pyquery库的使用

pyquery标签选择

获取了所有的img标签（css选择器，你也可以换成不同的class和id）

 

import requests
import re
from pyquery import PyQuery as pq
headers={
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Encoding": "gzip, deflate",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36"
  }
response=requests.get('https://www.zhihu.com/question/35239964/answer/66644148',headers=headers,timeout=9)
doc=pq(response.content)
#css选择器
a=doc('img')#<class 'pyquery.pyquery.PyQuery'>
print(a)

 

---

 

url初始化（通过访问url得到html代码）

有了pyquery，你甚至不需要再使用requests来get网页

from pyquery import PyQuery as pq
headers={
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Encoding": "gzip, deflate",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36"
  }
doc=pq(url='https://www.zhihu.com/question/35239964/answer/66644148',headers=headers)#直接初始化url得到源代码
print(doc('title').text())

---

文件初始化（通过文件得到html代码）

#文件初始化
from pyquery import PyQuery as pq
import requests
# 写文件
# headers={
#     "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
#     "Accept-Encoding": "gzip, deflate",
#     "Accept-Language": "zh-CN,zh;q=0.9",
#     "Upgrade-Insecure-Requests": "1",
#     "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36"
#   }
# result=requests.get('https://www.zhihu.com/question/35239964/answer/66644148',headers=headers)
# # result=pq(url='https://www.zhihu.com/question/35239964/answer/66644148',headers=headers)
# print(type(result))
# with open("zhihu.html",'wb')as f:
#     f.write(result.content)
#读文件
doc=pq(filename='test.html')
print(doc('title'))

css选择器

doc('#content .list li')#得到的是所有的符合这种层级关系的li

---

 

查找元素

子元素

find（查内部的元素）

html=‘.....’
doc=py(html)
a=doc('.content')
b=a.find('img')查找.content内的img标签

children（和find一样）

html=‘.....’
doc=py(html)
a=doc('.content')
b=a.children('img')查找.content内的img标签

父元素

html=‘.....’
doc=py(html)
a=doc('.content')
b=a.parent()查找.content的父元素整体

html=‘.....’
doc=py(html)
a=doc('.content')
b=a.parents()遍历输出.content的所有祖先元素整体

当然也可以加上css选择器

html=‘.....’
doc=py(html)
a=doc('.content')
b=a.parents(‘.wrap’)查找.content的祖先节点中为.wrap的标签

兄弟元素

html=‘.....’
doc=py(html)
a=doc('.content')
b=a.siblings()#查找.content的同级标签，也可以加css选择器

---

 

遍历查找的元素

from pyquery import PyQuery as pq
headers={
    "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8",
    "Accept-Encoding": "gzip, deflate",
    "Accept-Language": "zh-CN,zh;q=0.9",
    "Upgrade-Insecure-Requests": "1",
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36"
  }
doc=pq(url='https://www.zhihu.com/question/35239964/answer/66644148',headers=headers)
a=doc('img').items()#得到可迭代对象
for i in a:
    print(i)

---

 

<img src="data:image/svg+xml;utf8,&lt;svg%20xmlns='http://www.w3.org/2000/svg'%20width='503'%20height='410'&gt;&lt;/svg&gt;" data-rawwidth="503" data-rawheight="410" class="origin_image zh-lightbox-thumb lazy" width="503" data-original="https://pic4.zhimg.com/d8d9743a16e6db3f36b19a3397469b1d_r.jpg" data-actualsrc="https://pic4.zhimg.com/50/d8d9743a16e6db3f36b19a3397469b1d_hd.jpg"/>

加入i是得到的上述的html元素

获取属性:jpgurl=i.attr('data-original')

获取文本：text=i.text()

获取HTML：html=i.html()//获取i里面的html元素

---

 

DOM操作

addclass(添加class)、removeclass（移除class）

attr： .attr('name':'userid')//添加或替换name属性

css： .css('height':'500px')//添加或替换style

 

remove：

http='''
<div class='wrap'>
helloworld
<p>this is p</p>
</div>'''
from pyquery import PyQuery as pq
doc=pq(http)
wrap=doc('.wrap')
print(wrap.text())#helloworld this is p
wrap.find('p').remove()
print(wrap.text())#helloworld