Html解析，方便速查

记性不好，收集，方便查询

lxml_xpath

 

xpath('//button/span[contains(text(), "指定文本内容")]')

#使用 xpath 定位包含指定文本内容的标签，例如：a = tree.xpath('//a[contains(text(), "下一页")]/@href')[0]

文本完全匹配，a = tree.xpath('//a[text()="下一页"]/@href')[0]

 

#from lxml import etree　　
     tree = etree.HTML(html)
        node_list = tree.xpath('//div[contains(@id, "qiushi_tag")]')
        #id属性中包含'qiushi_tag'
        #<div class="article block untagged mb15 typs_long" id="qiushi_tag_120321510">
        for node in node_list:
            author = node.xpath('./div/a[2]/h2')[0].text.strip()
            content = node.xpath('.//div[@class="content"]/span')[0].text.strip()
            zan = node.xpath('.//div[@class="stats"]/span[1]/i')[0].text
#zan = node.xpath('.//div[@class="stats"]/span[1]/i/text()')[0]
            comments = node.xpath('.//a[@class="qiushi_comments"]/i')[0].text
            items = {"author" : author, "content" : content, "zan" : zan, "comments" : comments}

属性名称杂乱，'//'，'/'，'[ ]'，'|'等符号，让节点的选取更方便

‘/’ 是用来获取子元素的，因此前后要父子关系

‘[2]’ 表示第二个，非list类型中的索引

 

BeautifulSoup_CSS  详细常用：http://www.cnblogs.com/math98/p/8776898.html

from bs4 import BeautifulSoup
doc = '''
        <div>
            <ul>
                 <li class="item-0"><a href="link1.html">first item</a></li>
                 <li class="item-1"><a href="link2.html">second item</a></li>
                 <li class="item-inactive"><a href="link3.html"><span class="bold">third item</span></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>'''
soup = BeautifulSoup(doc, 'lxml')
a = soup.select('body p')[1].select('a')[0].text
b = soup.select('ul span')[0].text
#ul span 前后两标签不一定要父子关系
c = soup.select('.item-0 a')[0]

print(c['href'])