8.1. 概览
我经常在 comp.lang.python 上看到关于如下的问题： “ 怎么才能从我的 HTML 文档中列出所有的 [头|图像|链接] 呢？” “怎么才能 [分析|解释|munge] 我的 HTML 文档的文本，但是又要保留标记呢？” “怎么才能一次给我所有的 HTML 标记 [增加|删除|加引号] 属性呢？” 本章将回答所有这些问题。
下面给出一个完整的，可工作的 Python 程序，它分为两部分。第一部分，BaseHTMLProcessor.py 是一个通用工具，它可以通过扫描标记和文本块来帮助您处理 HTML 文件。第二部分，dialect.py 是一个例子，演示了如何使用 BaseHTMLProcessor.py 来转化 HTML 文档，保留文本但是去掉了标记。阅读文档字符串 (doc string) 和注释来了解将要发生事情的概况。大部分内容看上去像巫术，因为任一个这些类的方法是如何调用的不是很清楚。不要紧，所有内容都会按进度被逐步地展示出来。
例 8.1. BaseHTMLProcessor.py
如果您还没有下载本书附带的样例程序, 可以 下载本程序和其他样例程序。
from sgmllib import SGMLParser
import htmlentitydefs
class BaseHTMLProcessor(SGMLParser):
def reset(self):
# extend (called by SGMLParser.__init__)
self.pieces = []
SGMLParser.reset(self)
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())
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())
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())
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(";")
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.
self.pieces.append(text)
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())
def handle_pi(self, text):
# called for each processing instruction, e.g. <?instruction>
# Reconstruct original processing instruction.
self.pieces.append("<?%(text)s>" % locals())
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)
例 8.2. dialect.py
import re
from BaseHTMLProcessor import BaseHTMLProcessor
class Dialectizer(BaseHTMLProcessor):
subs = ()
def reset(self):
# extend (called from __init__ in ancestor)
# Reset all data attributes
self.verbatim = 0
BaseHTMLProcessor.reset(self)
def start_pre(self, attrs):
# called for every <pre> tag in HTML source
# Increment verbatim mode count, then handle tag like normal
self.verbatim += 1
self.unknown_starttag("pre", attrs)
def end_pre(self):
# called for every </pre> tag in HTML source
# Decrement verbatim mode count
self.unknown_endtag("pre")
self.verbatim -= 1
def handle_data(self, text):
# override
# called for every block of text in HTML source
# If in verbatim mode, save text unaltered;
# otherwise process the text with a series of substitutions
self.pieces.append(self.verbatim and text or self.process(text))
def process(self, text):
# called from handle_data
# Process text block by performing series of regular expression
# substitutions (actual substitions are defined in descendant)
for fromPattern, toPattern in self.subs:
text = re.sub(fromPattern, toPattern, text)
return text
class ChefDialectizer(Dialectizer):
"""convert HTML to Swedish Chef-speak
based on the classic chef.x, copyright (c) 1992, 1993 John Hagerman
"""
subs = ((r'a([nu])', r'u\1'),
(r'A([nu])', r'U\1'),
(r'a\B', r'e'),
(r'A\B', r'E'),
(r'en\b', r'ee'),
(r'\Bew', r'oo'),
(r'\Be\b', r'e-a'),
(r'\be', r'i'),
(r'\bE', r'I'),
(r'\Bf', r'ff'),
(r'\Bir', r'ur'),
(r'(\w*?)i(\w*?)$', r'\1ee\2'),
(r'\bow', r'oo'),
(r'\bo', r'oo'),
(r'\bO', r'Oo'),
(r'the', r'zee'),
(r'The', r'Zee'),
(r'th\b', r't'),
(r'\Btion', r'shun'),
(r'\Bu', r'oo'),
(r'\BU', r'Oo'),
(r'v', r'f'),
(r'V', r'F'),
(r'w', r'w'),
(r'W', r'W'),
(r'([a-z])[.]', r'\1\. Bork Bork Bork!'))
class FuddDialectizer(Dialectizer):
"""convert HTML to Elmer Fudd-speak"""
subs = ((r'[rl]', r'w'),
(r'qu', r'qw'),
(r'th\b', r'f'),
(r'th', r'd'),
(r'n[.]', r'n, uh-hah-hah-hah.'))
class OldeDialectizer(Dialectizer):
"""convert HTML to mock Middle English"""
subs = ((r'i([bcdfghjklmnpqrstvwxyz])e\b', r'y\1'),
(r'i([bcdfghjklmnpqrstvwxyz])e', r'y\1\1e'),
(r'ick\b', r'yk'),
(r'ia([bcdfghjklmnpqrstvwxyz])', r'e\1e'),
(r'e[ea]([bcdfghjklmnpqrstvwxyz])', r'e\1e'),
(r'([bcdfghjklmnpqrstvwxyz])y', r'\1ee'),
(r'([bcdfghjklmnpqrstvwxyz])er', r'\1re'),
(r'([aeiou])re\b', r'\1r'),
(r'ia([bcdfghjklmnpqrstvwxyz])', r'i\1e'),
(r'tion\b', r'cioun'),
(r'ion\b', r'ioun'),
(r'aid', r'ayde'),
(r'ai', r'ey'),
(r'ay\b', r'y'),
(r'ay', r'ey'),
(r'ant', r'aunt'),
(r'ea', r'ee'),
(r'oa', r'oo'),
(r'ue', r'e'),
(r'oe', r'o'),
(r'ou', r'ow'),
(r'ow', r'ou'),
(r'\bhe', r'hi'),
(r've\b', r'veth'),
(r'se\b', r'e'),
(r"'s\b", r'es'),
(r'ic\b', r'ick'),
(r'ics\b', r'icc'),
(r'ical\b', r'ick'),
(r'tle\b', r'til'),
(r'll\b', r'l'),
(r'ould\b', r'olde'),
(r'own\b', r'oune'),
(r'un\b', r'onne'),
(r'rry\b', r'rye'),
(r'est\b', r'este'),
(r'pt\b', r'pte'),
(r'th\b', r'the'),
(r'ch\b', r'che'),
(r'ss\b', r'sse'),
(r'([wybdp])\b', r'\1e'),
(r'([rnt])\b', r'\1\1e'),
(r'from', r'fro'),
(r'when', r'whan'))
def translate(url, dialectName="chef"):
"""fetch URL and translate using dialect
dialect in ("chef", "fudd", "olde")"""
import urllib
sock = urllib.urlopen(url)
htmlSource = sock.read()
sock.close()
parserName = "%sDialectizer" % dialectName.capitalize()
parserClass = globals()[parserName]
parser = parserClass()
parser.feed(htmlSource)
parser.close()
return parser.output()
def test(url):
"""test all dialects against URL"""
for dialect in ("chef", "fudd", "olde"):
outfile = "%s.html" % dialect
fsock = open(outfile, "wb")
fsock.write(translate(url, dialect))
fsock.close()
import webbrowser
webbrowser.open_new(outfile)
if __name__ == "__main__":
test("http://diveintopython.org/odbchelper_list.html")
例 8.3. dialect.py 的输出结果
运行这个脚本会将 第 3.2 节 “List 介绍” 转换成模仿瑞典厨师用语 (mock Swedish Chef-speak) (来自 The Muppets)、模仿埃尔默唠叨者用语 (mock Elmer Fudd-speak) (来自 Bugs Bunny 卡通画) 和模仿中世纪英语 (mock Middle English) (零散地来源于乔叟的《坎特伯雷故事集》)。如果您查看输出页面的 HTML 源代码，您会发现所有的 HTML 标记和属性没有改动，但是在标记之间的文本被转换成模仿语言了。如果您观查得更仔细些，您会发现，实际上，仅有标题和段落被转换了；代码列表和屏幕例子没有改动。
<div class="abstract">
<p>Lists awe <span class="application">Pydon</span>'s wowkhowse datatype.
If youw onwy expewience wif wists is awways in
<span class="application">Visuaw Basic</span> ow (God fowbid) de datastowe
in <span class="application">Powewbuiwdew</span>, bwace youwsewf fow
<span class="application">Pydon</span> wists.</p>
</div>