xpath语法

基础命令

hxs = response.xpath('//a')         # 子子孙孙的 【a标签】      # 标签
hxs = response.xpath('//a[2]')      # 无结果                    # 标签
hxs = response.xpath('//a[@id]')    # 所有含有id值的【a标签】   # 标签
hxs = response.xpath('//a/@id')     # 所有a标签的【id值】       # 属性值
hxs = response.xpath('//a[@id="i1"]')   # id值=1的【a标签】     # 标签
hxs = response.xpath('//a[@href="link.html"][@id]')         # 逻辑与+标签
hxs = response.xpath('//a[contains(@href, "link")]')        # 包含+标签
hxs = response.xpath('//a[starts-with(@href, "link")]')     # 开头+标签
hxs = response.xpath('//a[re:test(@id, "id+")]')           # 正则+标签
hxs = response.xpath('//a[re:test(@id, "id+")]/text()')    # 正则+文本
hxs = response.xpath('//a[re:test(@id, "id+")]/@href')     # 正则+属性值
hxs = response.xpath('/html/body/ul/li/a/@href')            # 属性值
hxs = response.xpath('//body/ul/li/a/@href')                # 属性值

# print(hxs)                # xpath对象
# print(hxs.extract())        # 解析所有
# print(hxs.extract_first())  # 解析第一个

循环

ul_list = Selector(response=response).xpath('//body/ul/li')
for item in ul_list:
    print(item.extract())
    # v = item.xpath('./a/span')        # 1
    # v = item.xpath('a/span')          # 2
    v = item.xpath('.//span')             # 3
    print(v.extract())