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)
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 forhtml.parse.HTMLParserand see if I can monkey patch it to ignore errors . Ignore my last comment \$\endgroup\$handle_starttag()to ignore errors. \$\endgroup\$handle_startendtag()with adecoratorthat will cause the decorated method to ignore any errors but that didn't work at all. \$\endgroup\$requests? \$\endgroup\$