pyquery 库的使用

 from pyquery import PyQuery as pq
 # 文件勿命名为 pyquery.py，会发生冲突

 # 字符串初始化
 html = '''
 <div id="page">
     <div id="car_test">
         <ul class="menu-list">
             <li class="icon1"><a href="link1.html">科目一</a></li>
             <li class="icon2"><a href="link2.html">科目二</a></li>
             <li class="icon3 subject"><a href="link3.html">科目三</a></li>
             <li class="icon4"><a href="link4.html">科目四</a></li>
             <li class="buy car"><a href="link4.html">买车</a></li>
         </ul>
     </div>
 </div>
 '''
 doc = pq(html)
 print(doc('li'))
 # url初始化
 doc = pq(url='https://www.jiakaobaodian.com/')
 print(doc('title'))
 # 文件初始化
 doc = pq(filename='demo.html')
 print(doc('li'))

 # 基本 CSS 选择器
 doc = pq(html)
 print(doc('#car_test .menu-list li'))
 print(type(doc('#car_test .menu-list li')))
 # 当需要用 class 且名称内容有空格时，”.“表示并列
 print(doc('.menu-list .icon3.subject, .buy.car'))

 # 查找节点
 doc = pq(html)
 items = doc('.menu-list')
 print(type(items))
 print(items)
 # find() 查找节点里的所有子孙节点
 link_list = items.find('a')
 print(type(link_list))
 print(link_list)
 print('\n')
 # children() 查找节点里的子节点
 menu_list = items.children()
 print(menu_list)
 last_li = items.children('.buy.car')
 print(last_li)
 # parent() 父节点
 car_test = items.parent()
 print(type(car_test))
 print(car_test)
 # parents() 祖先节点，此处输出 class 为 page 和 car_test 的两个节点
 parents = items.parents()
 print(parents)
 # siblings() 兄弟节点
 li = doc('.menu-list .icon3.subject')
 print(li.siblings())

 # 遍历
 doc = pq(html)
 menu_list = doc('li').items()
 print(type(menu_list))
 for li in menu_list:
     print(li, type(li))

 # 获取信息
 doc = pq(html)
 a = doc('.icon3.subject a')
 b = doc('.icon4')
 # 获取属性，此处为 class_
 print(a.attr.href)
 print(b.attr.class_)
 # 获取文本，html() 返回节点内所有代码
 print(type(a.text()))
 print(a.text())
 print(b.text())
 print(b.html())

参考资料：静觅 » [Python3网络爬虫开发实战] 4.3-使用pyquery