xpath的使用：定位，獲取文本和屬性值
<title>TITLE</title>
<body>
<h1></h1>
<div></div>
<div id="photos">
<img src="pic1.jpeg"/><span id="pic1">*</span>
<img src="pic2.jpeg"/><span id="pic2">****</span>
<a href="http://www.baidu.com">****</a>
<a href="http://www.163.com">*****</a>
<a href="http://www.sohu.com">****</a>
</div>
<p class="myclassname">Hello,\nworld!<br/>-- by Adam</p>
</body>
</html>‘‘‘
html = etree.fromstring(myPage)
#一、定位
divs1 = html.xpath(‘//div‘)
divs2 = html.xpath(‘//div[@id]‘)
divs3 = html.xpath(‘//div[@class="foot"]‘)
divs4 = html.xpath(‘//div[@]‘)
divs5 = html.xpath(‘//div[1]‘)
divs6 = html.xpath(‘//div[last()-1]‘)
divs8 = html.xpath(‘//div|//h1‘)
divs9 = html.xpath(‘//div[not(@)]‘)
二、取文本 text() 區別 html.xpath(‘string()‘)
text1 = html.xpath(‘//div/text()‘)
text2 = html.xpath(‘//div[@id]/text()‘)
text3 = html.xpath(‘//div[@class="foot"]/text()‘)
text4 = html.xpath(‘//div[@*]/text()‘)
text5 = html.xpath(‘//div[1]/text()‘)
text6 = html.xpath(‘//div[last()-1]/text()‘)
text7 = html.xpath(‘//div[position()<3]/text()‘)
text8 = html.xpath(‘//div/text()|//h1/text()‘)
#三、取屬性 @
value1 = html.xpath(‘//a/@href‘)
value2 = html.xpath(‘//img/@src‘)
value3 = html.xpath(‘//div[2]/span/@id‘)
#四、定位（進階）
#1.文檔(DOM)元素(Element)的find，findall方法
divs = html.xpath(‘//div[position()<3]‘)
for div in divs:
ass = div.findall(‘a‘) # 這裏只能找到:div->a, 找不到:div->p->a
for a in ass:
if a is not None:
#print(dir(a))
print(a.text, a.attrib.get(‘href‘)) #文檔(DOM)元素(Element)的屬性：text, attrib
2.與1等價
a_href = html.xpath(‘//div[position()<3]/a/@href‘)
print(a_href)
#3.註意與1、2的區別
a_href = html.xpath(‘//div[position()<3]//a/@href‘)
print(a_href)
參考：https://www.cnblogs.com/hhh5460/p/5079465.html
xpath的使用：定位，獲取文本和屬性值