1.安裝方法
pip install pyquery
2.引用方法
from pyquery import PyQuery as pq
3.簡介
pyquery 是類型jquery 的一個專供python使用的html解析的庫，使用方法類似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/") #解析網頁
doc =pq("./a.html") #解析html 文本4.2 基本CSS選擇器
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")
運行結果：
<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的標簽 .是查找class 的標簽 link 是查找link 標簽 中間的空格表示裡層
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("類型為:%s"%type(items))
link = items.find('.s_from')
print(link)
link = items.children()
print(link)
運行結果：
<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> 類型為:<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>
根據運行結果可以發現返回結果類型為pyquery，並且find方法和children 方法都可以獲取裡層標簽
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)
運行結果:
<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可以查找出外層標簽包括的內容，與之類似的還有parents,可以獲取所有外層節點
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)
運行結果：
<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>
根據運行結果可以看出，siblings 返回了同級的其他標簽
結論：子元素查找，父元素查找，兄弟元素查找，這些方法返回的結果類型都是pyquery類型，可以針對結果再次進行選擇
4.6 遍歷查找結果
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)
運行結果：
<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獲取屬性信息
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)
運行結果：
http://asda.com http://asda.com http://asda1.com http://asda1.com http://asda2.com http://asda2.com
4.8 獲取文本
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())
運行結果
asdadasdad12312 asdadasdad12312 asdadasdad12312
4.9 獲取 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())
運行結果：
<a>asdadasdad12312</a> asdadasdad12312 asdadasdad12312
5.常用DOM操作
5.1 addClass removeClass
添加，移除class標簽
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'))
運行結果
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>
需要注意的是已經存在的class標簽不會繼續添加
5.2 attr css
attr 為獲取/修改屬性 css 添加style屬性
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'))
運行結果
C:\Python27\python.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" ><a>asdadasdad12312</a></link> 修改:<link class="active" href="http://asda1.com">asdadasdad12312</link> 添加:<link class="active" href="http://asda1.com" >asdadasdad12312</link> 修改:<link class="active" href="http://asda2.com">asdadasdad12312</link> 添加:<link class="active" href="http://asda2.com" >asdadasdad12312</link>
attr css操作直接修改對象的
5.3 remove
remove 移除標簽
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('移除前獲取文本結果:\n%s'%its.text())
it=its.remove('ul')
print('移除後獲取文本結果:\n%s'%it.text())
運行結果
移除前獲取文本結果: hello nihao asdasd asdadasdad12312 asdadasdad12312 asdadasdad12312 移除後獲取文本結果: hello nihao
其他DOM方法參考：
http://pyquery.readthedocs.io/en/latest/api.html
6.偽類選擇器
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('第一個標簽:%s'%its)
its=doc("link:last-child")
print('最後一個標簽:%s'%its)
its=doc("link:nth-child(2)")
print('第二個標簽:%s'%its)
its=doc("link:gt(0)") #從零開始
print("獲取0以後的標簽:%s"%its)
its=doc("link:nth-child(2n-1)")
print("獲取奇數標簽:%s"%its)
its=doc("link:contains('hello')")
print("獲取文本包含hello的標簽:%s"%its)
運行結果
第一個標簽:<link class="active1 a123" href="http://asda.com"><a>helloasdadasdad12312</a></link> 最後一個標簽:<link class="movie1" href="http://asda2.com">asdadasdad12312</link> 第二個標簽:<link class="active2" href="http://asda1.com">asdadasdad12312</link> 獲取0以後的標簽:<link class="active2" href="http://asda1.com">asdadasdad12312</link> <link class="movie1" href="http://asda2.com">asdadasdad12312</link> 獲取奇數標簽:<link class="active1 a123" href="http://asda.com"><a>helloasdadasdad12312</a></link> <link class="movie1" href="http://asda2.com">asdadasdad12312</link> 獲取文本包含hello的標簽:<link class="active1 a123" href="http://asda.com"><a>helloasdadasdad12312</a></link>
