<PYTHON>[BeautifulSoup]

설치

 

pip install BeautifulSoup4

 

파싱방법

 

soup.title
# <title>The Dormouse's story</title>
soup.title.name
# u'title'
soup.title.string
# u'The Dormouse's story'
soup.title.parent.name
# u'head'
soup.p
# <p class="title"><b>The Dormouse's story</b></p>
soup.p['class']
# u'title'
soup.a
# <a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
soup.find_all('a')
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
soup.find(id="link3")
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>

 

 

URL 추출

 

for link in soup.find_all('a'):
print(link.get('href'))

 

샘플

 

웹페이지 파싱

 

#-*- coding:utf-8 -*-
import urllib
 
from bs4 import BeautifulSoup
 
html = urllib.urlopen(URL)
fSoup = BeautifulSoup(html, "lxml")
statusImg = fSoup.find(keyword)
 
s = statusImg.get('key')
 
ss = s.split('/')
 
if ss[3] == "value":
    statusNum = "1"
 
elif ss[3] == "value":
    statusNum = "2"
 
elif ss[3] == "value":
    statusNum = "3"
 
else:
    pass