Python 3 version of HTMLParser

This commit is contained in:
Philipp Hagemeister 2012-11-28 00:06:28 +01:00
parent 3e669f369f
commit a8156c1d2e
1 changed files with 10 additions and 6 deletions

View File

@ -2,7 +2,6 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
import gzip import gzip
import HTMLParser
import locale import locale
import os import os
import re import re
@ -41,6 +40,11 @@ try:
except NameError: # Python 2 except NameError: # Python 2
import htmlentitydefs as compat_html_entities import htmlentitydefs as compat_html_entities
try:
import html.parser as compat_html_parser
except NameError: # Python 2
import HTMLParser as compat_html_parser
try: try:
compat_str = unicode # Python 2 compat_str = unicode # Python 2
except NameError: except NameError:
@ -99,8 +103,8 @@ def htmlentity_transform(matchobj):
# Unknown entity in name, return its literal representation # Unknown entity in name, return its literal representation
return (u'&%s;' % entity) return (u'&%s;' % entity)
HTMLParser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
class IDParser(HTMLParser.HTMLParser): class IDParser(compat_html_parser.HTMLParser):
"""Modified HTMLParser that isolates a tag with the specified id""" """Modified HTMLParser that isolates a tag with the specified id"""
def __init__(self, id): def __init__(self, id):
self.id = id self.id = id
@ -110,11 +114,11 @@ class IDParser(HTMLParser.HTMLParser):
self.html = None self.html = None
self.watch_startpos = False self.watch_startpos = False
self.error_count = 0 self.error_count = 0
HTMLParser.HTMLParser.__init__(self) compat_html_parser.HTMLParser.__init__(self)
def error(self, message): def error(self, message):
if self.error_count > 10 or self.started: if self.error_count > 10 or self.started:
raise HTMLParser.HTMLParseError(message, self.getpos()) raise compat_html_parser.HTMLParseError(message, self.getpos())
self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
self.error_count += 1 self.error_count += 1
self.goahead(1) self.goahead(1)
@ -170,7 +174,7 @@ def get_element_by_id(id, html):
parser = IDParser(id) parser = IDParser(id)
try: try:
parser.loads(html) parser.loads(html)
except HTMLParser.HTMLParseError: except compat_html_parser.HTMLParseError:
pass pass
return parser.get_result() return parser.get_result()