pyquery库

一、pyquery库

PyQuery是一个类似于jQuery的解析网页工具，使用lxml操作xml和html文档，它的语法和jQuery很像。和XPATH，Beautiful Soup比起来，PyQuery更加灵活，提供增加节点的class信息，移除某个节点，提取文本信息等功能，pyquery和BeautifulSoup都是用来解析html的库，但是pyquery的CSS选择器更加强大。

安装：

pip install pyquery

1、URL初始化，通过网址初始化pyquery对象

from pyquery import PyQuery as pq

with open("./html.html","r",encoding="utf-8") as f:
    html = f.read()

# 通过网页初始化pyquery对象
doc = pq(html)
print(type(doc)) #<class 'pyquery.pyquery.PyQuery'>

二、CSS选择器

1、查找元素-子元素

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li><a href="/">首页</a></li>
            <li><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li><a href="/v2.0/doc/app02.html">课程建设</a></li>
            <li><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

# 字符串初始化，得到pyquery对象
doc = pq(html)
items = doc(".nav")
list = items.find("li") 
child = items.children("li") #子元素

2、查找元素-父元素

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li><a href="/">首页</a></li>
            <li><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li><a href="/v2.0/doc/app02.html">课程建设</a></li>
            <li><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

# 查找父元素
doc = pq(html)
items = doc.find(".nav")
parent = items.parent(".collapse")
print(parent)

 3、查找元素-兄弟元素

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

# 查找兄弟元素
doc = pq(html)
li  = doc(".navbar-nav .item-0.active") #选择器后面不加空格，表示并列，即获取item-0又满足active
print(li.siblings()) #获取除了课程建设标签之外的其他兄弟标签

 5、遍历-多个元素

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

from pyquery import PyQuery as pq
doc = pq(html)
element = doc("li").items() #获取多个元素，items()生成一个产生器
print(type(element)) #<class 'generator'>
for ele in element:
    print(ele)

三、获取信息

1、获取标签属性--attr()

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

from pyquery import PyQuery as pq
doc = pq(html)
element = doc(".item-0.active a")
print(element.attr("name")) #result: course

2、获取文本--text()

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

from pyquery import PyQuery as pq
doc = pq(html)
element = doc(".item-0.active a")
print(element.text()) #result：课程建设

3、获取HTML

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

from pyquery import PyQuery as pq
doc = pq(html)
li = doc(".item-0.active")
print(li.html()) #result：<a href="/v2.0/doc/app02.html" name="course">课程建设</a>

四、DOM操作

1、增加/删除属性---addClass、removeClass

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

from pyquery import PyQuery as pq
doc = pq(html)
li = doc(".item-0.active")
print(li) #result：<li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>

remove_attr = li.removeClass("active")
print(remove_attr) #result：<li class="item-0"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>

add_attr = li.addClass("active")
print(add_attr) #result：<li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>

 2、修改标签属性、修改样式---attr、css

html = """
    <div class="collapse navbar-collapse" id="navbar-collapse-2">
        <ul class="nav navbar-nav">
            <li class="item-0"><a href="/">首页</a></li>
            <li class="item-1"><a href="/v2.0/doc/app01.html">系统开发</a></li>
            <li class="item-0 active"><a href="/v2.0/doc/app02.html" name="course">课程建设</a></li>
            <li class="item-1"><a href="/v2.0/doc/app03.html">资源共享</a></li>
            <li class="item-2"><a href="http://www.beian.gov.cn" target="_blank">粤ICP备13085204号-1</a></li>
        </ul>
    </div>"""

from pyquery import PyQuery as pq
doc = pq(html)
li = doc(".item-0.active a")

update_attr = li.attr("name","cour") #若该标签不存在name属性则新增，若存在则修改该属性
print(update_attr) #result：<a href="/v2.0/doc/app02.html" name="cour">课程建设</a>

css_tag = li.css("font-size","14px")
print(css_tag) #result：<a href="/v2.0/doc/app02.html" name="cour" style="font-size: 14px">课程建设</a>

 3、remove()

html_test = """
    <div class="rem">
        www.baidu.com,百度一下
        <p>《大秦赋》</p>
    </div>
"""

from pyquery import PyQuery as pq
doc = pq(html_test)
# 只需要获取p标签上面一句话
element = doc(".rem")
ele = element.find("p").remove() # 找到p标签并移除
print(element.text()) #在获取文本