#-*-coding:utf8-*-
from lxml import etree
html1 = '''
<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<title></title>
</head>
<body>
<div id="test-1">需要的内容1</div>
<div id="test-2">需要的内容2</div>
<div id="testfault">需要的内容3</div>
</body>
</html>
'''
html2 = '''
<!DOCTYPE html>
<html>
<head lang="en">
<meta charset="UTF-8">
<title></title>
</head>
<body>
<div id="test3">
我左青龙,
<span id="tiger">
右白虎,
<ul>上朱雀,
<li>下玄武。</li>
</ul>
老牛在当中,
</span>
龙头在胸口。
</div>
</body>
</html>
'''
# selector = etree.HTML(html1)
# #content = selector.xpath('//div[starts-with(@id,"test")]/text()')
# content = selector.xpath('//div[contains(@id,"test-1")]/text()')
# for each in content:
# print (each)
# selector = etree.HTML(html2)
# content_1 = selector.xpath('//div[@id="test3"]/text()')
# for each in content_1:
# print(each)
selector = etree.HTML(html2)
data = selector.xpath('//div[@id="test3"]')[0]
print(data)
info = data.xpath('string(.)')
print(info)
content_2 = info.replace('\n','').replace(' ','').replace(' ','')
print(content_2)
print(''.join(content_2.split()))
字符串的startswith,endswith函数的用法:
str = "this is string example....wow!!!"
print (str.startswith( 'this' ))
print (str.startswith( 'is', 2, 4 ))
print (str.startswith( 'this', 2, 4 ))
str = "this is string example....wow!!!"
suffix = "wow!!!"
print(str.endswith(suffix))
print(str.endswith(suffix, 20))
suffix = "is"
print(str.endswith(suffix, 2, 4))
print(str.endswith(suffix, 2, 6))
# 输入一个字符串返回满足以下条件的字符串
# 如果字符串长度大等于3,添加 'ing' 到字符串的末尾
# 如果字符串是以 'ing' 结尾的,就在末尾添加 'ly'
# 如果字符串长度小于3,返回原字符串
str = input("请输入一个字符串:")
length = len(str)
if str.endswith('ing'):
str += 'ly'
elif length >= 3:
str += 'ing'
else:
pass
print(str)