HTML parser written with the Python 3 standard lib

Question

I'm working on a project where I have to extract some basic information from webpages like links, title etc. I can't use any of the awesome libs like bs4 or my personal favorite lxml.

At first I tried xml.minidon.parseString() but it had zero tolerance for broken html. My app needs to parse html from random sources so I have no control over the quality of the HTML that gets passed to the parser.

It was suggested to me by a fellow coder to use html.parse.HTMLParser(). My first impression of HTMLParser was that this is low level but pretty cool.

I wouldn't want to do any advanced scraping with it but it's great at extracting basic information from a web page like the title and links. It also seems to be pretty fast. So I figured HTMLParser() was the best choice for the job.

I quickly hacked this parser together and was able to make it do most of what I need it to do.

Before I begin expanding this parser I would like to do as much refactoring as possible.

#-*-coding:utf8;-*-
#qpy:3
#qpy:console
from html.parser import HTMLParser
from urllib.request import urlopen
from urllib.parse import urlparse
ANCHOR = 'a'
TITLE = 'title'
META = 'meta'
BOLD = 'b'
class BasicParser(HTMLParser):
 recording_title = 0
 recording_bold = 0
 links = set()
 bold_text = []
 title = None
 url = None
 root_url = None
 resolve_links = 1
 def set_url(self, url):
 parsed_url = urlparse(url)
 scheme = parsed_url.scheme
 host = parsed_url.netloc
 self.root_url = '{}://{}/'.format(scheme, host)
 self.url = parsed_url.geturl()
 def handle_starttag(self, tag, attrs):
 # TODO; flatten this out!
 if tag == ANCHOR:
 for attribute in attrs:
 if attribute[0] == 'href':
 link = attribute[1]
 if not self.resolve_links:
 self.links.append(link)
 else:
 if link.startswith('http'):
 self.links.add(attribute[1])
 else:
 self.links.add(self.root_url + attribute[1])
 if tag == TITLE:
 self.recording_title = 1
 else:
 self.recording_title = 0
 if tag == BOLD:
 self.recording_bold = 1
 else:
 self.recording_bold = 0
 def handle_data(self, data):
 if self.recording_title:
 self.title = data.strip()
 if self.recording_bold:
 self.bold_text.append(data)
# example usage.
url = 'http://www.cnn.com/'
def parse_page(url):
 p = BasicParser()
 p.set_url(url)
 html = urlopen(url).read().decode('latin-1')
 p.feed(html)
 return p
page = parse_page(url)
print(page.title)

Here is the source code to HTMLParser:

"""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 re
import warnings
import _markupbase
from html import unescape
__all__ = ['HTMLParser']
# Regular expressions used for parsing
interesting_normal = re.compile('[&<]')
incomplete = re.compile('&[a-zA-Z#]')
entityref = re.compile('&([a-zA-Z][-.a-zA-Z0-9]*)[^a-zA-Z0-9]')
charref = re.compile('&#(?:[0-9]+|[xX][0-9a-fA-F]+)[^0-9a-fA-F]')
starttagopen = re.compile('<[a-zA-Z]')
piclose = re.compile('>')
commentclose = re.compile(r'--\s*>')
# Note:
# 1) if you change tagfind/attrfind remember to update locatestarttagend too;
# 2) if you change tagfind/attrfind and/or locatestarttagend the parser will
# explode, so don't do it.
# see http://www.w3.org/TR/html5/tokenization.html#tag-open-state
# and http://www.w3.org/TR/html5/tokenization.html#tag-name-state
tagfind_tolerant = re.compile(r'([a-zA-Z][^\t\n\r\f />\x00]*)(?:\s|/(?!>))*')
attrfind_tolerant = re.compile(
 r'((?<=[\'"\s/])[^\s/>][^\s/=>]*)(\s*=+\s*'
 r'(\'[^\']*\'|"[^"]*"|(?![\'"])[^>\s]*))?(?:\s|/(?!>))*')
locatestarttagend_tolerant = re.compile(r"""
 <[a-zA-Z][^\t\n\r\f />\x00]* # tag name
 (?:[\s/]* # optional whitespace before attribute name
 (?:(?<=['"\s/])[^\s/>][^\s/=>]* # attribute name
 (?:\s*=+\s* # value indicator
 (?:'[^']*' # LITA-enclosed value
 |"[^"]*" # LIT-enclosed value
 |(?!['"])[^>\s]* # bare value
 )
 (?:\s*,)* # possibly followed by a comma
 )?(?:\s|/(?!>))*
 )*
 )?
 \s* # trailing whitespace
""", re.VERBOSE)
endendtag = re.compile('>')
# the HTML 5 spec, section 8.1.2.2, doesn't allow spaces between
# </ and the tag name, so maybe this should be fixed
endtagfind = re.compile(r'</\s*([a-zA-Z][-.a-zA-Z0-9:_]*)\s*>')
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). If convert_charrefs is
 True the character references are converted automatically to the
 corresponding Unicode character (and self.handle_data() is no
 longer split in chunks), otherwise they are passed by calling
 self.handle_entityref() or self.handle_charref() with the string
 containing respectively the named or numeric reference as the
 argument.
 """
 CDATA_CONTENT_ELEMENTS = ("script", "style")
 iidef __init__(self, *, convert_charrefs=True):
 """Initialize and reset this instance.
 If convert_charrefs is True (the default), all character references
 are automatically converted to the corresponding Unicode characters.
 """
 self.convert_charrefs = convert_charrefs
 self.reset()
 def reset(self):
 """Reset this instance. Loses all unprocessed data."""
 self.rawdata = ''
 self.lasttag = '???'
 self.interesting = interesting_normal
 self.cdata_elem = None
 _markupbase.ParserBase.reset(self)
 def feed(self, data):
 r"""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)
 __starttag_text = None
 def get_starttag_text(self):
 """Return full source of start tag: '<...>'."""
 return self.__starttag_text
 def set_cdata_mode(self, elem):
 self.cdata_elem = elem.lower()
 self.interesting = re.compile(r'</\s*%s\s*>' % self.cdata_elem, re.I)
 def clear_cdata_mode(self):
 self.interesting = interesting_normal
 self.cdata_elem = None
 # 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:
 if self.convert_charrefs and not self.cdata_elem:
 j = rawdata.find('<', i)
 if j < 0:
 # if we can't find the next <, either we are at the end
 # or there's more text incoming. If the latter is True,
 # we can't pass the text to handle_data in case we have
 # a charref cut in half at end. Try to determine if
 # this is the case before proceeding by looking for an
 # & near the end and see if it's followed by a space or ;.
 amppos = rawdata.rfind('&', max(i, n-34))
 if (amppos >= 0 and
 not re.compile(r'[\s;]').search(rawdata, amppos)):
 break # wait till we get all the text
 j = n
 else:
 match = self.interesting.search(rawdata, i) # < or &
 if match:
 j = match.start()
 else:
 if self.cdata_elem:
 break
 j = n
 if i < j:
 if self.convert_charrefs and not self.cdata_elem:
 self.handle_data(unescape(rawdata[i:j]))
 else:
 self.handle_data(rawdata[i:j])
 i = self.updatepos(i, j)
 if i == n: break
 startswith = rawdata.startswith
 if startswith('<', i):
 if starttagopen.match(rawdata, i): # < + letter
 k = self.parse_starttag(i)
 elif startswith("</", i):
 k = self.parse_endtag(i)
 elif startswith("<!--", i):
 k = self.parse_comment(i)
 elif startswith("<?", i):
 k = self.parse_pi(i)
 elif startswith("<!", i):
 k = self.parse_html_declaration(i)
 elif (i + 1) < n:
 self.handle_data("<")
 k = i + 1
 else:
 break
 if k < 0:
 if not end:
 break
 k = rawdata.find('>', i + 1)
 if k < 0:
 k = rawdata.find('<', i + 1)
 if k < 0:
 k = i + 1
 else:
 k += 1
 if self.convert_charrefs and not self.cdata_elem:
 self.handle_data(unescape(rawdata[i:k]))
 else:
 self.handle_data(rawdata[i:k])
 i = self.updatepos(i, k)
 elif startswith("&#", i):
 match = charref.match(rawdata, i)
 if match:
 name = match.group()[2:-1]
 self.handle_charref(name)
 k = match.end()
 if not startswith(';', k-1):
 k = k - 1
 i = self.updatepos(i, k)
 continue
 else:
 if ";" in rawdata[i:]: # bail by consuming &#
 self.handle_data(rawdata[i:i+2])
 i = self.updatepos(i, i+2)
 break
 elif startswith('&', i):
 match = entityref.match(rawdata, i)
 if match:
 name = match.group(1)
 self.handle_entityref(name)
 k = match.end()
 if not startswith(';', k-1):
 k = k - 1
 i = self.updatepos(i, k)
 continue
 match = incomplete.match(rawdata, i)
 if match:
 # match.group() will contain at least 2 chars
 if end and match.group() == rawdata[i:]:
 k = match.end()
 if k <= i:
 k = n
 i = self.updatepos(i, i + 1)
 # incomplete
 break
 elif (i + 1) < n:
 # not the end of the buffer, and can't be confused
 # with some other construct
 self.handle_data("&")
 i = self.updatepos(i, i + 1)
 else:
 break
 else:
 assert 0, "interesting.search() lied"
 # end while
 if end and i < n and not self.cdata_elem:
 if self.convert_charrefs and not self.cdata_elem:
 self.handle_data(unescape(rawdata[i:n]))
 else:
 self.handle_data(rawdata[i:n])
 i = self.updatepos(i, n)
 self.rawdata = rawdata[i:]
 # Internal -- parse html declarations, return length or -1 if not terminated
 # See w3.org/TR/html5/tokenization.html#markup-declaration-open-state
 # See also parse_declaration in _markupbase
 def parse_html_declaration(self, i):
 rawdata = self.rawdata
 assert rawdata[i:i+2] == '<!', ('unexpected call to '
 'parse_html_declaration()')
 if rawdata[i:i+4] == '<!--':
 # this case is actually already handled in goahead()
 return self.parse_comment(i)
 elif rawdata[i:i+3] == '<![':
 return self.parse_marked_section(i)
 elif rawdata[i:i+9].lower() == '<!doctype':
 # find the closing >
 gtpos = rawdata.find('>', i+9)
 if gtpos == -1:
 return -1
 self.handle_decl(rawdata[i+2:gtpos])
 return gtpos+1
 else:
 return self.parse_bogus_comment(i)
 # Internal -- parse bogus comment, return length or -1 if not terminated
 # see http://www.w3.org/TR/html5/tokenization.html#bogus-comment-state
 def parse_bogus_comment(self, i, report=1):
 rawdata = self.rawdata
 assert rawdata[i:i+2] in ('<!', '</'), ('unexpected call to '
 'parse_comment()')
 pos = rawdata.find('>', i+2)
 if pos == -1:
 return -1
 if report:
 self.handle_comment(rawdata[i+2:pos])
 return pos + 1
 # Internal -- parse processing instr, return end or -1 if not terminated
 def parse_pi(self, i):
 rawdata = self.rawdata
 assert rawdata[i:i+2] == '<?', 'unexpected call to parse_pi()'
 match = piclose.search(rawdata, i+2) # >
 if not match:
 return -1
 j = match.start()
 self.handle_pi(rawdata[i+2: j])
 j = match.end()
 return j
 # Internal -- handle starttag, return end or -1 if not terminated
 def parse_starttag(self, i):
 self.__starttag_text = None
 endpos = self.check_for_whole_start_tag(i)
 if endpos < 0:
 return endpos
 rawdata = self.rawdata
 self.__starttag_text = rawdata[i:endpos]
 # Now parse the data between i+1 and j into a tag and attrs
 attrs = []
 match = tagfind_tolerant.match(rawdata, i+1)
 assert match, 'unexpected call to parse_starttag()'
 k = match.end()
 self.lasttag = tag = match.group(1).lower()
 while k < endpos:
 m = attrfind_tolerant.match(rawdata, k)
 if not m:
 break
 attrname, rest, attrvalue = m.group(1, 2, 3)
 if not rest:
 attrvalue = None
 elif attrvalue[:1] == '\'' == attrvalue[-1:] or \
 attrvalue[:1] == '"' == attrvalue[-1:]:
 attrvalue = attrvalue[1:-1]
 if attrvalue:
 attrvalue = unescape(attrvalue)
 attrs.append((attrname.lower(), attrvalue))
 k = m.end()
 end = rawdata[k:endpos].strip()
 if end not in (">", "/>"):
 lineno, offset = self.getpos()
 if "\n" in self.__starttag_text:
 lineno = lineno + self.__starttag_text.count("\n")
 offset = len(self.__starttag_text) \
 - self.__starttag_text.rfind("\n")
 else:
 offset = offset + len(self.__starttag_text)
 self.handle_data(rawdata[i:endpos])
 return endpos
 if end.endswith('/>'):
 # XHTML-style empty tag: <span attr="value" />
 self.handle_startendtag(tag, attrs)
 else:
 self.handle_starttag(tag, attrs)
 if tag in self.CDATA_CONTENT_ELEMENTS:
 self.set_cdata_mode(tag)
 return endpos
 # Internal -- check to see if we have a complete starttag; return end
 # or -1 if incomplete.
 def check_for_whole_start_tag(self, i):
 rawdata = self.rawdata
 m = locatestarttagend_tolerant.match(rawdata, i)
 if m:
 j = m.end()
 next = rawdata[j:j+1]
 if next == ">":
 return j + 1
 if next == "/":
 if rawdata.startswith("/>", j):
 return j + 2
 if rawdata.startswith("/", j):
 # buffer boundary
 return -1
 # else bogus input
 if j > i:
 return j
 else:
 return i + 1
 if next == "":
 # end of input
 return -1
 if next in ("abcdefghijklmnopqrstuvwxyz=/"
 "ABCDEFGHIJKLMNOPQRSTUVWXYZ"):
 # end of input in or before attribute value, or we have the
 # '/' from a '/>' ending
 return -1
 if j > i:
 return j
 else:
 return i + 1
 raise AssertionError("we should not get here!")
 # Internal -- parse endtag, return end or -1 if incomplete
 def parse_endtag(self, i):
 rawdata = self.rawdata
 assert rawdata[i:i+2] == "</", "unexpected call to parse_endtag"
 match = endendtag.search(rawdata, i+1) # >
 if not match:
 return -1
 gtpos = match.end()
 match = endtagfind.match(rawdata, i) # </ + tag + >
 if not match:
 if self.cdata_elem is not None:
 self.handle_data(rawdata[i:gtpos])
 return gtpos
 # find the name: w3.org/TR/html5/tokenization.html#tag-name-state
 namematch = tagfind_tolerant.match(rawdata, i+2)
 if not namematch:
 # w3.org/TR/html5/tokenization.html#end-tag-open-state
 if rawdata[i:i+3] == '</>':
 return i+3
 else:
 return self.parse_bogus_comment(i)
 tagname = namematch.group(1).lower()
 # consume and ignore other stuff between the name and the >
 # Note: this is not 100% correct, since we might have things like
 # </tag attr=">">, but looking for > after tha name should cover
 # most of the cases and is much simpler
 gtpos = rawdata.find('>', namematch.end())
 self.handle_endtag(tagname)
 return gtpos+1
 elem = match.group(1).lower() # script or style
 if self.cdata_elem is not None:
 if elem != self.cdata_elem:
 self.handle_data(rawdata[i:gtpos])
 return gtpos
 self.handle_endtag(elem.lower())
 self.clear_cdata_mode()
 return gtpos
 # Overridable -- finish processing of start+end tag: <tag.../>
 def handle_startendtag(self, tag, attrs):
 self.handle_starttag(tag, attrs)
 self.handle_endtag(tag)
 # Overridable -- handle start tag
 def handle_starttag(self, tag, attrs):
 pass
 # Overridable -- handle end tag
 def handle_endtag(self, tag):
 pass
 # Overridable -- handle character reference
 def handle_charref(self, name):
 pass
 # Overridable -- handle entity reference
 def handle_entityref(self, name):
 pass
 # Overridable -- handle data
 def handle_data(self, data):
 pass
 # Overridable -- handle comment
 def handle_comment(self, data):
 pass
 # Overridable -- handle declaration
 def handle_decl(self, decl):
 pass
 # Overridable -- handle processing instruction
 def handle_pi(self, data):
 pass
 def unknown_decl(self, data):
 pass
 # Internal -- helper to remove special character quoting
 def unescape(self, s):
 warnings.warn('The unescape method is deprecated and will be removed '
 'in 3.5, use html.unescape() instead.',
 DeprecationWarning, stacklevel=2)
 return unescape(s)

• Ricky Wilson: Now I'm having the same problem I was having with XML.mimidom. I'm getting errors because of broken html. It seems the standard library doesn't have a method that will parse broken html. I will have to look at the source for `htm
• Ricky Wilson: Now I'm having the same problem I was having with xml.mimidom. I'm getting errors because of broken html. It seems the standard library doesn't have a method that will parse broken html. I will have to look at the source for html.parse.HTMLParser and see if I can monkey patch it to ignore errors . Ignore my last comment
• Ricky Wilson: I wonder if I could just monkey patch handle_starttag() to ignore errors.
• Ricky Wilson: I tried monkey patching handle_startendtag() with a decorator that will cause the decorated method to ignore any errors but that didn't work at all.
• Luke: Can you use requests?

Answer 1

There are some quick wins we can have here:

• "recording" variables can be defined in this concise manner:

  self.recording_title = tag == TITLE
  self.recording_bold = tag == BOLD
  

• the anchor processing can be improved by adding some advanced unpacking:

  if tag == ANCHOR:
   for name, value, *_ in attrs:
   if name == 'href':
   if not self.resolve_links:
   self.links.append(value)
   else:
   if value.startswith('http'):
   self.links.add(value)
   else:
   self.links.add(self.root_url + value)
  

  Also, are you sure self.links.append(value) is going to work? self.links is defined as a set which does not have an .append() method.

• I would also use urljoin() to join absolute and relative URLs

• the initial value for the variables should better be defined as instance variables inside __init__() instead of being defined as class variables: more at Instance variables vs. class variables in Python

• Ricky Wilson: Thanks for the insight I have already fixed most of the issues you noticed. I reluctantly defined the initial variables as members to avoid overwriting html.parser.HTMLParser.__init__.
• alecxe: @RickyWilson okay, thanks. You can still have the __init__ implemented, but call the superclass’s __init__ from there.
• alecxe: Test comment test
• Ricky Wilson: Could you give me an example of how to overwrite __init__ by using super @alecxe
• alecxe: @RickyWilson sure, here is a sample: stackoverflow.com/a/3276119/771848.