Python爬虫之PyQuery使用(六)

Python爬虫之PyQuery使用

 

PyQuery简介

pyquery能够通过选择器精确定位 DOM 树中的目标并进行操作。pyquery相当于jQuery的python实现,可以用于解析HTML网页等。它的语法与jQuery几乎完全相同,对于使用过jQuery的人来说很熟悉,也很好上手。

初始化

有 4 种方法可以进行初始化:
可以通过传入 字符串、lxml、文件 或者 url 来使用PyQuery

from pyquery import PyQuery as pq
from lxml import etree

d = pq("<html></html>")#传入字符串
d = pq(etree.fromstring("<html></html>"))#传入lxml
d = pq(url='http://baidu.com/') #传入url
d = pq(filename=path_to_html_file) #传入文件

  

基本CSS选择器

html='''
<html>
 <body>
  <ul class="mh-col">
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-1"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E6%AD%8C%E6%89%8B%E9%AB%98%E7%A9%BA%E6%8B%8DMV%E5%9D%A0%E4%BA%A1&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     歌手高空拍MV坠亡
    </a>
    <span class="mh-ico-up">
    </span>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-2"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E4%BD%9B%E7%A5%96%E6%9C%B1%E9%BE%99%E5%B9%BF%E9%87%91%E5%A9%9A&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D&fr=hao_360so_history_b" target="_blank">
     佛祖朱龙广金婚
    </a>
    <span class="mh-ico-down">
    </span>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-3"}' href="http://www.so.com/link?url=http%3A%2F%2Fbaike.so.com%2Fzt%2Fzufangfangpian.html%3Fsrc%3Dreci&q=%E5%91%A8%E6%9D%B0%E4%BC%A6%E7%9A%84%E6%AD%8C&ts=1540365398&t=c6890eee0e669832ca96d5223582d6e" target="_blank">
     常见租房陷阱
    </a>
    <span class="mh-ico-up">
    </span>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-4"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E9%9D%B3%E4%B8%9C%E5%9B%9E%E5%BA%94%E5%8F%91%E9%94%99%E8%AF%97%E8%AF%8D&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     靳东回应发错诗词
    </a>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-5"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E7%85%A4%E8%80%81%E6%9D%BF%E4%BB%AC%E7%9A%84%E5%BD%B1%E8%A7%86%E6%B1%9F%E6%B9%96&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     煤老板们的影视江湖
    </a>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-6"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=1024%E7%A8%8B%E5%BA%8F%E5%91%98%E8%8A%82&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     1024程序员节
    </a>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-7"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E7%BE%8E%E7%9A%84%E5%90%88%E5%B9%B6%E5%B0%8F%E5%A4%A9%E9%B9%85&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     美的合并小天鹅
    </a>
   </li>
   <li class="g-ellipsis">
    <a class="g-a-noline" data-md='{"b":"list","p":"1-8"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E4%BA%AC%E6%98%86%E9%AB%98%E9%80%9F4%E8%BD%A6%E7%9B%B8%E6%92%9E&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     京昆高速4车相撞
    </a>
   </li>

  </ul>
 </body>
</html>
'''

from pyquery import PyQuery as pq
doc = pq(html)

# 获取所有a标签
print(doc('body .mh-col li a'))



注意:
类名用.
id用#
标签用标签名

另外选择的是具有层级关系,从左到右,不是直接的父子的关系。

运行结果如下:

<a class="g-a-noline" data-md="{"b":"list","p":"1-1"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E6%AD%8C%E6%89%8B%E9%AB%98%E7%A9%BA%E6%8B%8DMV%E5%9D%A0%E4%BA%A1&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     歌手高空拍MV坠亡
    </a>
    <a class="g-a-noline" data-md="{"b":"list","p":"1-2"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E4%BD%9B%E7%A5%96%E6%9C%B1%E9%BE%99%E5%B9%BF%E9%87%91%E5%A9%9A&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D&fr=hao_360so_history_b" target="_blank">
     佛祖朱龙广金婚
    </a>
    <a class="g-a-noline" data-md="{"b":"list","p":"1-3"}" href="http://www.so.com/link?url=http%3A%2F%2Fbaike.so.com%2Fzt%2Fzufangfangpian.html%3Fsrc%3Dreci&q=%E5%91%A8%E6%9D%B0%E4%BC%A6%E7%9A%84%E6%AD%8C&ts=1540365398&t=c6890eee0e669832ca96d5223582d6e" target="_blank">
     常见租房陷阱
    </a>
    <a class="g-a-noline" data-md="{"b":"list","p":"1-4"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E9%9D%B3%E4%B8%9C%E5%9B%9E%E5%BA%94%E5%8F%91%E9%94%99%E8%AF%97%E8%AF%8D&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     靳东回应发错诗词
    </a>
   <a class="g-a-noline" data-md="{"b":"list","p":"1-5"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E7%85%A4%E8%80%81%E6%9D%BF%E4%BB%AC%E7%9A%84%E5%BD%B1%E8%A7%86%E6%B1%9F%E6%B9%96&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     煤老板们的影视江湖
    </a>
   <a class="g-a-noline" data-md="{"b":"list","p":"1-6"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=1024%E7%A8%8B%E5%BA%8F%E5%91%98%E8%8A%82&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     1024程序员节
    </a>
   <a class="g-a-noline" data-md="{"b":"list","p":"1-7"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E7%BE%8E%E7%9A%84%E5%90%88%E5%B9%B6%E5%B0%8F%E5%A4%A9%E9%B9%85&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     美的合并小天鹅
    </a>
   <a class="g-a-noline" data-md="{"b":"list","p":"1-8"}" href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E4%BA%AC%E6%98%86%E9%AB%98%E9%80%9F4%E8%BD%A6%E7%9B%B8%E6%92%9E&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     京昆高速4车相撞
    </a>
   

  

操作

html='''
<html>
 <body>
  <ul class="mh-col">
   <li class="g-ellipsis1">
    <a class="g-a-noline1" data-md='{"b":"list","p":"1-1"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E6%AD%8C%E6%89%8B%E9%AB%98%E7%A9%BA%E6%8B%8DMV%E5%9D%A0%E4%BA%A1&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     歌手高空拍MV坠亡
    </a>
    <span class="mh-ico-up">
    </span>
   </li>
   <li class="g-ellipsis2">
    <a class="g-a-noline2" data-md='{"b":"list","p":"1-2"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E4%BD%9B%E7%A5%96%E6%9C%B1%E9%BE%99%E5%B9%BF%E9%87%91%E5%A9%9A&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D&fr=hao_360so_history_b" target="_blank">
     佛祖朱龙广金婚
    </a>
    <span class="mh-ico-down">
    </span>
   </li>
   <li class="g-ellipsis3">
    <a class="g-a-noline3" data-md='{"b":"list","p":"1-3"}' href="http://www.so.com/link?url=http%3A%2F%2Fbaike.so.com%2Fzt%2Fzufangfangpian.html%3Fsrc%3Dreci&q=%E5%91%A8%E6%9D%B0%E4%BC%A6%E7%9A%84%E6%AD%8C&ts=1540365398&t=c6890eee0e669832ca96d5223582d6e" target="_blank">
     常见租房陷阱
    </a>
    <span class="mh-ico-up">
    </span>
   </li>
   <li class="g-ellipsis4">
    <a class="g-a-noline4" data-md='{"b":"list","p":"1-4"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E9%9D%B3%E4%B8%9C%E5%9B%9E%E5%BA%94%E5%8F%91%E9%94%99%E8%AF%97%E8%AF%8D&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     靳东回应发错诗词
    </a>
   </li>
   <li class="g-ellipsis5">
    <a class="g-a-noline5" data-md='{"b":"list","p":"1-5"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E7%85%A4%E8%80%81%E6%9D%BF%E4%BB%AC%E7%9A%84%E5%BD%B1%E8%A7%86%E6%B1%9F%E6%B9%96&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     煤老板们的影视江湖
    </a>
   </li>
   <li class="g-ellipsis6">
    <a class="g-a-noline6" data-md='{"b":"list","p":"1-6"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=1024%E7%A8%8B%E5%BA%8F%E5%91%98%E8%8A%82&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     1024程序员节
    </a>
   </li>
   <li class="g-ellipsis7">
    <a class="g-a-noline7" data-md='{"b":"list","p":"1-7"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E7%BE%8E%E7%9A%84%E5%90%88%E5%B9%B6%E5%B0%8F%E5%A4%A9%E9%B9%85&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     美的合并小天鹅
    </a>
   </li>
   <li class="g-ellipsis8">
    <a class="g-a-noline8" data-md='{"b":"list","p":"1-8"}' href="https://www.so.com/s?ie=utf-8&src=know_side_nlp_sohot&q=%E4%BA%AC%E6%98%86%E9%AB%98%E9%80%9F4%E8%BD%A6%E7%9B%B8%E6%92%9E&ob_ext=%7B%22rsv_cq%22%3A%22%5Cu5468%5Cu6770%5Cu4f26%5Cu7684%5Cu6b4c%22%2C%22rt%22%3A%22%5Cu5b9e%5Cu65f6%5Cu70ed%5Cu641c%22%2C%22rclken%22%3Anull%7D" target="_blank">
     <p>新闻</p>
     京昆高速4车相撞
    </a>
   </li>

  </ul>
 </body>
</html>
'''
from pyquery import PyQuery as pq
doc = pq(html)
items = doc('.mh-col')



#.find():查找嵌套元素 alist = items.find('li a') print(alist)
#查找所有子元素 alist2 = items.children() print(alist2) #查找指定的子元素 alist3 = items.children('.g-ellipsis1')
print(alist2)


#查找父元素
#注意:一个元素只有一个父元素
body = items.parent()
print(body)


#查找祖先元素
content = items.parents()
print(content)

#查找兄弟元素
li = doc('.mh-col .g-ellipsis1')
print(li.siblings())

#遍历 单个元素
#遍历所有的a标签
alist =doc('.mh-col li a').items()
  for a in alist: print(a)

  

获取信息

获取属性
a =doc('.mh-col li .g-a-noline8')
print(a.attr['href'])
print(a.attr.href)


获取文本
a =doc('.mh-col li .g-a-noline8')
print(a.text())

获取HTML
a =doc('.mh-col li .g-a-noline8')
print(a.html())

 

简单的DOM操作

#addClass、removerClass
#修改类名 a =doc('.mh-col li .g-a-noline8') print(a) a.removeClass('g-a-noline8') print(a) a.addClass('g-a-noline8') print(a) #attr、css
#修改属性和样式 a =doc('.mh-col li .g-a-noline8') print(a) a.attr('name','link') print(a) a.css('font-size','14px') print(a)
#remove
#删除标签
li = doc('.mh-col .g-ellipsis8')
print(li)
li.find('a').remove()
print(li)

  

更多的DOM操作:https://pyquery.readthedocs.io/en/latest/api.html

原文地址:https://www.cnblogs.com/-wenli/p/9881604.html