Xpath解析器

from lxml import etree

html = etree.HTML(doc)

a = html.xpath(‘//*‘)    # 匹配所有的标签

a = html.xpath(‘//head‘)    # 匹配所有的head标签

a = html.xpath(‘//div/a‘)    # 匹配div标签内部所有的儿子a标签
a = html.xpath(‘//body/a‘)    # 没有符合条件的儿子a
a = html.xpath(‘//div//a‘)    # 匹配div标签内容所有的后代a标签
a = html.xpath(‘//boay//a‘)    # 也可以匹配到

a = html.xpath(‘//boay//a[@href="image1.html"]‘)    # 属性查找，获取body内部所有的href=image1.html后代a
a = html.xpath(‘//body//a[@href="image1.html"]/..‘)    # .. 表示查找上一级父标签
a = html.xpath(‘//title[@id="t1"]/..‘)    # ..表示查找上一级父标签
a = html.xpath(‘//body//a[1]‘)    # 从1开始取值
‘‘‘xpath选择器中中括号内部可以放属性也可以放位置数，从1开始‘‘‘

a = html.xpath(‘//body//a[1]/parent::*‘)

a = html.xpath(‘//body//a[@href="image1.html"]/text()‘)
a = html.xpath(‘..body//a/text()‘)    # 获取body内部所有后代a标签内部文本（一次性获取不需要循环）

a = html.xpath(‘//body//a/@href‘)    # 获取body内部所有后代a标签href属性值（一次性获取不需要循环）
a = html.xpath(‘//title/@id)    # 获取title标签id属性值
# 注意从1开始取（不是从0）
a = html.xpath(‘//body//a[2]/@href‘)

a = html.xpath(‘//body//a[@class="li"]‘)    # 写等号就表示等于，不是包含
a = html.xpath(‘//body//a[contains(@class,"li")]/text()‘)    # 包含需要使用关键字contains

a = html.xpath(‘//body//a[contains(@class,"li") or @name="items"]‘)

a = html.xpath(‘//body//a[contains(@class,"li") and @name="items"]/text()‘)

a = html.xpath(‘//a[last()]/@href‘)

a = html.xpath(‘//a[position()<3]/@href‘)    # position()关键字用于定位

a = html.xpath(‘//a[last()-2]/@href‘)

a = html.xpath(‘//a/ancestor::*‘)

a = html.xpath(‘//a/ancestor::div‘)

a = html.xpath(‘//a[1]/attribute::*‘)  # 查找a标签内部所有的属性值

a = html.xpath(‘//a[1]/child::*‘)

a = html.xpath(‘//a[6]/descendant::*‘)

a = html.xpath(‘//a[1]/following::*‘)
a = html.xpath(‘//a[1]/following::*[1]/@href‘)

a = html.xpath(‘//a[1]/following-sibling::*‘)
a = html.xpath(‘//a[1]/following-sibling::a‘)
a = html.xpath(‘//a[1]/following-sibling::*[2]/text()‘)
a = html.xpath(‘//a[1]/following-sibling::*[2]/@href‘)
print(a)

import requests
from bs4 import BeautifulSoup
from lxml import etree

res = requests.get(‘https://shanghai.zbj.com/search/f/‘,
                   params={‘kw‘: ‘python‘}
                   )
x_html = etree.HTML(res.text)
# 分析标签特征并书写xpath语法筛选
# 1.先查找所有的外部div标签
div_list = x_html.xpath(‘/html/body/div[6]/div/div/div[2]/div[5]/div[1]/div‘)  # 利用浏览器自动生成
# div_list = x_html.xpath(‘//div[@class="new-service-wrap"]/div‘)  # 自己写
# 2.循环获取每一个div标签
for div in div_list:
    price = div.xpath(‘.//span[@class="price"]/text()‘)
    company_name = div.xpath(‘./div/div/a[1]/div[1]/p/text()‘)
    order_num = div.xpath(‘./div/div/a[2]/div[2]/div[1]/span[2]/text()‘)
    info = div.xpath(‘./div/div/a[2]/div[2]/div[2]/p/text()‘)
    print(info)
"""
研究./div/div/a[2]/div[2]/div[1]/span[2]表达式作用
"""