xxxx"]/dl[@class="xxxxxx"]/*/text()').extract()
# 匹配任意条件的tag
xpath_5 = s.xpath('//div[@class="xxxx"]/dl/*[@class="xxxxxx"]/text()').extract()