Python网络爬虫神器PyQuery的使用方法

#!/usr/bin/env python 
# -*- coding: utf-8 -*-

import requests
from pyquery import PyQuery as pq


url = 'http://www.136book.com/huaqiangu/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36'
                  ' (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'
}

# 请求网页链接 获取页面源码
r = requests.get(url, headers=headers).text
doc = pq(r)
# 获取网页的全部章节链接 这里去掉了前面的最新章节部分 直接从第一章开始 
# div#book_detail:nth-child(2) 选取的是第二个div的内容
links = doc('div#book_detail:nth-child(2) li a').items()

for link in links:

    download_url = link.attr('href')
    # 请求每个章节
    download_page = requests.get(download_url, headers=headers).text
    # 获取每一章节的源码
    doc = pq(download_page)
    # 获取每一章小说的内容
    contents = doc('div#content').text()
    with open('花千骨.txt', 'a+', encoding='utf8') as f:
        f.write(link.text()+"

")
        f.write(contents+"

")
print("写入文件完成!请查看")

1.安装方法

pip install pyquery

2.引用方法

from pyquery import PyQuery as pq

3.简介

　pyquery 是类型jquery 的一个专供python使用的html解析的库，使用方法类似bs4。

4.使用方法

　　4.1 初始化方法：

from pyquery import PyQuery as pq
doc =pq(html) #解析html字符串
doc =pq("http://news.baidu.com/") #解析网页
doc =pq("./a.html") #解析html 文本

      4.2 基本CSS选择器

from pyquery import PyQuery as pq
html = '''
    <div id="wrap">
        <ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''
doc = pq(html)
print doc("#wrap .s_from link")

　　运行结果：

<link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>

　　#是查找id的标签  .是查找class 的标签  link 是查找link 标签 中间的空格表示里层

　　4.3 查找子元素

from pyquery import PyQuery as pq
html = '''
    <div id="wrap">
        <ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''
#查找子元素
doc = pq(html)
items=doc("#wrap")
print(items)
print("类型为:%s"%type(items))
link = items.find('.s_from')
print(link)
link = items.children()
print(link)

　　运行结果：

<div id="wrap">
        <ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
类型为:<class 'pyquery.pyquery.PyQuery'>
<ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    
<ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>

　　根据运行结果可以发现返回结果类型为pyquery，并且find方法和children 方法都可以获取里层标签

　 4.4查找父元素

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
items=doc(".s_from")
print(items)
#查找父元素
parent_href=items.parent()
print(parent_href)

　　运行结果:

<ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    
<div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link href="http://asda.com">asdadasdad12312</link>
            <link href="http://asda1.com">asdadasdad12312</link>
            <link href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>

　　parent可以查找出外层标签包括的内容，与之类似的还有parents,可以获取所有外层节点

　　4.5 查找兄弟元素

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com">asdadasdad12312</link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
items=doc("link.active1.a123")
print(items)
#查找兄弟元素
siblings_href=items.siblings()
print(siblings_href)

　　运行结果：

<link class="active1 a123" href="http://asda.com">asdadasdad12312</link>
            
<link class="active2" href="http://asda1.com">asdadasdad12312</link>
            <link class="movie1" href="http://asda2.com">asdadasdad12312</link>

　　根据运行结果可以看出，siblings 返回了同级的其他标签

　　结论：子元素查找，父元素查找，兄弟元素查找，这些方法返回的结果类型都是pyquery类型，可以针对结果再次进行选择

　　4.6 遍历查找结果

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com">asdadasdad12312</link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link").items()
for it in its:
    print(it)

　　运行结果：

<link class="active1 a123" href="http://asda.com">asdadasdad12312</link>
            
<link class="active2" href="http://asda1.com">asdadasdad12312</link>
            
<link class="movie1" href="http://asda2.com">asdadasdad12312</link>

　　4.7获取属性信息

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com">asdadasdad12312</link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link").items()
for it in its:
    print(it.attr('href'))
    print(it.attr.href)

　　运行结果：

http://asda.com
http://asda.com
http://asda1.com
http://asda1.com
http://asda2.com
http://asda2.com

　　4.8 获取文本

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com">asdadasdad12312</link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link").items()
for it in its:
    print(it.text())

　　运行结果

asdadasdad12312
asdadasdad12312
asdadasdad12312

　　4.9 获取 HTML信息

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com"><a>asdadasdad12312</a></link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link").items()
for it in its:
    print(it.html())

　　运行结果：

<a>asdadasdad12312</a>
asdadasdad12312
asdadasdad12312

5.常用DOM操作

　　5.1 addClass removeClass

　　添加，移除class标签

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com"><a>asdadasdad12312</a></link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link").items()
for it in its:
    print("添加:%s"%it.addClass('active1'))
    print("移除:%s"%it.removeClass('active1'))

　　运行结果

添加:<link class="active1 a123" href="http://asda.com"><a>asdadasdad12312</a></link>
            
移除:<link class="a123" href="http://asda.com"><a>asdadasdad12312</a></link>
            
添加:<link class="active2 active1" href="http://asda1.com">asdadasdad12312</link>
            
移除:<link class="active2" href="http://asda1.com">asdadasdad12312</link>
            
添加:<link class="movie1 active1" href="http://asda2.com">asdadasdad12312</link>
        
移除:<link class="movie1" href="http://asda2.com">asdadasdad12312</link>

　　需要注意的是已经存在的class标签不会继续添加

　　5.2 attr css

　　attr 为获取/修改属性 css 添加style属性

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com"><a>asdadasdad12312</a></link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link").items()
for it in its:
    print("修改:%s"%it.attr('class','active'))
    print("添加:%s"%it.css('font-size','14px'))

　　运行结果

C:Python27python.exe D:/test_his/test_re_1.py
修改:<link class="active" href="http://asda.com"><a>asdadasdad12312</a></link>
            
添加:<link class="active" href="http://asda.com" style="font-size: 14px"><a>asdadasdad12312</a></link>
            
修改:<link class="active" href="http://asda1.com">asdadasdad12312</link>
            
添加:<link class="active" href="http://asda1.com" style="font-size: 14px">asdadasdad12312</link>
            
修改:<link class="active" href="http://asda2.com">asdadasdad12312</link>
        
添加:<link class="active" href="http://asda2.com" style="font-size: 14px">asdadasdad12312</link>

　　attr css操作直接修改对象的

　　5.3 remove

　　remove 移除标签

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com"><a>asdadasdad12312</a></link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("div")
print('移除前获取文本结果:
%s'%its.text())
it=its.remove('ul')
print('移除后获取文本结果:
%s'%it.text())

　　运行结果

移除前获取文本结果:
hello nihao
asdasd
asdadasdad12312
asdadasdad12312
asdadasdad12312
移除后获取文本结果:
hello nihao

　　其他DOM方法参考：

　　http://pyquery.readthedocs.io/en/latest/api.html

6.伪类选择器

from pyquery import PyQuery as pq
html = '''
    <div href="wrap">
        hello nihao
        <ul class="s_from">
            asdasd
            <link class='active1 a123' href="http://asda.com"><a>helloasdadasdad12312</a></link>
            <link class='active2' href="http://asda1.com">asdadasdad12312</link>
            <link class='movie1' href="http://asda2.com">asdadasdad12312</link>
        </ul>
    </div>
'''

doc = pq(html)
its=doc("link:first-child")
print('第一个标签:%s'%its)
its=doc("link:last-child")
print('最后一个标签:%s'%its)
its=doc("link:nth-child(2)")
print('第二个标签:%s'%its)
its=doc("link:gt(0)") #从零开始
print("获取0以后的标签:%s"%its)
its=doc("link:nth-child(2n-1)")
print("获取奇数标签:%s"%its)
its=doc("link:contains('hello')")
print("获取文本包含hello的标签:%s"%its)

　　运行结果

第一个标签:<link class="active1 a123" href="http://asda.com"><a>helloasdadasdad12312</a></link>
            
最后一个标签:<link class="movie1" href="http://asda2.com">asdadasdad12312</link>
        
第二个标签:<link class="active2" href="http://asda1.com">asdadasdad12312</link>
            
获取0以后的标签:<link class="active2" href="http://asda1.com">asdadasdad12312</link>
            <link class="movie1" href="http://asda2.com">asdadasdad12312</link>
        
获取奇数标签:<link class="active1 a123" href="http://asda.com"><a>helloasdadasdad12312</a></link>
            <link class="movie1" href="http://asda2.com">asdadasdad12312</link>
        
获取文本包含hello的标签:<link class="active1 a123" href="http://asda.com"><a>helloasdadasdad12312</a></link>