Python sgmllib.SGMLParser.__init__() Examples

The following are 30 code examples of sgmllib.SGMLParser.__init__(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module sgmllib.SGMLParser , or try the search function .
Example #1
Source File: uspto-sgml-parser.py    From uspto-patents-parsing-tools with MIT License 6 votes vote down vote up 
def __init__(self):
    SGMLParser.__init__(self, False)
    # gather data
    self.information = []
    # states
    self.document_id = 0
    self.date = 0
    self.ipc_data = 0
    self.usc_data = 0
    self.title = 0
    self.inventor = 0
    self.assignee = 0
    self.abstract = 0
    self.readable = 0
    # buffers
    self.docid_buffer = ''
    self.date_buffer = ''
    self.ipc_buffer = ''
    self.usc_buffer = ''
    self.title_buffer = ''
    self.inventor_buffer = ''
    self.assignee_buffer = ''
    self.abstract_buffer = ''
Example #2
Source File: sgml.py    From learn_python3_spider with MIT License 6 votes vote down vote up 
def __init__(self, allow=(), deny=(), allow_domains=(), deny_domains=(), restrict_xpaths=(),
                 tags=('a', 'area'), attrs=('href',), canonicalize=False, unique=True,
                 process_value=None, deny_extensions=None, restrict_css=(),
                 strip=True, restrict_text=()):
        warnings.warn(
            "SgmlLinkExtractor is deprecated and will be removed in future releases. "
            "Please use scrapy.linkextractors.LinkExtractor",
            ScrapyDeprecationWarning, stacklevel=2,
        )

        tags, attrs = set(arg_to_iter(tags)), set(arg_to_iter(attrs))
        tag_func = lambda x: x in tags
        attr_func = lambda x: x in attrs

        with warnings.catch_warnings():
            warnings.simplefilter('ignore', ScrapyDeprecationWarning)
            lx = BaseSgmlLinkExtractor(tag=tag_func, attr=attr_func,
                                       unique=unique, process_value=process_value, strip=strip,
                                       canonicalized=canonicalize)

        super(SgmlLinkExtractor, self).__init__(lx, allow=allow, deny=deny,
                                                allow_domains=allow_domains, deny_domains=deny_domains,
                                                restrict_xpaths=restrict_xpaths, restrict_css=restrict_css,
                                                canonicalize=canonicalize, deny_extensions=deny_extensions,
                                                restrict_text=restrict_text)
Example #3
Source File: sgml.py    From learn_python3_spider with MIT License 6 votes vote down vote up 
def __init__(self, tag="a", attr="href", unique=False, process_value=None,
                 strip=True, canonicalized=False):
        warnings.warn(
            "BaseSgmlLinkExtractor is deprecated and will be removed in future releases. "
            "Please use scrapy.linkextractors.LinkExtractor",
            ScrapyDeprecationWarning, stacklevel=2,
        )
        SGMLParser.__init__(self)
        self.scan_tag = tag if callable(tag) else lambda t: t == tag
        self.scan_attr = attr if callable(attr) else lambda a: a == attr
        self.process_value = (lambda v: v) if process_value is None else process_value
        self.current_link = None
        self.unique = unique
        self.strip = strip
        if canonicalized:
            self.link_key = lambda link: link.url
        else:
            self.link_key = lambda link: canonicalize_url(link.url,
                                                          keep_fragments=True)
Example #4
Source File: sgml.py    From learn_python3_spider with MIT License 6 votes vote down vote up 
def __init__(self, allow=(), deny=(), allow_domains=(), deny_domains=(), restrict_xpaths=(),
                 tags=('a', 'area'), attrs=('href',), canonicalize=False, unique=True,
                 process_value=None, deny_extensions=None, restrict_css=(),
                 strip=True, restrict_text=()):
        warnings.warn(
            "SgmlLinkExtractor is deprecated and will be removed in future releases. "
            "Please use scrapy.linkextractors.LinkExtractor",
            ScrapyDeprecationWarning, stacklevel=2,
        )

        tags, attrs = set(arg_to_iter(tags)), set(arg_to_iter(attrs))
        tag_func = lambda x: x in tags
        attr_func = lambda x: x in attrs

        with warnings.catch_warnings():
            warnings.simplefilter('ignore', ScrapyDeprecationWarning)
            lx = BaseSgmlLinkExtractor(tag=tag_func, attr=attr_func,
                                       unique=unique, process_value=process_value, strip=strip,
                                       canonicalized=canonicalize)

        super(SgmlLinkExtractor, self).__init__(lx, allow=allow, deny=deny,
                                                allow_domains=allow_domains, deny_domains=deny_domains,
                                                restrict_xpaths=restrict_xpaths, restrict_css=restrict_css,
                                                canonicalize=canonicalize, deny_extensions=deny_extensions,
                                                restrict_text=restrict_text)
Example #5
Source File: sgml.py    From learn_python3_spider with MIT License 6 votes vote down vote up 
def __init__(self, tag="a", attr="href", unique=False, process_value=None,
                 strip=True, canonicalized=False):
        warnings.warn(
            "BaseSgmlLinkExtractor is deprecated and will be removed in future releases. "
            "Please use scrapy.linkextractors.LinkExtractor",
            ScrapyDeprecationWarning, stacklevel=2,
        )
        SGMLParser.__init__(self)
        self.scan_tag = tag if callable(tag) else lambda t: t == tag
        self.scan_attr = attr if callable(attr) else lambda a: a == attr
        self.process_value = (lambda v: v) if process_value is None else process_value
        self.current_link = None
        self.unique = unique
        self.strip = strip
        if canonicalized:
            self.link_key = lambda link: link.url
        else:
            self.link_key = lambda link: canonicalize_url(link.url,
                                                          keep_fragments=True)
Example #6
Source File: BeautifulSoup.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def reset(self):
        Tag.__init__(self, self, self.ROOT_TAG_NAME)
        self.hidden = 1
        SGMLParser.reset(self)
        self.currentData = []
        self.currentTag = None
        self.tagStack = []
        self.quoteStack = []
        self.pushTag(self)
Example #7
Source File: BeautifulSoup.py    From yalih with Apache License 2.0 5 votes vote down vote up 
def __init__(self, name=None, attrs={}, text=None, **kwargs):
        self.name = name
        if isinstance(attrs, basestring):
            kwargs['class'] = _match_css_class(attrs)
            attrs = None
        if kwargs:
            if attrs:
                attrs = attrs.copy()
                attrs.update(kwargs)
            else:
                attrs = kwargs
        self.attrs = attrs
        self.text = text
Example #8
Source File: BeautifulSoup.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def __init__(self, *args, **kwargs):
        if not kwargs.has_key('smartQuotesTo'):
            kwargs['smartQuotesTo'] = self.HTML_ENTITIES
        kwargs['isHTML'] = True
        BeautifulStoneSoup.__init__(self, *args, **kwargs)
Example #9
Source File: BeautifulSoup.py    From luscan-devel with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, parser, name, attrs=None, parent=None,
                 previous=None):
        "Basic constructor."

        # We don't actually store the parser object: that lets extracted
        # chunks be garbage-collected
        self.parserClass = parser.__class__
        self.isSelfClosing = parser.isSelfClosingTag(name)
        self.name = name
        if attrs is None:
            attrs = []
        elif isinstance(attrs, dict):
            attrs = attrs.items()
        self.attrs = attrs
        self.contents = []
        self.setup(parent, previous)
        self.hidden = False
        self.containsSubstitutions = False
        self.convertHTMLEntities = parser.convertHTMLEntities
        self.convertXMLEntities = parser.convertXMLEntities
        self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities

        # Convert any HTML, XML, or numeric entities in the attribute values.
        convert = lambda(k, val): (k,
                                   re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
                                          self._convertEntities,
                                          val))
        self.attrs = map(convert, self.attrs)
Example #10
Source File: moduleBS.py    From D-Tech with GNU General Public License v3.0 5 votes vote down vote up 
def __init__(self, name=None, attrs={}, text=None, **kwargs):
        self.name = name
        if isinstance(attrs, basestring):
            kwargs['class'] = _match_css_class(attrs)
            attrs = None
        if kwargs:
            if attrs:
                attrs = attrs.copy()
                attrs.update(kwargs)
            else:
                attrs = kwargs
        self.attrs = attrs
        self.text = text
Example #11
Source File: BeautifulSoup.py    From yalih with Apache License 2.0 5 votes vote down vote up 
def __init__(self, source):
        list.__init__([])
        self.source = source

# Now, some helper functions.
Example #12
Source File: BeautifulSoup.py    From yalih with Apache License 2.0 5 votes vote down vote up 
def reset(self):
        Tag.__init__(self, self, self.ROOT_TAG_NAME)
        self.hidden = 1
        SGMLParser.reset(self)
        self.currentData = []
        self.currentTag = None
        self.tagStack = []
        self.quoteStack = []
        self.pushTag(self)
Example #13
Source File: BeautifulSoup.py    From yalih with Apache License 2.0 5 votes vote down vote up 
def __init__(self, *args, **kwargs):
        if not kwargs.has_key('smartQuotesTo'):
            kwargs['smartQuotesTo'] = self.HTML_ENTITIES
        kwargs['isHTML'] = True
        BeautifulStoneSoup.__init__(self, *args, **kwargs)
Example #14
Source File: moduleBS.py    From D-Tech with GNU General Public License v3.0 5 votes vote down vote up 
def __init__(self, parser, name, attrs=None, parent=None,
                 previous=None):
        "Basic constructor."

        # We don't actually store the parser object: that lets extracted
        # chunks be garbage-collected
        self.parserClass = parser.__class__
        self.isSelfClosing = parser.isSelfClosingTag(name)
        self.name = name
        if attrs is None:
            attrs = []
        elif isinstance(attrs, dict):
            attrs = attrs.items()
        self.attrs = attrs
        self.contents = []
        self.setup(parent, previous)
        self.hidden = False
        self.containsSubstitutions = False
        self.convertHTMLEntities = parser.convertHTMLEntities
        self.convertXMLEntities = parser.convertXMLEntities
        self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities

        # Convert any HTML, XML, or numeric entities in the attribute values.
        convert = lambda(k, val): (k,
                                   re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
                                          self._convertEntities,
                                          val))
        self.attrs = map(convert, self.attrs)
Example #15
Source File: moduleBS.py    From D-Tech with GNU General Public License v3.0 5 votes vote down vote up 
def reset(self):
        Tag.__init__(self, self, self.ROOT_TAG_NAME)
        self.hidden = 1
        SGMLParser.reset(self)
        self.currentData = []
        self.currentTag = None
        self.tagStack = []
        self.quoteStack = []
        self.pushTag(self)
Example #16
Source File: BeautifulSoup.py    From ru with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, parser, name, attrs=None, parent=None,
                 previous=None):
        "Basic constructor."

        # We don't actually store the parser object: that lets extracted
        # chunks be garbage-collected
        self.parserClass = parser.__class__
        self.isSelfClosing = parser.isSelfClosingTag(name)
        self.name = name
        if attrs is None:
            attrs = []
        elif isinstance(attrs, dict):
            attrs = attrs.items()
        self.attrs = attrs
        self.contents = []
        self.setup(parent, previous)
        self.hidden = False
        self.containsSubstitutions = False
        self.convertHTMLEntities = parser.convertHTMLEntities
        self.convertXMLEntities = parser.convertXMLEntities
        self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities

        # Convert any HTML, XML, or numeric entities in the attribute values.
        convert = lambda(k, val): (k,
                                   re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
                                          self._convertEntities,
                                          val))
        self.attrs = map(convert, self.attrs)
Example #17
Source File: moduleBS.py    From D-Tech with GNU General Public License v3.0 5 votes vote down vote up 
def __init__(self, *args, **kwargs):
        if not kwargs.has_key('smartQuotesTo'):
            kwargs['smartQuotesTo'] = self.HTML_ENTITIES
        kwargs['isHTML'] = True
        BeautifulStoneSoup.__init__(self, *args, **kwargs)
Example #18
Source File: BeautifulSoup.py    From luscan-devel with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, name=None, attrs={}, text=None, **kwargs):
        self.name = name
        if isinstance(attrs, basestring):
            kwargs['class'] = _match_css_class(attrs)
            attrs = None
        if kwargs:
            if attrs:
                attrs = attrs.copy()
                attrs.update(kwargs)
            else:
                attrs = kwargs
        self.attrs = attrs
        self.text = text
Example #19
Source File: BeautifulSoup.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def __init__(self, source):
        list.__init__([])
        self.source = source

# Now, some helper functions.
Example #20
Source File: BeautifulSoup.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def __init__(self, name=None, attrs={}, text=None, **kwargs):
        self.name = name
        if isinstance(attrs, basestring):
            kwargs['class'] = _match_css_class(attrs)
            attrs = None
        if kwargs:
            if attrs:
                attrs = attrs.copy()
                attrs.update(kwargs)
            else:
                attrs = kwargs
        self.attrs = attrs
        self.text = text
Example #21
Source File: BeautifulSoup.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def __init__(self, parser, name, attrs=None, parent=None,
                 previous=None):
        "Basic constructor."

        # We don't actually store the parser object: that lets extracted
        # chunks be garbage-collected
        self.parserClass = parser.__class__
        self.isSelfClosing = parser.isSelfClosingTag(name)
        self.name = name
        if attrs is None:
            attrs = []
        elif isinstance(attrs, dict):
            attrs = attrs.items()
        self.attrs = attrs
        self.contents = []
        self.setup(parent, previous)
        self.hidden = False
        self.containsSubstitutions = False
        self.convertHTMLEntities = parser.convertHTMLEntities
        self.convertXMLEntities = parser.convertXMLEntities
        self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities

        # Convert any HTML, XML, or numeric entities in the attribute values.
        convert = lambda(k, val): (k,
                                   re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
                                          self._convertEntities,
                                          val))
        self.attrs = map(convert, self.attrs)
Example #22
Source File: nuclesgmlparser.py    From m2scorer with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self):
        SGMLParser.__init__(self)
        self.docs = []
Example #23
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, *args, **kwargs):
        if not kwargs.has_key('smartQuotesTo'):
            kwargs['smartQuotesTo'] = self.HTML_ENTITIES
        kwargs['isHTML'] = True
        BeautifulStoneSoup.__init__(self, *args, **kwargs)
Example #24
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def reset(self):
        Tag.__init__(self, self, self.ROOT_TAG_NAME)
        self.hidden = 1
        SGMLParser.reset(self)
        self.currentData = []
        self.currentTag = None
        self.tagStack = []
        self.quoteStack = []
        self.pushTag(self)
Example #25
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, source):
        list.__init__([])
        self.source = source

# Now, some helper functions.
Example #26
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, name=None, attrs={}, text=None, **kwargs):
        self.name = name
        if isinstance(attrs, basestring):
            kwargs['class'] = _match_css_class(attrs)
            attrs = None
        if kwargs:
            if attrs:
                attrs = attrs.copy()
                attrs.update(kwargs)
            else:
                attrs = kwargs
        self.attrs = attrs
        self.text = text
Example #27
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, parser, name, attrs=None, parent=None,
                 previous=None):
        "Basic constructor."

        # We don't actually store the parser object: that lets extracted
        # chunks be garbage-collected
        self.parserClass = parser.__class__
        self.isSelfClosing = parser.isSelfClosingTag(name)
        self.name = name
        if attrs is None:
            attrs = []
        elif isinstance(attrs, dict):
            attrs = attrs.items()
        self.attrs = attrs
        self.contents = []
        self.setup(parent, previous)
        self.hidden = False
        self.containsSubstitutions = False
        self.convertHTMLEntities = parser.convertHTMLEntities
        self.convertXMLEntities = parser.convertXMLEntities
        self.escapeUnrecognizedEntities = parser.escapeUnrecognizedEntities

        # Convert any HTML, XML, or numeric entities in the attribute values.
        convert = lambda(k, val): (k,
                                   re.sub("&(#\d+|#x[0-9a-fA-F]+|\w+);",
                                          self._convertEntities,
                                          val))
        self.attrs = map(convert, self.attrs)
Example #28
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, *args, **kwargs):
        if not kwargs.has_key('smartQuotesTo'):
            kwargs['smartQuotesTo'] = self.HTML_ENTITIES
        kwargs['isHTML'] = True
        BeautifulStoneSoup.__init__(self, *args, **kwargs)
Example #29
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def reset(self):
        Tag.__init__(self, self, self.ROOT_TAG_NAME)
        self.hidden = 1
        SGMLParser.reset(self)
        self.currentData = []
        self.currentTag = None
        self.tagStack = []
        self.quoteStack = []
        self.pushTag(self)
Example #30
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def __init__(self, source):
        list.__init__([])
        self.source = source

# Now, some helper functions.