':
- depth = 0
- for piece in pieces[:-1]:
- if piece.startswith(''):
- depth -= 1
- if depth == 0:
- break
- elif piece.startswith('<') and not piece.endswith('/>'):
- depth += 1
- else:
- pieces = pieces[1:-1]
-
- # Ensure each piece is a str for Python 3
- for (i, v) in enumerate(pieces):
- if not isinstance(v, unicode):
- pieces[i] = v.decode('utf-8')
-
- output = u''.join(pieces)
- if stripWhitespace:
- output = output.strip()
- if not expectingText:
- return output
-
- # decode base64 content
- if base64 and self.contentparams.get('base64', 0):
- try:
- output = _base64decode(output)
- except binascii.Error:
- pass
- except binascii.Incomplete:
- pass
- except TypeError:
- # In Python 3, base64 takes and outputs bytes, not str
- # This may not be the most correct way to accomplish this
- output = _base64decode(output.encode('utf-8')).decode('utf-8')
-
- # resolve relative URIs
- if (element in self.can_be_relative_uri) and output:
- output = self.resolveURI(output)
-
- # decode entities within embedded markup
- if not self.contentparams.get('base64', 0):
- output = self.decodeEntities(element, output)
-
- # some feed formats require consumers to guess
- # whether the content is html or plain text
- if not self.version.startswith(u'atom') and self.contentparams.get('type') == u'text/plain':
- if self.lookslikehtml(output):
- self.contentparams['type'] = u'text/html'
-
- # remove temporary cruft from contentparams
- try:
- del self.contentparams['mode']
- except KeyError:
- pass
- try:
- del self.contentparams['base64']
- except KeyError:
- pass
-
- is_htmlish = self.mapContentType(self.contentparams.get('type', u'text/html')) in self.html_types
- # resolve relative URIs within embedded markup
- if is_htmlish and RESOLVE_RELATIVE_URIS:
- if element in self.can_contain_relative_uris:
- output = _resolveRelativeURIs(output, self.baseuri, self.encoding, self.contentparams.get('type', u'text/html'))
-
- # parse microformats
- # (must do this before sanitizing because some microformats
- # rely on elements that we sanitize)
- if PARSE_MICROFORMATS and is_htmlish and element in ['content', 'description', 'summary']:
- mfresults = _parseMicroformats(output, self.baseuri, self.encoding)
- if mfresults:
- for tag in mfresults.get('tags', []):
- self._addTag(tag['term'], tag['scheme'], tag['label'])
- for enclosure in mfresults.get('enclosures', []):
- self._start_enclosure(enclosure)
- for xfn in mfresults.get('xfn', []):
- self._addXFN(xfn['relationships'], xfn['href'], xfn['name'])
- vcard = mfresults.get('vcard')
- if vcard:
- self._getContext()['vcard'] = vcard
-
- # sanitize embedded markup
- if is_htmlish and SANITIZE_HTML:
- if element in self.can_contain_dangerous_markup:
- output = _sanitizeHTML(output, self.encoding, self.contentparams.get('type', u'text/html'))
-
- if self.encoding and not isinstance(output, unicode):
- output = output.decode(self.encoding, 'ignore')
-
- # address common error where people take data that is already
- # utf-8, presume that it is iso-8859-1, and re-encode it.
- if self.encoding in (u'utf-8', u'utf-8_INVALID_PYTHON_3') and isinstance(output, unicode):
- try:
- output = output.encode('iso-8859-1').decode('utf-8')
- except (UnicodeEncodeError, UnicodeDecodeError):
- pass
-
- # map win-1252 extensions to the proper code points
- if isinstance(output, unicode):
- output = output.translate(_cp1252)
-
- # categories/tags/keywords/whatever are handled in _end_category
- if element == 'category':
- return output
-
- if element == 'title' and -1 < self.title_depth <= self.depth:
- return output
-
- # store output in appropriate place(s)
- if self.inentry and not self.insource:
- if element == 'content':
- self.entries[-1].setdefault(element, [])
- contentparams = copy.deepcopy(self.contentparams)
- contentparams['value'] = output
- self.entries[-1][element].append(contentparams)
- elif element == 'link':
- if not self.inimage:
- # query variables in urls in link elements are improperly
- # converted from `?a=1&b=2` to `?a=1&b;=2` as if they're
- # unhandled character references. fix this special case.
- output = re.sub("&([A-Za-z0-9_]+);", "&\g<1>", output)
- self.entries[-1][element] = output
- if output:
- self.entries[-1]['links'][-1]['href'] = output
- else:
- if element == 'description':
- element = 'summary'
- old_value_depth = self.property_depth_map.setdefault(self.entries[-1], {}).get(element)
- if old_value_depth is None or self.depth <= old_value_depth:
- self.property_depth_map[self.entries[-1]][element] = self.depth
- self.entries[-1][element] = output
- if self.incontent:
- contentparams = copy.deepcopy(self.contentparams)
- contentparams['value'] = output
- self.entries[-1][element + '_detail'] = contentparams
- elif (self.infeed or self.insource):# and (not self.intextinput) and (not self.inimage):
- context = self._getContext()
- if element == 'description':
- element = 'subtitle'
- context[element] = output
- if element == 'link':
- # fix query variables; see above for the explanation
- output = re.sub("&([A-Za-z0-9_]+);", "&\g<1>", output)
- context[element] = output
- context['links'][-1]['href'] = output
- elif self.incontent:
- contentparams = copy.deepcopy(self.contentparams)
- contentparams['value'] = output
- context[element + '_detail'] = contentparams
- return output
-
- def pushContent(self, tag, attrsD, defaultContentType, expectingText):
- self.incontent += 1
- if self.lang:
- self.lang=self.lang.replace('_','-')
- self.contentparams = FeedParserDict({
- 'type': self.mapContentType(attrsD.get('type', defaultContentType)),
- 'language': self.lang,
- 'base': self.baseuri})
- self.contentparams['base64'] = self._isBase64(attrsD, self.contentparams)
- self.push(tag, expectingText)
-
- def popContent(self, tag):
- value = self.pop(tag)
- self.incontent -= 1
- self.contentparams.clear()
- return value
-
- # a number of elements in a number of RSS variants are nominally plain
- # text, but this is routinely ignored. This is an attempt to detect
- # the most common cases. As false positives often result in silent
- # data loss, this function errs on the conservative side.
- @staticmethod
- def lookslikehtml(s):
- # must have a close tag or an entity reference to qualify
- if not (re.search(r'(\w+)>',s) or re.search("?\w+;",s)):
- return
-
- # all tags must be in a restricted subset of valid HTML tags
- if filter(lambda t: t.lower() not in _HTMLSanitizer.acceptable_elements,
- re.findall(r'?(\w+)',s)):
- return
-
- # all entities must have been defined as valid HTML entities
- if filter(lambda e: e not in entitydefs.keys(), re.findall(r'&(\w+);', s)):
- return
-
- return 1
-
- def _mapToStandardPrefix(self, name):
- colonpos = name.find(':')
- if colonpos <> -1:
- prefix = name[:colonpos]
- suffix = name[colonpos+1:]
- prefix = self.namespacemap.get(prefix, prefix)
- name = prefix + ':' + suffix
- return name
-
- def _getAttribute(self, attrsD, name):
- return attrsD.get(self._mapToStandardPrefix(name))
-
- def _isBase64(self, attrsD, contentparams):
- if attrsD.get('mode', '') == 'base64':
- return 1
- if self.contentparams['type'].startswith(u'text/'):
- return 0
- if self.contentparams['type'].endswith(u'+xml'):
- return 0
- if self.contentparams['type'].endswith(u'/xml'):
- return 0
- return 1
-
- def _itsAnHrefDamnIt(self, attrsD):
- href = attrsD.get('url', attrsD.get('uri', attrsD.get('href', None)))
- if href:
- try:
- del attrsD['url']
- except KeyError:
- pass
- try:
- del attrsD['uri']
- except KeyError:
- pass
- attrsD['href'] = href
- return attrsD
-
- def _save(self, key, value, overwrite=False):
- context = self._getContext()
- if overwrite:
- context[key] = value
- else:
- context.setdefault(key, value)
-
- def _start_rss(self, attrsD):
- versionmap = {'0.91': u'rss091u',
- '0.92': u'rss092',
- '0.93': u'rss093',
- '0.94': u'rss094'}
- #If we're here then this is an RSS feed.
- #If we don't have a version or have a version that starts with something
- #other than RSS then there's been a mistake. Correct it.
- if not self.version or not self.version.startswith(u'rss'):
- attr_version = attrsD.get('version', '')
- version = versionmap.get(attr_version)
- if version:
- self.version = version
- elif attr_version.startswith('2.'):
- self.version = u'rss20'
- else:
- self.version = u'rss'
-
- def _start_channel(self, attrsD):
- self.infeed = 1
- self._cdf_common(attrsD)
-
- def _cdf_common(self, attrsD):
- if 'lastmod' in attrsD:
- self._start_modified({})
- self.elementstack[-1][-1] = attrsD['lastmod']
- self._end_modified()
- if 'href' in attrsD:
- self._start_link({})
- self.elementstack[-1][-1] = attrsD['href']
- self._end_link()
-
- def _start_feed(self, attrsD):
- self.infeed = 1
- versionmap = {'0.1': u'atom01',
- '0.2': u'atom02',
- '0.3': u'atom03'}
- if not self.version:
- attr_version = attrsD.get('version')
- version = versionmap.get(attr_version)
- if version:
- self.version = version
- else:
- self.version = u'atom'
-
- def _end_channel(self):
- self.infeed = 0
- _end_feed = _end_channel
-
- def _start_image(self, attrsD):
- context = self._getContext()
- if not self.inentry:
- context.setdefault('image', FeedParserDict())
- self.inimage = 1
- self.title_depth = -1
- self.push('image', 0)
-
- def _end_image(self):
- self.pop('image')
- self.inimage = 0
-
- def _start_textinput(self, attrsD):
- context = self._getContext()
- context.setdefault('textinput', FeedParserDict())
- self.intextinput = 1
- self.title_depth = -1
- self.push('textinput', 0)
- _start_textInput = _start_textinput
-
- def _end_textinput(self):
- self.pop('textinput')
- self.intextinput = 0
- _end_textInput = _end_textinput
-
- def _start_author(self, attrsD):
- self.inauthor = 1
- self.push('author', 1)
- # Append a new FeedParserDict when expecting an author
- context = self._getContext()
- context.setdefault('authors', [])
- context['authors'].append(FeedParserDict())
- _start_managingeditor = _start_author
- _start_dc_author = _start_author
- _start_dc_creator = _start_author
- _start_itunes_author = _start_author
-
- def _end_author(self):
- self.pop('author')
- self.inauthor = 0
- self._sync_author_detail()
- _end_managingeditor = _end_author
- _end_dc_author = _end_author
- _end_dc_creator = _end_author
- _end_itunes_author = _end_author
-
- def _start_itunes_owner(self, attrsD):
- self.inpublisher = 1
- self.push('publisher', 0)
-
- def _end_itunes_owner(self):
- self.pop('publisher')
- self.inpublisher = 0
- self._sync_author_detail('publisher')
-
- def _start_contributor(self, attrsD):
- self.incontributor = 1
- context = self._getContext()
- context.setdefault('contributors', [])
- context['contributors'].append(FeedParserDict())
- self.push('contributor', 0)
-
- def _end_contributor(self):
- self.pop('contributor')
- self.incontributor = 0
-
- def _start_dc_contributor(self, attrsD):
- self.incontributor = 1
- context = self._getContext()
- context.setdefault('contributors', [])
- context['contributors'].append(FeedParserDict())
- self.push('name', 0)
-
- def _end_dc_contributor(self):
- self._end_name()
- self.incontributor = 0
-
- def _start_name(self, attrsD):
- self.push('name', 0)
- _start_itunes_name = _start_name
-
- def _end_name(self):
- value = self.pop('name')
- if self.inpublisher:
- self._save_author('name', value, 'publisher')
- elif self.inauthor:
- self._save_author('name', value)
- elif self.incontributor:
- self._save_contributor('name', value)
- elif self.intextinput:
- context = self._getContext()
- context['name'] = value
- _end_itunes_name = _end_name
-
- def _start_width(self, attrsD):
- self.push('width', 0)
-
- def _end_width(self):
- value = self.pop('width')
- try:
- value = int(value)
- except ValueError:
- value = 0
- if self.inimage:
- context = self._getContext()
- context['width'] = value
-
- def _start_height(self, attrsD):
- self.push('height', 0)
-
- def _end_height(self):
- value = self.pop('height')
- try:
- value = int(value)
- except ValueError:
- value = 0
- if self.inimage:
- context = self._getContext()
- context['height'] = value
-
- def _start_url(self, attrsD):
- self.push('href', 1)
- _start_homepage = _start_url
- _start_uri = _start_url
-
- def _end_url(self):
- value = self.pop('href')
- if self.inauthor:
- self._save_author('href', value)
- elif self.incontributor:
- self._save_contributor('href', value)
- _end_homepage = _end_url
- _end_uri = _end_url
-
- def _start_email(self, attrsD):
- self.push('email', 0)
- _start_itunes_email = _start_email
-
- def _end_email(self):
- value = self.pop('email')
- if self.inpublisher:
- self._save_author('email', value, 'publisher')
- elif self.inauthor:
- self._save_author('email', value)
- elif self.incontributor:
- self._save_contributor('email', value)
- _end_itunes_email = _end_email
-
- def _getContext(self):
- if self.insource:
- context = self.sourcedata
- elif self.inimage and 'image' in self.feeddata:
- context = self.feeddata['image']
- elif self.intextinput:
- context = self.feeddata['textinput']
- elif self.inentry:
- context = self.entries[-1]
- else:
- context = self.feeddata
- return context
-
- def _save_author(self, key, value, prefix='author'):
- context = self._getContext()
- context.setdefault(prefix + '_detail', FeedParserDict())
- context[prefix + '_detail'][key] = value
- self._sync_author_detail()
- context.setdefault('authors', [FeedParserDict()])
- context['authors'][-1][key] = value
-
- def _save_contributor(self, key, value):
- context = self._getContext()
- context.setdefault('contributors', [FeedParserDict()])
- context['contributors'][-1][key] = value
-
- def _sync_author_detail(self, key='author'):
- context = self._getContext()
- detail = context.get('%s_detail' % key)
- if detail:
- name = detail.get('name')
- email = detail.get('email')
- if name and email:
- context[key] = u'%s (%s)' % (name, email)
- elif name:
- context[key] = name
- elif email:
- context[key] = email
- else:
- author, email = context.get(key), None
- if not author:
- return
- emailmatch = re.search(ur'''(([a-zA-Z0-9\_\-\.\+]+)@((\[[0-9]{1,3}\.[0-9]{1,3}\.[0-9]{1,3}\.)|(([a-zA-Z0-9\-]+\.)+))([a-zA-Z]{2,4}|[0-9]{1,3})(\]?))(\?subject=\S+)?''', author)
- if emailmatch:
- email = emailmatch.group(0)
- # probably a better way to do the following, but it passes all the tests
- author = author.replace(email, u'')
- author = author.replace(u'()', u'')
- author = author.replace(u'<>', u'')
- author = author.replace(u'<>', u'')
- author = author.strip()
- if author and (author[0] == u'('):
- author = author[1:]
- if author and (author[-1] == u')'):
- author = author[:-1]
- author = author.strip()
- if author or email:
- context.setdefault('%s_detail' % key, FeedParserDict())
- if author:
- context['%s_detail' % key]['name'] = author
- if email:
- context['%s_detail' % key]['email'] = email
-
- def _start_subtitle(self, attrsD):
- self.pushContent('subtitle', attrsD, u'text/plain', 1)
- _start_tagline = _start_subtitle
- _start_itunes_subtitle = _start_subtitle
-
- def _end_subtitle(self):
- self.popContent('subtitle')
- _end_tagline = _end_subtitle
- _end_itunes_subtitle = _end_subtitle
-
- def _start_rights(self, attrsD):
- self.pushContent('rights', attrsD, u'text/plain', 1)
- _start_dc_rights = _start_rights
- _start_copyright = _start_rights
-
- def _end_rights(self):
- self.popContent('rights')
- _end_dc_rights = _end_rights
- _end_copyright = _end_rights
-
- def _start_item(self, attrsD):
- self.entries.append(FeedParserDict())
- self.push('item', 0)
- self.inentry = 1
- self.guidislink = 0
- self.title_depth = -1
- id = self._getAttribute(attrsD, 'rdf:about')
- if id:
- context = self._getContext()
- context['id'] = id
- self._cdf_common(attrsD)
- _start_entry = _start_item
-
- def _end_item(self):
- self.pop('item')
- self.inentry = 0
- _end_entry = _end_item
-
- def _start_dc_language(self, attrsD):
- self.push('language', 1)
- _start_language = _start_dc_language
-
- def _end_dc_language(self):
- self.lang = self.pop('language')
- _end_language = _end_dc_language
-
- def _start_dc_publisher(self, attrsD):
- self.push('publisher', 1)
- _start_webmaster = _start_dc_publisher
-
- def _end_dc_publisher(self):
- self.pop('publisher')
- self._sync_author_detail('publisher')
- _end_webmaster = _end_dc_publisher
-
- def _start_published(self, attrsD):
- self.push('published', 1)
- _start_dcterms_issued = _start_published
- _start_issued = _start_published
- _start_pubdate = _start_published
-
- def _end_published(self):
- value = self.pop('published')
- self._save('published_parsed', _parse_date(value), overwrite=True)
- _end_dcterms_issued = _end_published
- _end_issued = _end_published
- _end_pubdate = _end_published
-
- def _start_updated(self, attrsD):
- self.push('updated', 1)
- _start_modified = _start_updated
- _start_dcterms_modified = _start_updated
- _start_dc_date = _start_updated
- _start_lastbuilddate = _start_updated
-
- def _end_updated(self):
- value = self.pop('updated')
- parsed_value = _parse_date(value)
- self._save('updated_parsed', parsed_value, overwrite=True)
- _end_modified = _end_updated
- _end_dcterms_modified = _end_updated
- _end_dc_date = _end_updated
- _end_lastbuilddate = _end_updated
-
- def _start_created(self, attrsD):
- self.push('created', 1)
- _start_dcterms_created = _start_created
-
- def _end_created(self):
- value = self.pop('created')
- self._save('created_parsed', _parse_date(value), overwrite=True)
- _end_dcterms_created = _end_created
-
- def _start_expirationdate(self, attrsD):
- self.push('expired', 1)
-
- def _end_expirationdate(self):
- self._save('expired_parsed', _parse_date(self.pop('expired')), overwrite=True)
-
- def _start_cc_license(self, attrsD):
- context = self._getContext()
- value = self._getAttribute(attrsD, 'rdf:resource')
- attrsD = FeedParserDict()
- attrsD['rel'] = u'license'
- if value:
- attrsD['href']=value
- context.setdefault('links', []).append(attrsD)
-
- def _start_creativecommons_license(self, attrsD):
- self.push('license', 1)
- _start_creativeCommons_license = _start_creativecommons_license
-
- def _end_creativecommons_license(self):
- value = self.pop('license')
- context = self._getContext()
- attrsD = FeedParserDict()
- attrsD['rel'] = u'license'
- if value:
- attrsD['href'] = value
- context.setdefault('links', []).append(attrsD)
- del context['license']
- _end_creativeCommons_license = _end_creativecommons_license
-
- def _addXFN(self, relationships, href, name):
- context = self._getContext()
- xfn = context.setdefault('xfn', [])
- value = FeedParserDict({'relationships': relationships, 'href': href, 'name': name})
- if value not in xfn:
- xfn.append(value)
-
- def _addTag(self, term, scheme, label):
- context = self._getContext()
- tags = context.setdefault('tags', [])
- if (not term) and (not scheme) and (not label):
- return
- value = FeedParserDict({'term': term, 'scheme': scheme, 'label': label})
- if value not in tags:
- tags.append(value)
-
- def _start_category(self, attrsD):
- term = attrsD.get('term')
- scheme = attrsD.get('scheme', attrsD.get('domain'))
- label = attrsD.get('label')
- self._addTag(term, scheme, label)
- self.push('category', 1)
- _start_dc_subject = _start_category
- _start_keywords = _start_category
-
- def _start_media_category(self, attrsD):
- attrsD.setdefault('scheme', u'http://search.yahoo.com/mrss/category_schema')
- self._start_category(attrsD)
-
- def _end_itunes_keywords(self):
- for term in self.pop('itunes_keywords').split(','):
- if term.strip():
- self._addTag(term.strip(), u'http://www.itunes.com/', None)
-
- def _start_itunes_category(self, attrsD):
- self._addTag(attrsD.get('text'), u'http://www.itunes.com/', None)
- self.push('category', 1)
-
- def _end_category(self):
- value = self.pop('category')
- if not value:
- return
- context = self._getContext()
- tags = context['tags']
- if value and len(tags) and not tags[-1]['term']:
- tags[-1]['term'] = value
- else:
- self._addTag(value, None, None)
- _end_dc_subject = _end_category
- _end_keywords = _end_category
- _end_itunes_category = _end_category
- _end_media_category = _end_category
-
- def _start_cloud(self, attrsD):
- self._getContext()['cloud'] = FeedParserDict(attrsD)
-
- def _start_link(self, attrsD):
- attrsD.setdefault('rel', u'alternate')
- if attrsD['rel'] == u'self':
- attrsD.setdefault('type', u'application/atom+xml')
- else:
- attrsD.setdefault('type', u'text/html')
- context = self._getContext()
- attrsD = self._itsAnHrefDamnIt(attrsD)
- if 'href' in attrsD:
- attrsD['href'] = self.resolveURI(attrsD['href'])
- expectingText = self.infeed or self.inentry or self.insource
- context.setdefault('links', [])
- if not (self.inentry and self.inimage):
- context['links'].append(FeedParserDict(attrsD))
- if 'href' in attrsD:
- expectingText = 0
- if (attrsD.get('rel') == u'alternate') and (self.mapContentType(attrsD.get('type')) in self.html_types):
- context['link'] = attrsD['href']
- else:
- self.push('link', expectingText)
-
- def _end_link(self):
- value = self.pop('link')
-
- def _start_guid(self, attrsD):
- self.guidislink = (attrsD.get('ispermalink', 'true') == 'true')
- self.push('id', 1)
- _start_id = _start_guid
-
- def _end_guid(self):
- value = self.pop('id')
- self._save('guidislink', self.guidislink and 'link' not in self._getContext())
- if self.guidislink:
- # guid acts as link, but only if 'ispermalink' is not present or is 'true',
- # and only if the item doesn't already have a link element
- self._save('link', value)
- _end_id = _end_guid
-
- def _start_title(self, attrsD):
- if self.svgOK:
- return self.unknown_starttag('title', attrsD.items())
- self.pushContent('title', attrsD, u'text/plain', self.infeed or self.inentry or self.insource)
- _start_dc_title = _start_title
- _start_media_title = _start_title
-
- def _end_title(self):
- if self.svgOK:
- return
- value = self.popContent('title')
- if not value:
- return
- self.title_depth = self.depth
- _end_dc_title = _end_title
-
- def _end_media_title(self):
- title_depth = self.title_depth
- self._end_title()
- self.title_depth = title_depth
-
- def _start_description(self, attrsD):
- context = self._getContext()
- if 'summary' in context:
- self._summaryKey = 'content'
- self._start_content(attrsD)
- else:
- self.pushContent('description', attrsD, u'text/html', self.infeed or self.inentry or self.insource)
- _start_dc_description = _start_description
-
- def _start_abstract(self, attrsD):
- self.pushContent('description', attrsD, u'text/plain', self.infeed or self.inentry or self.insource)
-
- def _end_description(self):
- if self._summaryKey == 'content':
- self._end_content()
- else:
- value = self.popContent('description')
- self._summaryKey = None
- _end_abstract = _end_description
- _end_dc_description = _end_description
-
- def _start_info(self, attrsD):
- self.pushContent('info', attrsD, u'text/plain', 1)
- _start_feedburner_browserfriendly = _start_info
-
- def _end_info(self):
- self.popContent('info')
- _end_feedburner_browserfriendly = _end_info
-
- def _start_generator(self, attrsD):
- if attrsD:
- attrsD = self._itsAnHrefDamnIt(attrsD)
- if 'href' in attrsD:
- attrsD['href'] = self.resolveURI(attrsD['href'])
- self._getContext()['generator_detail'] = FeedParserDict(attrsD)
- self.push('generator', 1)
-
- def _end_generator(self):
- value = self.pop('generator')
- context = self._getContext()
- if 'generator_detail' in context:
- context['generator_detail']['name'] = value
-
- def _start_admin_generatoragent(self, attrsD):
- self.push('generator', 1)
- value = self._getAttribute(attrsD, 'rdf:resource')
- if value:
- self.elementstack[-1][2].append(value)
- self.pop('generator')
- self._getContext()['generator_detail'] = FeedParserDict({'href': value})
-
- def _start_admin_errorreportsto(self, attrsD):
- self.push('errorreportsto', 1)
- value = self._getAttribute(attrsD, 'rdf:resource')
- if value:
- self.elementstack[-1][2].append(value)
- self.pop('errorreportsto')
-
- def _start_summary(self, attrsD):
- context = self._getContext()
- if 'summary' in context:
- self._summaryKey = 'content'
- self._start_content(attrsD)
- else:
- self._summaryKey = 'summary'
- self.pushContent(self._summaryKey, attrsD, u'text/plain', 1)
- _start_itunes_summary = _start_summary
-
- def _end_summary(self):
- if self._summaryKey == 'content':
- self._end_content()
- else:
- self.popContent(self._summaryKey or 'summary')
- self._summaryKey = None
- _end_itunes_summary = _end_summary
-
- def _start_enclosure(self, attrsD):
- attrsD = self._itsAnHrefDamnIt(attrsD)
- context = self._getContext()
- attrsD['rel'] = u'enclosure'
- context.setdefault('links', []).append(FeedParserDict(attrsD))
-
- def _start_source(self, attrsD):
- if 'url' in attrsD:
- # This means that we're processing a source element from an RSS 2.0 feed
- self.sourcedata['href'] = attrsD[u'url']
- self.push('source', 1)
- self.insource = 1
- self.title_depth = -1
-
- def _end_source(self):
- self.insource = 0
- value = self.pop('source')
- if value:
- self.sourcedata['title'] = value
- self._getContext()['source'] = copy.deepcopy(self.sourcedata)
- self.sourcedata.clear()
-
- def _start_content(self, attrsD):
- self.pushContent('content', attrsD, u'text/plain', 1)
- src = attrsD.get('src')
- if src:
- self.contentparams['src'] = src
- self.push('content', 1)
-
- def _start_body(self, attrsD):
- self.pushContent('content', attrsD, u'application/xhtml+xml', 1)
- _start_xhtml_body = _start_body
-
- def _start_content_encoded(self, attrsD):
- self.pushContent('content', attrsD, u'text/html', 1)
- _start_fullitem = _start_content_encoded
-
- def _end_content(self):
- copyToSummary = self.mapContentType(self.contentparams.get('type')) in ([u'text/plain'] + self.html_types)
- value = self.popContent('content')
- if copyToSummary:
- self._save('summary', value)
-
- _end_body = _end_content
- _end_xhtml_body = _end_content
- _end_content_encoded = _end_content
- _end_fullitem = _end_content
-
- def _start_itunes_image(self, attrsD):
- self.push('itunes_image', 0)
- if attrsD.get('href'):
- self._getContext()['image'] = FeedParserDict({'href': attrsD.get('href')})
- _start_itunes_link = _start_itunes_image
-
- def _end_itunes_block(self):
- value = self.pop('itunes_block', 0)
- self._getContext()['itunes_block'] = (value == 'yes') and 1 or 0
-
- def _end_itunes_explicit(self):
- value = self.pop('itunes_explicit', 0)
- # Convert 'yes' -> True, 'clean' to False, and any other value to None
- # False and None both evaluate as False, so the difference can be ignored
- # by applications that only need to know if the content is explicit.
- self._getContext()['itunes_explicit'] = (None, False, True)[(value == 'yes' and 2) or value == 'clean' or 0]
-
- def _start_media_content(self, attrsD):
- context = self._getContext()
- context.setdefault('media_content', [])
- context['media_content'].append(attrsD)
-
- def _start_media_thumbnail(self, attrsD):
- context = self._getContext()
- context.setdefault('media_thumbnail', [])
- self.push('url', 1) # new
- context['media_thumbnail'].append(attrsD)
-
- def _end_media_thumbnail(self):
- url = self.pop('url')
- context = self._getContext()
- if url != None and len(url.strip()) != 0:
- if 'url' not in context['media_thumbnail'][-1]:
- context['media_thumbnail'][-1]['url'] = url
-
- def _start_media_player(self, attrsD):
- self.push('media_player', 0)
- self._getContext()['media_player'] = FeedParserDict(attrsD)
-
- def _end_media_player(self):
- value = self.pop('media_player')
- context = self._getContext()
- context['media_player']['content'] = value
-
- def _start_newlocation(self, attrsD):
- self.push('newlocation', 1)
-
- def _end_newlocation(self):
- url = self.pop('newlocation')
- context = self._getContext()
- # don't set newlocation if the context isn't right
- if context is not self.feeddata:
- return
- context['newlocation'] = _makeSafeAbsoluteURI(self.baseuri, url.strip())
-
-if _XML_AVAILABLE:
- class _StrictFeedParser(_FeedParserMixin, xml.sax.handler.ContentHandler):
- def __init__(self, baseuri, baselang, encoding):
- xml.sax.handler.ContentHandler.__init__(self)
- _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
- self.bozo = 0
- self.exc = None
- self.decls = {}
-
- def startPrefixMapping(self, prefix, uri):
- if not uri:
- return
- # Jython uses '' instead of None; standardize on None
- prefix = prefix or None
- self.trackNamespace(prefix, uri)
- if prefix and uri == 'http://www.w3.org/1999/xlink':
- self.decls['xmlns:' + prefix] = uri
-
- def startElementNS(self, name, qname, attrs):
- namespace, localname = name
- lowernamespace = str(namespace or '').lower()
- if lowernamespace.find(u'backend.userland.com/rss') <> -1:
- # match any backend.userland.com namespace
- namespace = u'http://backend.userland.com/rss'
- lowernamespace = namespace
- if qname and qname.find(':') > 0:
- givenprefix = qname.split(':')[0]
- else:
- givenprefix = None
- prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
- if givenprefix and (prefix == None or (prefix == '' and lowernamespace == '')) and givenprefix not in self.namespacesInUse:
- raise UndeclaredNamespace, "'%s' is not associated with a namespace" % givenprefix
- localname = str(localname).lower()
-
- # qname implementation is horribly broken in Python 2.1 (it
- # doesn't report any), and slightly broken in Python 2.2 (it
- # doesn't report the xml: namespace). So we match up namespaces
- # with a known list first, and then possibly override them with
- # the qnames the SAX parser gives us (if indeed it gives us any
- # at all). Thanks to MatejC for helping me test this and
- # tirelessly telling me that it didn't work yet.
- attrsD, self.decls = self.decls, {}
- if localname=='math' and namespace=='http://www.w3.org/1998/Math/MathML':
- attrsD['xmlns']=namespace
- if localname=='svg' and namespace=='http://www.w3.org/2000/svg':
- attrsD['xmlns']=namespace
-
- if prefix:
- localname = prefix.lower() + ':' + localname
- elif namespace and not qname: #Expat
- for name,value in self.namespacesInUse.items():
- if name and value == namespace:
- localname = name + ':' + localname
- break
-
- for (namespace, attrlocalname), attrvalue in attrs.items():
- lowernamespace = (namespace or '').lower()
- prefix = self._matchnamespaces.get(lowernamespace, '')
- if prefix:
- attrlocalname = prefix + ':' + attrlocalname
- attrsD[str(attrlocalname).lower()] = attrvalue
- for qname in attrs.getQNames():
- attrsD[str(qname).lower()] = attrs.getValueByQName(qname)
- self.unknown_starttag(localname, attrsD.items())
-
- def characters(self, text):
- self.handle_data(text)
-
- def endElementNS(self, name, qname):
- namespace, localname = name
- lowernamespace = str(namespace or '').lower()
- if qname and qname.find(':') > 0:
- givenprefix = qname.split(':')[0]
- else:
- givenprefix = ''
- prefix = self._matchnamespaces.get(lowernamespace, givenprefix)
- if prefix:
- localname = prefix + ':' + localname
- elif namespace and not qname: #Expat
- for name,value in self.namespacesInUse.items():
- if name and value == namespace:
- localname = name + ':' + localname
- break
- localname = str(localname).lower()
- self.unknown_endtag(localname)
-
- def error(self, exc):
- self.bozo = 1
- self.exc = exc
-
- # drv_libxml2 calls warning() in some cases
- warning = error
-
- def fatalError(self, exc):
- self.error(exc)
- raise exc
-
-class _BaseHTMLProcessor(sgmllib.SGMLParser):
- special = re.compile('''[<>'"]''')
- bare_ampersand = re.compile("&(?!#\d+;|#x[0-9a-fA-F]+;|\w+;)")
- elements_no_end_tag = set([
- 'area', 'base', 'basefont', 'br', 'col', 'command', 'embed', 'frame',
- 'hr', 'img', 'input', 'isindex', 'keygen', 'link', 'meta', 'param',
- 'source', 'track', 'wbr'
- ])
-
- def __init__(self, encoding, _type):
- self.encoding = encoding
- self._type = _type
- sgmllib.SGMLParser.__init__(self)
-
- def reset(self):
- self.pieces = []
- sgmllib.SGMLParser.reset(self)
-
- def _shorttag_replace(self, match):
- tag = match.group(1)
- if tag in self.elements_no_end_tag:
- return '<' + tag + ' />'
- else:
- return '<' + tag + '>' + tag + '>'
-
- # By declaring these methods and overriding their compiled code
- # with the code from sgmllib, the original code will execute in
- # feedparser's scope instead of sgmllib's. This means that the
- # `tagfind` and `charref` regular expressions will be found as
- # they're declared above, not as they're declared in sgmllib.
- def goahead(self, i):
- pass
- goahead.func_code = sgmllib.SGMLParser.goahead.func_code
-
- def __parse_starttag(self, i):
- pass
- __parse_starttag.func_code = sgmllib.SGMLParser.parse_starttag.func_code
-
- def parse_starttag(self,i):
- j = self.__parse_starttag(i)
- if self._type == 'application/xhtml+xml':
- if j>2 and self.rawdata[j-2:j]=='/>':
- self.unknown_endtag(self.lasttag)
- return j
-
- def feed(self, data):
- data = re.compile(r'\s]+?)\s*/>', self._shorttag_replace, data)
- data = data.replace(''', "'")
- data = data.replace('"', '"')
- try:
- bytes
- if bytes is str:
- raise NameError
- self.encoding = self.encoding + u'_INVALID_PYTHON_3'
- except NameError:
- if self.encoding and isinstance(data, unicode):
- data = data.encode(self.encoding)
- sgmllib.SGMLParser.feed(self, data)
- sgmllib.SGMLParser.close(self)
-
- def normalize_attrs(self, attrs):
- if not attrs:
- return attrs
- # utility method to be called by descendants
- attrs = dict([(k.lower(), v) for k, v in attrs]).items()
- attrs = [(k, k in ('rel', 'type') and v.lower() or v) for k, v in attrs]
- attrs.sort()
- return attrs
-
- def unknown_starttag(self, tag, attrs):
- # called for each start tag
- # attrs is a list of (attr, value) tuples
- # e.g. for
, tag='pre', attrs=[('class', 'screen')]
- uattrs = []
- strattrs=''
- if attrs:
- for key, value in attrs:
- value=value.replace('>','>').replace('<','<').replace('"','"')
- value = self.bare_ampersand.sub("&", value)
- # thanks to Kevin Marks for this breathtaking hack to deal with (valid) high-bit attribute values in UTF-8 feeds
- if not isinstance(value, unicode):
- value = value.decode(self.encoding, 'ignore')
- try:
- # Currently, in Python 3 the key is already a str, and cannot be decoded again
- uattrs.append((unicode(key, self.encoding), value))
- except TypeError:
- uattrs.append((key, value))
- strattrs = u''.join([u' %s="%s"' % (key, value) for key, value in uattrs])
- if self.encoding:
- try:
- strattrs = strattrs.encode(self.encoding)
- except (UnicodeEncodeError, LookupError):
- pass
- if tag in self.elements_no_end_tag:
- self.pieces.append('<%s%s />' % (tag, strattrs))
- else:
- self.pieces.append('<%s%s>' % (tag, strattrs))
-
- def unknown_endtag(self, tag):
- # called for each end tag, e.g. for
, tag will be 'pre'
- # Reconstruct the original end tag.
- if tag not in self.elements_no_end_tag:
- self.pieces.append("%s>" % tag)
-
- def handle_charref(self, ref):
- # called for each character reference, e.g. for ' ', ref will be '160'
- # Reconstruct the original character reference.
- if ref.startswith('x'):
- value = int(ref[1:], 16)
- else:
- value = int(ref)
-
- if value in _cp1252:
- self.pieces.append('%s;' % hex(ord(_cp1252[value]))[1:])
- else:
- self.pieces.append('%s;' % ref)
-
- def handle_entityref(self, ref):
- # called for each entity reference, e.g. for '©', ref will be 'copy'
- # Reconstruct the original entity reference.
- if ref in name2codepoint or ref == 'apos':
- self.pieces.append('&%s;' % ref)
- else:
- self.pieces.append('&%s' % ref)
-
- 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.
- # Reconstruct the original comment.
- self.pieces.append('' % text)
-
- def handle_pi(self, text):
- # called for each processing instruction, e.g.
- # Reconstruct original processing instruction.
- self.pieces.append('%s>' % text)
-
- def handle_decl(self, text):
- # called for the DOCTYPE, if present, e.g.
- #
- # Reconstruct original DOCTYPE
- self.pieces.append('' % text)
-
- _new_declname_match = re.compile(r'[a-zA-Z][-_.a-zA-Z0-9:]*\s*').match
- def _scan_name(self, i, declstartpos):
- rawdata = self.rawdata
- n = len(rawdata)
- if i == n:
- return None, -1
- m = self._new_declname_match(rawdata, i)
- if m:
- s = m.group()
- name = s.strip()
- if (i + len(s)) == n:
- return None, -1 # end of buffer
- return name.lower(), m.end()
- else:
- self.handle_data(rawdata)
-# self.updatepos(declstartpos, i)
- return None, -1
-
- def convert_charref(self, name):
- return '%s;' % name
-
- def convert_entityref(self, name):
- return '&%s;' % name
-
- def output(self):
- '''Return processed HTML as a single string'''
- return ''.join([str(p) for p in self.pieces])
-
- def parse_declaration(self, i):
- try:
- return sgmllib.SGMLParser.parse_declaration(self, i)
- except sgmllib.SGMLParseError:
- # escape the doctype declaration and continue parsing
- self.handle_data('<')
- return i+1
-
-class _LooseFeedParser(_FeedParserMixin, _BaseHTMLProcessor):
- def __init__(self, baseuri, baselang, encoding, entities):
- sgmllib.SGMLParser.__init__(self)
- _FeedParserMixin.__init__(self, baseuri, baselang, encoding)
- _BaseHTMLProcessor.__init__(self, encoding, 'application/xhtml+xml')
- self.entities=entities
-
- def decodeEntities(self, element, data):
- data = data.replace('<', '<')
- data = data.replace('<', '<')
- data = data.replace('<', '<')
- data = data.replace('>', '>')
- data = data.replace('>', '>')
- data = data.replace('>', '>')
- data = data.replace('&', '&')
- data = data.replace('&', '&')
- data = data.replace('"', '"')
- data = data.replace('"', '"')
- data = data.replace(''', ''')
- data = data.replace(''', ''')
- if not self.contentparams.get('type', u'xml').endswith(u'xml'):
- data = data.replace('<', '<')
- data = data.replace('>', '>')
- data = data.replace('&', '&')
- data = data.replace('"', '"')
- data = data.replace(''', "'")
- return data
-
- def strattrs(self, attrs):
- return ''.join([' %s="%s"' % (n,v.replace('"','"')) for n,v in attrs])
-
-class _MicroformatsParser:
- STRING = 1
- DATE = 2
- URI = 3
- NODE = 4
- EMAIL = 5
-
- known_xfn_relationships = set(['contact', 'acquaintance', 'friend', 'met', 'co-worker', 'coworker', 'colleague', 'co-resident', 'coresident', 'neighbor', 'child', 'parent', 'sibling', 'brother', 'sister', 'spouse', 'wife', 'husband', 'kin', 'relative', 'muse', 'crush', 'date', 'sweetheart', 'me'])
- known_binary_extensions = set(['zip','rar','exe','gz','tar','tgz','tbz2','bz2','z','7z','dmg','img','sit','sitx','hqx','deb','rpm','bz2','jar','rar','iso','bin','msi','mp2','mp3','ogg','ogm','mp4','m4v','m4a','avi','wma','wmv'])
-
- def __init__(self, data, baseuri, encoding):
- self.document = BeautifulSoup.BeautifulSoup(data)
- self.baseuri = baseuri
- self.encoding = encoding
- if isinstance(data, unicode):
- data = data.encode(encoding)
- self.tags = []
- self.enclosures = []
- self.xfn = []
- self.vcard = None
-
- def vcardEscape(self, s):
- if isinstance(s, basestring):
- s = s.replace(',', '\\,').replace(';', '\\;').replace('\n', '\\n')
- return s
-
- def vcardFold(self, s):
- s = re.sub(';+$', '', s)
- sFolded = ''
- iMax = 75
- sPrefix = ''
- while len(s) > iMax:
- sFolded += sPrefix + s[:iMax] + '\n'
- s = s[iMax:]
- sPrefix = ' '
- iMax = 74
- sFolded += sPrefix + s
- return sFolded
-
- def normalize(self, s):
- return re.sub(r'\s+', ' ', s).strip()
-
- def unique(self, aList):
- results = []
- for element in aList:
- if element not in results:
- results.append(element)
- return results
-
- def toISO8601(self, dt):
- return time.strftime('%Y-%m-%dT%H:%M:%SZ', dt)
-
- def getPropertyValue(self, elmRoot, sProperty, iPropertyType=4, bAllowMultiple=0, bAutoEscape=0):
- all = lambda x: 1
- sProperty = sProperty.lower()
- bFound = 0
- bNormalize = 1
- propertyMatch = {'class': re.compile(r'\b%s\b' % sProperty)}
- if bAllowMultiple and (iPropertyType != self.NODE):
- snapResults = []
- containers = elmRoot(['ul', 'ol'], propertyMatch)
- for container in containers:
- snapResults.extend(container('li'))
- bFound = (len(snapResults) != 0)
- if not bFound:
- snapResults = elmRoot(all, propertyMatch)
- bFound = (len(snapResults) != 0)
- if (not bFound) and (sProperty == 'value'):
- snapResults = elmRoot('pre')
- bFound = (len(snapResults) != 0)
- bNormalize = not bFound
- if not bFound:
- snapResults = [elmRoot]
- bFound = (len(snapResults) != 0)
- arFilter = []
- if sProperty == 'vcard':
- snapFilter = elmRoot(all, propertyMatch)
- for node in snapFilter:
- if node.findParent(all, propertyMatch):
- arFilter.append(node)
- arResults = []
- for node in snapResults:
- if node not in arFilter:
- arResults.append(node)
- bFound = (len(arResults) != 0)
- if not bFound:
- if bAllowMultiple:
- return []
- elif iPropertyType == self.STRING:
- return ''
- elif iPropertyType == self.DATE:
- return None
- elif iPropertyType == self.URI:
- return ''
- elif iPropertyType == self.NODE:
- return None
- else:
- return None
- arValues = []
- for elmResult in arResults:
- sValue = None
- if iPropertyType == self.NODE:
- if bAllowMultiple:
- arValues.append(elmResult)
- continue
- else:
- return elmResult
- sNodeName = elmResult.name.lower()
- if (iPropertyType == self.EMAIL) and (sNodeName == 'a'):
- sValue = (elmResult.get('href') or '').split('mailto:').pop().split('?')[0]
- if sValue:
- sValue = bNormalize and self.normalize(sValue) or sValue.strip()
- if (not sValue) and (sNodeName == 'abbr'):
- sValue = elmResult.get('title')
- if sValue:
- sValue = bNormalize and self.normalize(sValue) or sValue.strip()
- if (not sValue) and (iPropertyType == self.URI):
- if sNodeName == 'a':
- sValue = elmResult.get('href')
- elif sNodeName == 'img':
- sValue = elmResult.get('src')
- elif sNodeName == 'object':
- sValue = elmResult.get('data')
- if sValue:
- sValue = bNormalize and self.normalize(sValue) or sValue.strip()
- if (not sValue) and (sNodeName == 'img'):
- sValue = elmResult.get('alt')
- if sValue:
- sValue = bNormalize and self.normalize(sValue) or sValue.strip()
- if not sValue:
- sValue = elmResult.renderContents()
- sValue = re.sub(r'<\S[^>]*>', '', sValue)
- sValue = sValue.replace('\r\n', '\n')
- sValue = sValue.replace('\r', '\n')
- if sValue:
- sValue = bNormalize and self.normalize(sValue) or sValue.strip()
- if not sValue:
- continue
- if iPropertyType == self.DATE:
- sValue = _parse_date_iso8601(sValue)
- if bAllowMultiple:
- arValues.append(bAutoEscape and self.vcardEscape(sValue) or sValue)
- else:
- return bAutoEscape and self.vcardEscape(sValue) or sValue
- return arValues
-
- def findVCards(self, elmRoot, bAgentParsing=0):
- sVCards = ''
-
- if not bAgentParsing:
- arCards = self.getPropertyValue(elmRoot, 'vcard', bAllowMultiple=1)
- else:
- arCards = [elmRoot]
-
- for elmCard in arCards:
- arLines = []
-
- def processSingleString(sProperty):
- sValue = self.getPropertyValue(elmCard, sProperty, self.STRING, bAutoEscape=1).decode(self.encoding)
- if sValue:
- arLines.append(self.vcardFold(sProperty.upper() + ':' + sValue))
- return sValue or u''
-
- def processSingleURI(sProperty):
- sValue = self.getPropertyValue(elmCard, sProperty, self.URI)
- if sValue:
- sContentType = ''
- sEncoding = ''
- sValueKey = ''
- if sValue.startswith('data:'):
- sEncoding = ';ENCODING=b'
- sContentType = sValue.split(';')[0].split('/').pop()
- sValue = sValue.split(',', 1).pop()
- else:
- elmValue = self.getPropertyValue(elmCard, sProperty)
- if elmValue:
- if sProperty != 'url':
- sValueKey = ';VALUE=uri'
- sContentType = elmValue.get('type', '').strip().split('/').pop().strip()
- sContentType = sContentType.upper()
- if sContentType == 'OCTET-STREAM':
- sContentType = ''
- if sContentType:
- sContentType = ';TYPE=' + sContentType.upper()
- arLines.append(self.vcardFold(sProperty.upper() + sEncoding + sContentType + sValueKey + ':' + sValue))
-
- def processTypeValue(sProperty, arDefaultType, arForceType=None):
- arResults = self.getPropertyValue(elmCard, sProperty, bAllowMultiple=1)
- for elmResult in arResults:
- arType = self.getPropertyValue(elmResult, 'type', self.STRING, 1, 1)
- if arForceType:
- arType = self.unique(arForceType + arType)
- if not arType:
- arType = arDefaultType
- sValue = self.getPropertyValue(elmResult, 'value', self.EMAIL, 0)
- if sValue:
- arLines.append(self.vcardFold(sProperty.upper() + ';TYPE=' + ','.join(arType) + ':' + sValue))
-
- # AGENT
- # must do this before all other properties because it is destructive
- # (removes nested class="vcard" nodes so they don't interfere with
- # this vcard's other properties)
- arAgent = self.getPropertyValue(elmCard, 'agent', bAllowMultiple=1)
- for elmAgent in arAgent:
- if re.compile(r'\bvcard\b').search(elmAgent.get('class')):
- sAgentValue = self.findVCards(elmAgent, 1) + '\n'
- sAgentValue = sAgentValue.replace('\n', '\\n')
- sAgentValue = sAgentValue.replace(';', '\\;')
- if sAgentValue:
- arLines.append(self.vcardFold('AGENT:' + sAgentValue))
- # Completely remove the agent element from the parse tree
- elmAgent.extract()
- else:
- sAgentValue = self.getPropertyValue(elmAgent, 'value', self.URI, bAutoEscape=1);
- if sAgentValue:
- arLines.append(self.vcardFold('AGENT;VALUE=uri:' + sAgentValue))
-
- # FN (full name)
- sFN = processSingleString('fn')
-
- # N (name)
- elmName = self.getPropertyValue(elmCard, 'n')
- if elmName:
- sFamilyName = self.getPropertyValue(elmName, 'family-name', self.STRING, bAutoEscape=1)
- sGivenName = self.getPropertyValue(elmName, 'given-name', self.STRING, bAutoEscape=1)
- arAdditionalNames = self.getPropertyValue(elmName, 'additional-name', self.STRING, 1, 1) + self.getPropertyValue(elmName, 'additional-names', self.STRING, 1, 1)
- arHonorificPrefixes = self.getPropertyValue(elmName, 'honorific-prefix', self.STRING, 1, 1) + self.getPropertyValue(elmName, 'honorific-prefixes', self.STRING, 1, 1)
- arHonorificSuffixes = self.getPropertyValue(elmName, 'honorific-suffix', self.STRING, 1, 1) + self.getPropertyValue(elmName, 'honorific-suffixes', self.STRING, 1, 1)
- arLines.append(self.vcardFold('N:' + sFamilyName + ';' +
- sGivenName + ';' +
- ','.join(arAdditionalNames) + ';' +
- ','.join(arHonorificPrefixes) + ';' +
- ','.join(arHonorificSuffixes)))
- elif sFN:
- # implied "N" optimization
- # http://microformats.org/wiki/hcard#Implied_.22N.22_Optimization
- arNames = self.normalize(sFN).split()
- if len(arNames) == 2:
- bFamilyNameFirst = (arNames[0].endswith(',') or
- len(arNames[1]) == 1 or
- ((len(arNames[1]) == 2) and (arNames[1].endswith('.'))))
- if bFamilyNameFirst:
- arLines.append(self.vcardFold('N:' + arNames[0] + ';' + arNames[1]))
- else:
- arLines.append(self.vcardFold('N:' + arNames[1] + ';' + arNames[0]))
-
- # SORT-STRING
- sSortString = self.getPropertyValue(elmCard, 'sort-string', self.STRING, bAutoEscape=1)
- if sSortString:
- arLines.append(self.vcardFold('SORT-STRING:' + sSortString))
-
- # NICKNAME
- arNickname = self.getPropertyValue(elmCard, 'nickname', self.STRING, 1, 1)
- if arNickname:
- arLines.append(self.vcardFold('NICKNAME:' + ','.join(arNickname)))
-
- # PHOTO
- processSingleURI('photo')
-
- # BDAY
- dtBday = self.getPropertyValue(elmCard, 'bday', self.DATE)
- if dtBday:
- arLines.append(self.vcardFold('BDAY:' + self.toISO8601(dtBday)))
-
- # ADR (address)
- arAdr = self.getPropertyValue(elmCard, 'adr', bAllowMultiple=1)
- for elmAdr in arAdr:
- arType = self.getPropertyValue(elmAdr, 'type', self.STRING, 1, 1)
- if not arType:
- arType = ['intl','postal','parcel','work'] # default adr types, see RFC 2426 section 3.2.1
- sPostOfficeBox = self.getPropertyValue(elmAdr, 'post-office-box', self.STRING, 0, 1)
- sExtendedAddress = self.getPropertyValue(elmAdr, 'extended-address', self.STRING, 0, 1)
- sStreetAddress = self.getPropertyValue(elmAdr, 'street-address', self.STRING, 0, 1)
- sLocality = self.getPropertyValue(elmAdr, 'locality', self.STRING, 0, 1)
- sRegion = self.getPropertyValue(elmAdr, 'region', self.STRING, 0, 1)
- sPostalCode = self.getPropertyValue(elmAdr, 'postal-code', self.STRING, 0, 1)
- sCountryName = self.getPropertyValue(elmAdr, 'country-name', self.STRING, 0, 1)
- arLines.append(self.vcardFold('ADR;TYPE=' + ','.join(arType) + ':' +
- sPostOfficeBox + ';' +
- sExtendedAddress + ';' +
- sStreetAddress + ';' +
- sLocality + ';' +
- sRegion + ';' +
- sPostalCode + ';' +
- sCountryName))
-
- # LABEL
- processTypeValue('label', ['intl','postal','parcel','work'])
-
- # TEL (phone number)
- processTypeValue('tel', ['voice'])
-
- # EMAIL
- processTypeValue('email', ['internet'], ['internet'])
-
- # MAILER
- processSingleString('mailer')
-
- # TZ (timezone)
- processSingleString('tz')
-
- # GEO (geographical information)
- elmGeo = self.getPropertyValue(elmCard, 'geo')
- if elmGeo:
- sLatitude = self.getPropertyValue(elmGeo, 'latitude', self.STRING, 0, 1)
- sLongitude = self.getPropertyValue(elmGeo, 'longitude', self.STRING, 0, 1)
- arLines.append(self.vcardFold('GEO:' + sLatitude + ';' + sLongitude))
-
- # TITLE
- processSingleString('title')
-
- # ROLE
- processSingleString('role')
-
- # LOGO
- processSingleURI('logo')
-
- # ORG (organization)
- elmOrg = self.getPropertyValue(elmCard, 'org')
- if elmOrg:
- sOrganizationName = self.getPropertyValue(elmOrg, 'organization-name', self.STRING, 0, 1)
- if not sOrganizationName:
- # implied "organization-name" optimization
- # http://microformats.org/wiki/hcard#Implied_.22organization-name.22_Optimization
- sOrganizationName = self.getPropertyValue(elmCard, 'org', self.STRING, 0, 1)
- if sOrganizationName:
- arLines.append(self.vcardFold('ORG:' + sOrganizationName))
- else:
- arOrganizationUnit = self.getPropertyValue(elmOrg, 'organization-unit', self.STRING, 1, 1)
- arLines.append(self.vcardFold('ORG:' + sOrganizationName + ';' + ';'.join(arOrganizationUnit)))
-
- # CATEGORY
- arCategory = self.getPropertyValue(elmCard, 'category', self.STRING, 1, 1) + self.getPropertyValue(elmCard, 'categories', self.STRING, 1, 1)
- if arCategory:
- arLines.append(self.vcardFold('CATEGORIES:' + ','.join(arCategory)))
-
- # NOTE
- processSingleString('note')
-
- # REV
- processSingleString('rev')
-
- # SOUND
- processSingleURI('sound')
-
- # UID
- processSingleString('uid')
-
- # URL
- processSingleURI('url')
-
- # CLASS
- processSingleString('class')
-
- # KEY
- processSingleURI('key')
-
- if arLines:
- arLines = [u'BEGIN:vCard',u'VERSION:3.0'] + arLines + [u'END:vCard']
- # XXX - this is super ugly; properly fix this with issue 148
- for i, s in enumerate(arLines):
- if not isinstance(s, unicode):
- arLines[i] = s.decode('utf-8', 'ignore')
- sVCards += u'\n'.join(arLines) + u'\n'
-
- return sVCards.strip()
-
- def isProbablyDownloadable(self, elm):
- attrsD = elm.attrMap
- if 'href' not in attrsD:
- return 0
- linktype = attrsD.get('type', '').strip()
- if linktype.startswith('audio/') or \
- linktype.startswith('video/') or \
- (linktype.startswith('application/') and not linktype.endswith('xml')):
- return 1
- path = urlparse.urlparse(attrsD['href'])[2]
- if path.find('.') == -1:
- return 0
- fileext = path.split('.').pop().lower()
- return fileext in self.known_binary_extensions
-
- def findTags(self):
- all = lambda x: 1
- for elm in self.document(all, {'rel': re.compile(r'\btag\b')}):
- href = elm.get('href')
- if not href:
- continue
- urlscheme, domain, path, params, query, fragment = \
- urlparse.urlparse(_urljoin(self.baseuri, href))
- segments = path.split('/')
- tag = segments.pop()
- if not tag:
- if segments:
- tag = segments.pop()
- else:
- # there are no tags
- continue
- tagscheme = urlparse.urlunparse((urlscheme, domain, '/'.join(segments), '', '', ''))
- if not tagscheme.endswith('/'):
- tagscheme += '/'
- self.tags.append(FeedParserDict({"term": tag, "scheme": tagscheme, "label": elm.string or ''}))
-
- def findEnclosures(self):
- all = lambda x: 1
- enclosure_match = re.compile(r'\benclosure\b')
- for elm in self.document(all, {'href': re.compile(r'.+')}):
- if not enclosure_match.search(elm.get('rel', u'')) and not self.isProbablyDownloadable(elm):
- continue
- if elm.attrMap not in self.enclosures:
- self.enclosures.append(elm.attrMap)
- if elm.string and not elm.get('title'):
- self.enclosures[-1]['title'] = elm.string
-
- def findXFN(self):
- all = lambda x: 1
- for elm in self.document(all, {'rel': re.compile('.+'), 'href': re.compile('.+')}):
- rels = elm.get('rel', u'').split()
- xfn_rels = [r for r in rels if r in self.known_xfn_relationships]
- if xfn_rels:
- self.xfn.append({"relationships": xfn_rels, "href": elm.get('href', ''), "name": elm.string})
-
-def _parseMicroformats(htmlSource, baseURI, encoding):
- if not BeautifulSoup:
- return
- try:
- p = _MicroformatsParser(htmlSource, baseURI, encoding)
- except UnicodeEncodeError:
- # sgmllib throws this exception when performing lookups of tags
- # with non-ASCII characters in them.
- return
- p.vcard = p.findVCards(p.document)
- p.findTags()
- p.findEnclosures()
- p.findXFN()
- return {"tags": p.tags, "enclosures": p.enclosures, "xfn": p.xfn, "vcard": p.vcard}
-
-class _RelativeURIResolver(_BaseHTMLProcessor):
- relative_uris = set([('a', 'href'),
- ('applet', 'codebase'),
- ('area', 'href'),
- ('blockquote', 'cite'),
- ('body', 'background'),
- ('del', 'cite'),
- ('form', 'action'),
- ('frame', 'longdesc'),
- ('frame', 'src'),
- ('iframe', 'longdesc'),
- ('iframe', 'src'),
- ('head', 'profile'),
- ('img', 'longdesc'),
- ('img', 'src'),
- ('img', 'usemap'),
- ('input', 'src'),
- ('input', 'usemap'),
- ('ins', 'cite'),
- ('link', 'href'),
- ('object', 'classid'),
- ('object', 'codebase'),
- ('object', 'data'),
- ('object', 'usemap'),
- ('q', 'cite'),
- ('script', 'src')])
-
- def __init__(self, baseuri, encoding, _type):
- _BaseHTMLProcessor.__init__(self, encoding, _type)
- self.baseuri = baseuri
-
- def resolveURI(self, uri):
- return _makeSafeAbsoluteURI(_urljoin(self.baseuri, uri.strip()))
-
- def unknown_starttag(self, tag, attrs):
- attrs = self.normalize_attrs(attrs)
- attrs = [(key, ((tag, key) in self.relative_uris) and self.resolveURI(value) or value) for key, value in attrs]
- _BaseHTMLProcessor.unknown_starttag(self, tag, attrs)
-
-def _resolveRelativeURIs(htmlSource, baseURI, encoding, _type):
- if not _SGML_AVAILABLE:
- return htmlSource
-
- p = _RelativeURIResolver(baseURI, encoding, _type)
- p.feed(htmlSource)
- return p.output()
-
-def _makeSafeAbsoluteURI(base, rel=None):
- # bail if ACCEPTABLE_URI_SCHEMES is empty
- if not ACCEPTABLE_URI_SCHEMES:
- try:
- return _urljoin(base, rel or u'')
- except ValueError:
- return u''
- if not base:
- return rel or u''
- if not rel:
- try:
- scheme = urlparse.urlparse(base)[0]
- except ValueError:
- return u''
- if not scheme or scheme in ACCEPTABLE_URI_SCHEMES:
- return base
- return u''
- try:
- uri = _urljoin(base, rel)
- except ValueError:
- return u''
- if uri.strip().split(':', 1)[0] not in ACCEPTABLE_URI_SCHEMES:
- return u''
- return uri
-
-class _HTMLSanitizer(_BaseHTMLProcessor):
- acceptable_elements = set(['a', 'abbr', 'acronym', 'address', 'area',
- 'article', 'aside', 'audio', 'b', 'big', 'blockquote', 'br', 'button',
- 'canvas', 'caption', 'center', 'cite', 'code', 'col', 'colgroup',
- 'command', 'datagrid', 'datalist', 'dd', 'del', 'details', 'dfn',
- 'dialog', 'dir', 'div', 'dl', 'dt', 'em', 'event-source', 'fieldset',
- 'figcaption', 'figure', 'footer', 'font', 'form', 'header', 'h1',
- 'h2', 'h3', 'h4', 'h5', 'h6', 'hr', 'i', 'img', 'input', 'ins',
- 'keygen', 'kbd', 'label', 'legend', 'li', 'm', 'map', 'menu', 'meter',
- 'multicol', 'nav', 'nextid', 'ol', 'output', 'optgroup', 'option',
- 'p', 'pre', 'progress', 'q', 's', 'samp', 'section', 'select',
- 'small', 'sound', 'source', 'spacer', 'span', 'strike', 'strong',
- 'sub', 'sup', 'table', 'tbody', 'td', 'textarea', 'time', 'tfoot',
- 'th', 'thead', 'tr', 'tt', 'u', 'ul', 'var', 'video', 'noscript'])
-
- acceptable_attributes = set(['abbr', 'accept', 'accept-charset', 'accesskey',
- 'action', 'align', 'alt', 'autocomplete', 'autofocus', 'axis',
- 'background', 'balance', 'bgcolor', 'bgproperties', 'border',
- 'bordercolor', 'bordercolordark', 'bordercolorlight', 'bottompadding',
- 'cellpadding', 'cellspacing', 'ch', 'challenge', 'char', 'charoff',
- 'choff', 'charset', 'checked', 'cite', 'class', 'clear', 'color', 'cols',
- 'colspan', 'compact', 'contenteditable', 'controls', 'coords', 'data',
- 'datafld', 'datapagesize', 'datasrc', 'datetime', 'default', 'delay',
- 'dir', 'disabled', 'draggable', 'dynsrc', 'enctype', 'end', 'face', 'for',
- 'form', 'frame', 'galleryimg', 'gutter', 'headers', 'height', 'hidefocus',
- 'hidden', 'high', 'href', 'hreflang', 'hspace', 'icon', 'id', 'inputmode',
- 'ismap', 'keytype', 'label', 'leftspacing', 'lang', 'list', 'longdesc',
- 'loop', 'loopcount', 'loopend', 'loopstart', 'low', 'lowsrc', 'max',
- 'maxlength', 'media', 'method', 'min', 'multiple', 'name', 'nohref',
- 'noshade', 'nowrap', 'open', 'optimum', 'pattern', 'ping', 'point-size',
- 'prompt', 'pqg', 'radiogroup', 'readonly', 'rel', 'repeat-max',
- 'repeat-min', 'replace', 'required', 'rev', 'rightspacing', 'rows',
- 'rowspan', 'rules', 'scope', 'selected', 'shape', 'size', 'span', 'src',
- 'start', 'step', 'summary', 'suppress', 'tabindex', 'target', 'template',
- 'title', 'toppadding', 'type', 'unselectable', 'usemap', 'urn', 'valign',
- 'value', 'variable', 'volume', 'vspace', 'vrml', 'width', 'wrap',
- 'xml:lang'])
-
- unacceptable_elements_with_end_tag = set(['script', 'applet', 'style'])
-
- acceptable_css_properties = set(['azimuth', 'background-color',
- 'border-bottom-color', 'border-collapse', 'border-color',
- 'border-left-color', 'border-right-color', 'border-top-color', 'clear',
- 'color', 'cursor', 'direction', 'display', 'elevation', 'float', 'font',
- 'font-family', 'font-size', 'font-style', 'font-variant', 'font-weight',
- 'height', 'letter-spacing', 'line-height', 'overflow', 'pause',
- 'pause-after', 'pause-before', 'pitch', 'pitch-range', 'richness',
- 'speak', 'speak-header', 'speak-numeral', 'speak-punctuation',
- 'speech-rate', 'stress', 'text-align', 'text-decoration', 'text-indent',
- 'unicode-bidi', 'vertical-align', 'voice-family', 'volume',
- 'white-space', 'width'])
-
- # survey of common keywords found in feeds
- acceptable_css_keywords = set(['auto', 'aqua', 'black', 'block', 'blue',
- 'bold', 'both', 'bottom', 'brown', 'center', 'collapse', 'dashed',
- 'dotted', 'fuchsia', 'gray', 'green', '!important', 'italic', 'left',
- 'lime', 'maroon', 'medium', 'none', 'navy', 'normal', 'nowrap', 'olive',
- 'pointer', 'purple', 'red', 'right', 'solid', 'silver', 'teal', 'top',
- 'transparent', 'underline', 'white', 'yellow'])
-
- valid_css_values = re.compile('^(#[0-9a-f]+|rgb\(\d+%?,\d*%?,?\d*%?\)?|' +
- '\d{0,2}\.?\d{0,2}(cm|em|ex|in|mm|pc|pt|px|%|,|\))?)$')
-
- mathml_elements = set(['annotation', 'annotation-xml', 'maction', 'math',
- 'merror', 'mfenced', 'mfrac', 'mi', 'mmultiscripts', 'mn', 'mo', 'mover', 'mpadded',
- 'mphantom', 'mprescripts', 'mroot', 'mrow', 'mspace', 'msqrt', 'mstyle',
- 'msub', 'msubsup', 'msup', 'mtable', 'mtd', 'mtext', 'mtr', 'munder',
- 'munderover', 'none', 'semantics'])
-
- mathml_attributes = set(['actiontype', 'align', 'columnalign', 'columnalign',
- 'columnalign', 'close', 'columnlines', 'columnspacing', 'columnspan', 'depth',
- 'display', 'displaystyle', 'encoding', 'equalcolumns', 'equalrows',
- 'fence', 'fontstyle', 'fontweight', 'frame', 'height', 'linethickness',
- 'lspace', 'mathbackground', 'mathcolor', 'mathvariant', 'mathvariant',
- 'maxsize', 'minsize', 'open', 'other', 'rowalign', 'rowalign', 'rowalign',
- 'rowlines', 'rowspacing', 'rowspan', 'rspace', 'scriptlevel', 'selection',
- 'separator', 'separators', 'stretchy', 'width', 'width', 'xlink:href',
- 'xlink:show', 'xlink:type', 'xmlns', 'xmlns:xlink'])
-
- # svgtiny - foreignObject + linearGradient + radialGradient + stop
- svg_elements = set(['a', 'animate', 'animateColor', 'animateMotion',
- 'animateTransform', 'circle', 'defs', 'desc', 'ellipse', 'foreignObject',
- 'font-face', 'font-face-name', 'font-face-src', 'g', 'glyph', 'hkern',
- 'linearGradient', 'line', 'marker', 'metadata', 'missing-glyph', 'mpath',
- 'path', 'polygon', 'polyline', 'radialGradient', 'rect', 'set', 'stop',
- 'svg', 'switch', 'text', 'title', 'tspan', 'use'])
-
- # svgtiny + class + opacity + offset + xmlns + xmlns:xlink
- svg_attributes = set(['accent-height', 'accumulate', 'additive', 'alphabetic',
- 'arabic-form', 'ascent', 'attributeName', 'attributeType',
- 'baseProfile', 'bbox', 'begin', 'by', 'calcMode', 'cap-height',
- 'class', 'color', 'color-rendering', 'content', 'cx', 'cy', 'd', 'dx',
- 'dy', 'descent', 'display', 'dur', 'end', 'fill', 'fill-opacity',
- 'fill-rule', 'font-family', 'font-size', 'font-stretch', 'font-style',
- 'font-variant', 'font-weight', 'from', 'fx', 'fy', 'g1', 'g2',
- 'glyph-name', 'gradientUnits', 'hanging', 'height', 'horiz-adv-x',
- 'horiz-origin-x', 'id', 'ideographic', 'k', 'keyPoints', 'keySplines',
- 'keyTimes', 'lang', 'mathematical', 'marker-end', 'marker-mid',
- 'marker-start', 'markerHeight', 'markerUnits', 'markerWidth', 'max',
- 'min', 'name', 'offset', 'opacity', 'orient', 'origin',
- 'overline-position', 'overline-thickness', 'panose-1', 'path',
- 'pathLength', 'points', 'preserveAspectRatio', 'r', 'refX', 'refY',
- 'repeatCount', 'repeatDur', 'requiredExtensions', 'requiredFeatures',
- 'restart', 'rotate', 'rx', 'ry', 'slope', 'stemh', 'stemv',
- 'stop-color', 'stop-opacity', 'strikethrough-position',
- 'strikethrough-thickness', 'stroke', 'stroke-dasharray',
- 'stroke-dashoffset', 'stroke-linecap', 'stroke-linejoin',
- 'stroke-miterlimit', 'stroke-opacity', 'stroke-width', 'systemLanguage',
- 'target', 'text-anchor', 'to', 'transform', 'type', 'u1', 'u2',
- 'underline-position', 'underline-thickness', 'unicode', 'unicode-range',
- 'units-per-em', 'values', 'version', 'viewBox', 'visibility', 'width',
- 'widths', 'x', 'x-height', 'x1', 'x2', 'xlink:actuate', 'xlink:arcrole',
- 'xlink:href', 'xlink:role', 'xlink:show', 'xlink:title', 'xlink:type',
- 'xml:base', 'xml:lang', 'xml:space', 'xmlns', 'xmlns:xlink', 'y', 'y1',
- 'y2', 'zoomAndPan'])
-
- svg_attr_map = None
- svg_elem_map = None
-
- acceptable_svg_properties = set([ 'fill', 'fill-opacity', 'fill-rule',
- 'stroke', 'stroke-width', 'stroke-linecap', 'stroke-linejoin',
- 'stroke-opacity'])
-
- def reset(self):
- _BaseHTMLProcessor.reset(self)
- self.unacceptablestack = 0
- self.mathmlOK = 0
- self.svgOK = 0
-
- def unknown_starttag(self, tag, attrs):
- acceptable_attributes = self.acceptable_attributes
- keymap = {}
- if not tag in self.acceptable_elements or self.svgOK:
- if tag in self.unacceptable_elements_with_end_tag:
- self.unacceptablestack += 1
-
- # add implicit namespaces to html5 inline svg/mathml
- if self._type.endswith('html'):
- if not dict(attrs).get('xmlns'):
- if tag=='svg':
- attrs.append( ('xmlns','http://www.w3.org/2000/svg') )
- if tag=='math':
- attrs.append( ('xmlns','http://www.w3.org/1998/Math/MathML') )
-
- # not otherwise acceptable, perhaps it is MathML or SVG?
- if tag=='math' and ('xmlns','http://www.w3.org/1998/Math/MathML') in attrs:
- self.mathmlOK += 1
- if tag=='svg' and ('xmlns','http://www.w3.org/2000/svg') in attrs:
- self.svgOK += 1
-
- # chose acceptable attributes based on tag class, else bail
- if self.mathmlOK and tag in self.mathml_elements:
- acceptable_attributes = self.mathml_attributes
- elif self.svgOK and tag in self.svg_elements:
- # for most vocabularies, lowercasing is a good idea. Many
- # svg elements, however, are camel case
- if not self.svg_attr_map:
- lower=[attr.lower() for attr in self.svg_attributes]
- mix=[a for a in self.svg_attributes if a not in lower]
- self.svg_attributes = lower
- self.svg_attr_map = dict([(a.lower(),a) for a in mix])
-
- lower=[attr.lower() for attr in self.svg_elements]
- mix=[a for a in self.svg_elements if a not in lower]
- self.svg_elements = lower
- self.svg_elem_map = dict([(a.lower(),a) for a in mix])
- acceptable_attributes = self.svg_attributes
- tag = self.svg_elem_map.get(tag,tag)
- keymap = self.svg_attr_map
- elif not tag in self.acceptable_elements:
- return
-
- # declare xlink namespace, if needed
- if self.mathmlOK or self.svgOK:
- if filter(lambda (n,v): n.startswith('xlink:'),attrs):
- if not ('xmlns:xlink','http://www.w3.org/1999/xlink') in attrs:
- attrs.append(('xmlns:xlink','http://www.w3.org/1999/xlink'))
-
- clean_attrs = []
- for key, value in self.normalize_attrs(attrs):
- if key in acceptable_attributes:
- key=keymap.get(key,key)
- # make sure the uri uses an acceptable uri scheme
- if key == u'href':
- value = _makeSafeAbsoluteURI(value)
- clean_attrs.append((key,value))
- elif key=='style':
- clean_value = self.sanitize_style(value)
- if clean_value:
- clean_attrs.append((key,clean_value))
- _BaseHTMLProcessor.unknown_starttag(self, tag, clean_attrs)
-
- def unknown_endtag(self, tag):
- if not tag in self.acceptable_elements:
- if tag in self.unacceptable_elements_with_end_tag:
- self.unacceptablestack -= 1
- if self.mathmlOK and tag in self.mathml_elements:
- if tag == 'math' and self.mathmlOK:
- self.mathmlOK -= 1
- elif self.svgOK and tag in self.svg_elements:
- tag = self.svg_elem_map.get(tag,tag)
- if tag == 'svg' and self.svgOK:
- self.svgOK -= 1
- else:
- return
- _BaseHTMLProcessor.unknown_endtag(self, tag)
-
- def handle_pi(self, text):
- pass
-
- def handle_decl(self, text):
- pass
-
- def handle_data(self, text):
- if not self.unacceptablestack:
- _BaseHTMLProcessor.handle_data(self, text)
-
- def sanitize_style(self, style):
- # disallow urls
- style=re.compile('url\s*\(\s*[^\s)]+?\s*\)\s*').sub(' ',style)
-
- # gauntlet
- if not re.match("""^([:,;#%.\sa-zA-Z0-9!]|\w-\w|'[\s\w]+'|"[\s\w]+"|\([\d,\s]+\))*$""", style):
- return ''
- # This replaced a regexp that used re.match and was prone to pathological back-tracking.
- if re.sub("\s*[-\w]+\s*:\s*[^:;]*;?", '', style).strip():
- return ''
-
- clean = []
- for prop,value in re.findall("([-\w]+)\s*:\s*([^:;]*)",style):
- if not value:
- continue
- if prop.lower() in self.acceptable_css_properties:
- clean.append(prop + ': ' + value + ';')
- elif prop.split('-')[0].lower() in ['background','border','margin','padding']:
- for keyword in value.split():
- if not keyword in self.acceptable_css_keywords and \
- not self.valid_css_values.match(keyword):
- break
- else:
- clean.append(prop + ': ' + value + ';')
- elif self.svgOK and prop.lower() in self.acceptable_svg_properties:
- clean.append(prop + ': ' + value + ';')
-
- return ' '.join(clean)
-
- def parse_comment(self, i, report=1):
- ret = _BaseHTMLProcessor.parse_comment(self, i, report)
- if ret >= 0:
- return ret
- # if ret == -1, this may be a malicious attempt to circumvent
- # sanitization, or a page-destroying unclosed comment
- match = re.compile(r'--[^>]*>').search(self.rawdata, i+4)
- if match:
- return match.end()
- # unclosed comment; deliberately fail to handle_data()
- return len(self.rawdata)
-
-
-def _sanitizeHTML(htmlSource, encoding, _type):
- if not _SGML_AVAILABLE:
- return htmlSource
- p = _HTMLSanitizer(encoding, _type)
- htmlSource = htmlSource.replace(''):
- data = data.split('>', 1)[1]
- if data.count('