| 失效链接处理 |
|
Beautiful_Soup中文文档 PDF 下载
本站整理下载：
提取码：y651
相关截图：
主要内容：
from BeautifulSoup import BeautifulSoup
import re
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>']
soup = BeautifulSoup (''.join(doc))
print soup.prettify()
# <html>
# <head>
# <title>
# Page title
# </title>
# </head>
# <body>
# <p id="firstpara" align="center">
# This is paragraph
# <b>
# one
# </b>
# .
# </p>
# <p id="secondpara" align="blah">
# This is paragraph
# <b>
# two
# </b>
# .
# </p>
# </body>
# </html>
navigate soup的一些方法:
soup.contents[0].name
# u'html'
soup.contents[0].contents[0].name
# u'head'
head = soup.contents[0].contents[0]
head.parent.name
# u'html'
head.next
# <title>Page title</title>
head.nextSibling .name
# u'body'
head.nextSibling .contents[0]
# <p id="firstpara" align="center">This is paragraph <b>one</b>.</p>
head.nextSibling .contents[0].nextSibling
# <p id="secondpara" align="blah">This is paragraph <b>two</b>.</p>
下面是一些方法搜索soup，获得特定标签或有着特定属性的标签：
titleTag = soup.html.head.title
titleTag
# <title>Page title</title>
titleTag.string
# u'Page title'
len(soup('p'))
# 2
soup.findAll('p', align="center")
# [<p id="firstpara" align="center">This is paragraph <b>one</b>. </p>]
soup.find('p', align="center")
# <p id="firstpara" align="center">This is paragraph <b>one</b>. </p>
soup('p', align="center")[0]['id']
# u'firstpara'
soup.find('p', align=re.compile('^b.*'))['id']
# u'secondpara'
soup.find('p').b.string
# u'one'
soup('p')[1].b.string
# u'two'
修改soup也很简单：
titleTag['id'] = 'theTitle'
titleTag.contents[0].replaceWith ("New title")
soup.html.head
# <head><title id="theTitle">New title</title></head>
soup.p.extract()
soup.prettify()
# <html>
# <head>
Beautiful Soup documentation Page 3
http://www.crummy.com/software/BeautifulSoup/documentation.zh.html 8/12/2010 3:58:02 PM
# <title id="theTitle">
# New title
# </title>
# </head>
# <body>
# <p id="secondpara" align="blah">
# This is paragraph
# <b>
# two
# </b>
# .
# </p>
# </body>
# </html>
soup.p.replaceWith (soup.b)
# <html>
# <head>
# <title id="theTitle">
# New title
# </title>
# </head>
# <body>
# <b>
# two
# </b>
# </body>
# </html>
soup.body.insert(0, "This page used to have ")
soup.body.insert(2, " <p> tags!")
soup.body
# <body>This page used to have <b>two</b> <p> tags!</body>
一个实际例子，用于抓取 ICC Commercial Crime Services weekly piracy report页面, 使用Beautiful Soup剖析并获得发生的盗
版事件:
import urllib2
from BeautifulSoup import BeautifulSoup
page = urllib2.urlopen("http://www.icc-ccs.org/prc/piracyreport.php")
soup = BeautifulSoup (page)
for incident in soup('td', width="90%"):
where, linebreak, what = incident.contents[:3]
print where.strip()
print what.strip()
print
|
| Java1234官方群25： | 
|
| Java1234官方群25： | 838462530 |
苏公网安备 32061202001004号
