from lxml import etree
text = ''' <div> <ul>
<li class="item-1"><a>first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a>
</ul> </div> '''
html = etree.HTML(text)
print(html)
# 查看element对象中所包含的字符串
print(etree.tostring(html).decode())
# 获取class为item-1 li下的a的href
ret1 = html.xpath("//li[@class='item-1']/a/@href")
print("ret1:")
print(ret1)
# 获取class为item-1 li下的a的文本
ret2 = html.xpath("//li[@class='item-1']/a/text()")
print("ret2:")
print(ret2)
# 每个li是一条新闻,把url和文本组成字典
for href in ret1:
item = {}
item['href'] = href
item["title"] = ret2[ret1.index(href)]
print(item)
print("*"*100)
ret3 = html.xpath("//li[@class='item-1']")
print("ret3:")
print(ret3)
print("*"*20)
for i in ret3:
item = {}
item["title"] = i.xpath("./a/text()")[0] if len(i.xpath("./a/text()"))>0 else None
item["href"] = i.xpath("./a/@href")[0] if len(i.xpath("./a/@href"))>0 else None
print(item)
"""
lxml能够修正HTML代码,但是可能会改错
使用etree.tostring观察修改之后的html的样子,根据修改之后的html字符串写xpath
-提取页面数据的思路
-先分组,取到一个包含分组标签的列表
-遍历,取其中每一组进行数据的提取,不会造成数据的对应错乱
"""
结果:
<Element html at 0x8c347c8>
<html><body><div> <ul>
<li class="item-1"><a>first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</a></li>
<li class="item-1"><a href="link4.html">fourth item</a></li>
<li class="item-0"><a href="link5.html">fifth item</a>
</li></ul> </div> </body></html>
ret1:
['link2.html', 'link4.html']
ret2:
['first item', 'second item', 'fourth item']
{'href': 'link2.html', 'title': 'first item'}
{'href': 'link4.html', 'title': 'second item'}
****************************************************************************************************
ret3:
[<Element li at 0x8be7dc8>, <Element li at 0x8c3d848>, <Element li at 0x8c3db48>]
********************
{'title': 'first item', 'href': None}
{'title': 'second item', 'href': 'link2.html'}
{'title': 'fourth item', 'href': 'link4.html'}