找出所有含特定标签的HTML元素
from bs4 import BeautifulSoup
html_sample = '\
<html>\
<body>\
<h1 id="title">Hello World</h1>\
<a href="#" class="link">This is link1</a>\
<a href="#link2" class="link">This is link2</a>\
</body>\
</html>'
soup = BeautifulSoup(html_sample,'html.parser')
#不加,'html.parser'将产生未使用剖析器的警告
print(soup.text)
使用select找出含有h1标签的元素
soup = BeautifulSoup(html_sample,'html.parser')
header = soup.select('h1')
print(header)
print(header[0])
print(header[0].text)
[h1 id="title">Hello World</h1>]
h1 id="title">Hello World</h>
Hello World
使用select找出含有a标签的元素
soup = BeautifulSoup(html_sample,'html.parser')
alink = soup.select('a')
print(alink)
for link in alink:
print(link)
for link in alink:
print(link.text)
[<a href="#" class="link">This is link1</a>,<a href="#link2" class="link">This is link2</a>]
<a href="#" class="link">This is link1</a>
<a href="#link2" class="link">This is link2</a>
This is link1
This is link2
取得含特定CSS属性的元素
使用select找出所有id为title的元素(id前需要加＃)
soup = BeautifulSoup(html_sample,'html.parser')
alink = soup.select('#title')
print(alink)
[<h1 id="title">Hello World</h1>]
使用select找出所有class为link的元素(class前需加.)
soup = BeautifulSoup(html_sample,'html.parser')
for link in soup.select('.link'):
print(link)
<a class="link" href="#">This is link1</a>
<a class="link" href="#link2">This is link2</a>
取得所有a标签内的链接
使用select找出所有a标签的href链接
soup = BeautifulSoup(html_sample,'html.parser')
alink = soup.select('a')
for link in alink:
print(link['href'])
#
#link2
例：
a = '<a href="#" qoo=123 abc=456>i am a link</a>'
soup2 = BeautifulSoup(a,'html.parser')
print(soup2.select('a')[0]['qoo'])
print(soup2.select('a')[0]['abc'])
print(soup2.select('a')[0]['href'])
123
456
#
寻找CSS定位
开发人员工具(浏览器一般都含有)
LnfoLite(Chrome专用)
下载地址：https://chrome.google.com/webstore/detail/infolite/ipjbadabbpedegielkhgpiekdlmfpgal
时间字符串转换
from datetime import datetime
字符串转时间-strptime
dt = datetime.strptime(timesource,'%Y年%m月%d日%H时%M分%S秒)
时间转字符串-strftime
dt.strftime('%Y-%m-%d-%H-%M-%S)
例：
from datetime import datetime
timesource = '2018年3月20日17时25分10秒'
dt = datetime.strptime(timesource,'%Y年%m月%d日%H时%M分%S秒')
print(dt)
print(dt.strftime('%Y年%m月%d日%H时%M分%S秒'))
2018-03-20 17:25:10
2018年03月20日17时25分10秒
