BeautifulSoup學習筆記

時間 2019-11-21

標籤 beautifulsoup 學習筆記简体版

原文原文鏈接

學習自http://rsj217.diandian.com/post/2012-11-01/40041235132html

#/usr/bin/env python                                                                                                                                     
# -*- coding:utf-8 -*-
import urllib2
import sys
import re

from bs4 import BeautifulSoup           # HTML
from bs4 import BeautifulStoneSoup      # XML
import bs4                              # ALL
                                                                                               
doc = ['<html><head><title>Page title</title></head>','<body><p id="firstpara" align="center">This is paragraph <b>one</b>.','<p id="secondpara" align="blah">This is paragraph <b>two</b>.','</html>']
# BeautifulSoup 接受一個字符串參數
soup = BeautifulSoup(''.join(doc))
print type(soup)
print type(soup.html)
print type(soup.title.string)

#BeautifulSoup文檔樹有三種基本對象
print
#BeautifulSoup對象
html = soup.html
print type(html)
print html

print
#BeautifulSoup.Tag
title = soup.title
print type(title)
print title

print
#BeautifulSoup.NavigableString
contents = soup.contents
print type(contents)
print contents

print
#使用contents方法查看文檔樹層級結構
print len(soup.contents[0].contents)
print soup.contents[0].contents[0]
print soup.contents[0].contents[1]
print len(soup.contents[0].contents[0])
print soup.contents[0].contents[0].contents[0]
print soup.contents[0].contents[0].contents[0].contents[0]


#獲取樹的子代元素，相似深度遍歷
print
head = html.next
print type(head)
print head

print
title = head.next
print type(title)
print title

print
title_content = title.next
print type(title_content)
print title_content


print
body = title_content.next
print type(body)
print body


#使用replacewith方法替換對象
print
print head
print head.parent
head.replaceWith('head was replace')
print head.parent #輸出空，由於原數據保留並被剪除
print head #沒有改變正常輸出
print soup.head #輸出空，head對象已不存在
print soup #文檔對象已經被修改


print
#使用find,findAll方法進行搜索
print soup.findAll('p')
print
print soup.findAll('p',id='firstpara')
print
#傳一個屬性或多個屬性對
print soup.findAll('p',{'align':'blah'})
#使用正則表達式
print soup.findAll(id=re.compile("para$"))


#讀取和修改屬性
print
p1 = soup.p
print p1
print p1['id']
p1['id'] = 'changeid'
print p1 #已被修改
print soup #文檔對象已經被修改

相關標籤/搜索

每日一句

每一个你不满意的现在，都有一个你没有努力的曾经。