摘录了dive into python的例子
有两种方法,HTMLParser和SGMLParser
第一种:
#-*-coding:utf-8-*-
import HTMLParser
#html解析,继承HTMLParser类
class MyHTMLParser(HTMLParser.HTMLParser):
def _init(self):
HTMLParser.HTMLParser.__init__(self);
# 处理开始标签和结束标签 -- finish processing of start+end tag: <tag.../>
def handle_startendtag(self, tag, attrs):
self.handle_starttag(tag, attrs)
self.handle_endtag(tag)
#handle start tag
#处理开始标签和结束标签 这里打印出a标签的href的属性值
def handle_starttag(self,tag, attrs):
if tag=='a':
for name,value in attrs:
if name=='href':
print value
# 处理结束标签,比如</xx> -- handle end tag
def handle_endtag(self,tag):
pass;
# 处理特殊字符串,就是以&#开头的,一般是内码表示的字符 -- handle character reference
def handle_charref(self, name):
pass
# 处理一些特殊字符,以&开头的,比如 -- handle entity reference
def handle_entityref(self, name):
pass
# 处理数据,就是<xx>data</xx>中间的那些数据 -- handle data
def handle_data(self, data):
pass
# 处理注释 -- handle comment
def handle_comment(self, data):
pass
# 处理<!开头的,比如<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" -- handle declaration
def handle_decl(self, decl):
pass
# 处理形如<?instruction>的东西 -- handle processing instruction
def handle_pi(self, data):
pass
a='<body><a href="www.163.com">test</a></body>'
print a
my=MyHTMLParser()
my.feed(a)
#结果为www.163.com
第二种方式:
首先是一个基础类,和上面的方式一样
#!/usr/bin/env python
#-*-coding:utf-8-*-
from sgmllib import SGMLParser
import htmlentitydefs
class BaseHTMLProcessor(SGMLParser):
def reset(self):
# extend (called by SGMLParser.__init__)
self.pieces = []
SGMLParser.reset(self)
#是一个开始一个块的 HTML 标记,象 <html>,<head>,<body> 或 <pre> 等,或是一个独一的标记,
#象 <br> 或 <img> 等。当它找到一个开始标记 tagname,SGMLParser 将查找名为 start_tagname
#或 do_tagname 的方法。例如,当它找到一个 <pre> 标记,它将查找一个 start_pre 或 do_pre 的方法。
#如果找到了,SGMLParser 会使用这个标记的属性列表来调用这个方法;否则,它用这个标记的名字和属性
#列表来调用 unknown_starttag 方法。
def unknown_starttag(self, tag, attrs):
# called for each start tag
# attrs is a list of (attr, value) tuples
# e.g. for <pre class="screen">, tag="pre", attrs=[("class", "screen")]
# Ideally we would like to reconstruct original tag and attributes, but
# we may end up quoting attribute values that weren't quoted in the source
# document, or we may change the type of quotes around the attribute value
# (single to double quotes).
# Note that improperly embedded non-HTML code (like client-side Javascript)
# may be parsed incorrectly by the ancestor, causing runtime script errors.
# All non-HTML code must be enclosed in HTML comment tags (<!-- code -->)
# to ensure that it will pass through this parser unaltered (in handle_comment).
strattrs = "".join([' %s="%s"' % (key, value) for key, value in attrs])
self.pieces.append("<%(tag)s%(strattrs)s>" % locals())
#是结束一个块的 HTML 标记,象 </html>,</head>,</body> 或 </pre> 等。
#当找到一个结束标记时,SGMLParser 将查找名为 end_tagname 的方法。如果找到,
#SGMLParser 调用这个方法,否则它使用标记的名字来调用 unknown_endtag 。
def unknown_endtag(self, tag):
# called for each end tag, e.g. for </pre>, tag will be "pre"
# Reconstruct the original end tag.
self.pieces.append("</%(tag)s>" % locals())
#用字符的十进制或等同的十六进制来表示的转义字符,象  。当
#找到,SGMLParser 使用十进制或等同的十六进制字符文本来调用 handle_charref 。
def handle_charref(self, ref):
# called for each character reference, e.g. for " ", ref will be "160"
# Reconstruct the original character reference.
self.pieces.append("&#%(ref)s;" % locals())
#HTML 实体,象 ©。当找到,SGMLParser 使用 HTML 实体的名字来调用 handle_entityref 。
def handle_entityref(self, ref):
# called for each entity reference, e.g. for "©", ref will be "copy"
# Reconstruct the original entity reference.
self.pieces.append("&%(ref)s" % locals())
# standard HTML entities are closed with a semicolon; other entities are not
if htmlentitydefs.entitydefs.has_key(ref):
self.pieces.append(";")
#文本块。不满足其它 7 种类别的任何东西。当找到,SGMLParser 用文本来调用 handle_data。
def handle_data(self, text):
# called for each block of plain text, i.e. outside of any tag and
# not containing any character or entity references
# Store the original text verbatim.
#数据的处理
self.pieces.append(text)
#HTML 注释, 包括在 <!-- ... -->之间。当找到,SGMLParser 用注释内容来调用 handle_comment
def handle_comment(self, text):
# called for each HTML comment, e.g. <!-- insert Javascript code here -->
# Reconstruct the original comment.
# It is especially important that the source document enclose client-side
# code (like Javascript) within comments so it can pass through this
# processor undisturbed; see comments in unknown_starttag for details.
self.pieces.append("<!--%(text)s-->" % locals())
#HTML 处理指令,包括在 <? ... > 之间。当找到,SGMLParser 用处理指令内容来调用 handle_pi。
def handle_pi(self, text):
# called for each processing instruction, e.g. <?instruction>
# Reconstruct original processing instruction.
self.pieces.append("<?%(text)s>" % locals())
#HTML 声明,如 DOCTYPE,包括在 <! ... >之间。当找到,SGMLParser 用声明内容来调用 handle_decl
def handle_decl(self, text):
# called for the DOCTYPE, if present, e.g.
# <!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"
# "http://www.w3.org/TR/html4/loose.dtd">
# Reconstruct original DOCTYPE
self.pieces.append("<!%(text)s>" % locals())
def output(self):
"""Return processed HTML as a single string"""
return "".join(self.pieces)
接着第二种方法具体的应用,解析的是新浪一个特定blog的文章的内容和标题代码如下:
#!/usr/bin/env python
#coding:utf8
import re
from BaseHTMLProcessor import BaseHTMLProcessor
import urllib
class Dialectizer(BaseHTMLProcessor):
subs = ()
def reset(self):
# extend (called from __init__ in ancestor)
# Reset all data attributes
self.verbatim = 0
BaseHTMLProcessor.reset(self)
def unknown_starttag(self, tag, attrs):
self.pieces.append("")
def unknown_endtag(self, tag):
self.pieces.append("")
def start_title(self, attrs):
self.pieces.append("title")
def end_title(self):
self.pieces.append("title")
def start_p(self, attrs):
self.pieces.append("\n")
def end_p(self):
self.pieces.append("")
def start_div(self, attrs):
strattrs = "".join([value for key, value in attrs])
self.pieces.append(strattrs)
def end_div(self):
self.pieces.append("div")
def handle_data(self, text):
self.pieces.append(self.verbatim and text or self.process(text))
def process(self, text):
for fromPattern, toPattern in self.subs:
text = re.sub(fromPattern, toPattern, text)
return text
def translate(url):
import urllib
sock = urllib.urlopen(url)
htmlSource = sock.read()
sock.close()
parser = Dialectizer()
#parser.subs=((r"本",r"aaa"),)
parser.feed(htmlSource)#进行解析
parser.close()
return parser.output()
def test(url,filename):
htmlSource=translate(url)
#标题
title=htmlSource[re.search("title",htmlSource).end():]
title=title[:re.search("title",title).end()-5]
#内容
content=htmlSource[re.search("articleBody",htmlSource).end()+2:]
content=content[:re.search("div",content).end()-3]
content=re.sub(" ","",content)
content=re.sub("nbsp;","",content)
#文件名称
fileName=title;
#输出的文件内容
fileContent=title+"\n\n\n"+content;
fsock = open(filename, "wb")
fsock.write(fileContent)
fsock.close()
if __name__ == "__main__":
test("http://blog.sina.com.cn/s/blog_4bd7b9a20100cpgb.html",'test.txt')