python的HTMLParser学习

blovekyo

　　先来大致看看HTMLParser的源代码吧：



"""A parser for HTML and XHTML."""
# This file is based on sgmllib.py, but the API is slightly different.
# XXX There should be a way to distinguish between PCDATA (parsed
# character data -- the normal case), RCDATA (replaceable character
# data -- only char and entity references and end tags are special)
# and CDATA (character data -- only end tags are special).

import markupbase
import re
# Regular expressions used for parsing
interesting_normal = re.compile('[&')
endtagfind = re.compile('')

class HTMLParseError(Exception):
"""Exception raised for all parse errors."""
def __init__(self, msg, position=(None, None)):
assert msg
self.msg = msg
self.lineno = position[0]
self.offset = position[1]
def __str__(self):
result = self.msg
if self.lineno is not None:
result = result + ", at line %d" % self.lineno
if self.offset is not None:
result = result + ", column %d" % (self.offset + 1)
return result

class HTMLParser(markupbase.ParserBase):
"""Find tags and other markup and call handler functions.
Usage:
p = HTMLParser()
p.feed(data)
...
p.close()
Start tags are handled by calling self.handle_starttag() or
self.handle_startendtag(); end tags by self.handle_endtag().  The
data between tags is passed from the parser to the derived class
by calling self.handle_data() with the data as argument (the data
may be split up in arbitrary chunks).  Entity references are
passed by calling self.handle_entityref() with the entity
reference as the argument.  Numeric character references are
passed to self.handle_charref() with the string containing the
reference as the argument.
"""
CDATA_CONTENT_ELEMENTS = ("script", "style")

def __init__(self):
"""Initialize and reset this instance."""
self.reset()
def reset(self):
"""Reset this instance.  Loses all unprocessed data."""
self.rawdata = ''
self.lasttag = '???'
self.interesting = interesting_normal
markupbase.ParserBase.reset(self)
def feed(self, data):
"""Feed data to the parser.
Call this as often as you want, with as little or as much text
as you want (may include '\n').
"""
self.rawdata = self.rawdata + data
self.goahead(0)
def close(self):
"""Handle any buffered data."""
self.goahead(1)
def error(self, message):
raise HTMLParseError(message, self.getpos())
__starttag_text = None
def get_starttag_text(self):
"""Return full source of start tag: ''."""
return self.__starttag_text
def set_cdata_mode(self):
self.interesting = interesting_cdata
def clear_cdata_mode(self):
self.interesting = interesting_normal
# Internal -- handle data as far as reasonable.  May leave state
# and data to be processed by a subsequent call.  If 'end' is
# true, force handling all data as if followed by EOF marker.
def goahead(self, end):
rawdata = self.rawdata
i = 0
n = len(rawdata)
while i < n:
match = self.interesting.search(rawdata, i) # < or &
if match:
j = match.start()
else:
j = n
if i < j: self.handle_data(rawdata[i:j])
i = self.updatepos(i, j)
if i == n: break
startswith = rawdata.startswith
if startswith('