Python sgmllib.SGMLParser.feed() Examples

The following are 29 code examples of sgmllib.SGMLParser.feed(). 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: BeautifulSoup.py    From ru with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #2
Source File: BeautifulSoup.py    From canvas with BSD 3-Clause "New" or "Revised" License 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not isList(self.markupMassage):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #3
Source File: BeautifulSoup.py    From fimap with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
        if markup:
            if self.markupMassage:
                if not isList(self.markupMassage):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #4
Source File: beautifulsoup.py    From EasY_HaCk with Apache License 2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #5
Source File: BeautifulSoup.py    From filmkodi with Apache License 2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #6
Source File: BeautifulSoup.py    From filmkodi with Apache License 2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #7
Source File: BeautifulSoup.py    From doork with MIT License 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
        if markup:
            if self.markupMassage:
                if not isList(self.markupMassage):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #8
Source File: BeautifulSoup.py    From Cloudmare with GNU General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #9
Source File: beautifulsoup.py    From POC-EXP with GNU General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #10
Source File: BeautifulSoup.py    From darkc0de-old-stuff with GNU General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
        if markup:
            if self.markupMassage:
                if not isList(self.markupMassage):
                    self.markupMassage = self.MARKUP_MASSAGE            
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
        self.reset()

        SGMLParser.feed(self, markup or "")
        SGMLParser.close(self)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #11
Source File: BeautifulSoup.py    From plugin.git.browser with GNU General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #12
Source File: BeautifulSoup.py    From ru with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #13
Source File: BeautifulSoup.py    From ru with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #14
Source File: BeautifulSoup.py    From ru with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #15
Source File: BeautifulSoup.py    From ru with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #16
Source File: __init__.py    From arnold-usd with Apache License 2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #17
Source File: moduleBS.py    From D-Tech with GNU General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #18
Source File: BeautifulSoup.py    From yalih with Apache License 2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #19
Source File: moduleBS.py    From D-TECT with GNU General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #20
Source File: BeautifulSoup.py    From luscan-devel with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #21
Source File: BeautifulSoup.py    From MARA_Framework with GNU Lesser General Public License v3.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #22
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #23
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #24
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #25
Source File: beautifulsoup.py    From NoobSec-Toolkit with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #26
Source File: BeautifulSoup.py    From xbmc-betaseries with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #27
Source File: BeautifulSoup.py    From xbmc-betaseries with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #28
Source File: BeautifulSoup.py    From nightmare with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not hasattr(self.markupMassage, "__iter__"):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()
Example #29
Source File: _bsoup.py    From faces with GNU General Public License v2.0 5 votes vote down vote up 
def _feed(self, inDocumentEncoding=None, isHTML=False):
        # Convert the document to Unicode.
        markup = self.markup
        if isinstance(markup, unicode):
            if not hasattr(self, 'originalEncoding'):
                self.originalEncoding = None
        else:
            dammit = UnicodeDammit\
                     (markup, [self.fromEncoding, inDocumentEncoding],
                      smartQuotesTo=self.smartQuotesTo, isHTML=isHTML)
            markup = dammit.unicode
            self.originalEncoding = dammit.originalEncoding
            self.declaredHTMLEncoding = dammit.declaredHTMLEncoding
        if markup:
            if self.markupMassage:
                if not isList(self.markupMassage):
                    self.markupMassage = self.MARKUP_MASSAGE
                for fix, m in self.markupMassage:
                    markup = fix.sub(m, markup)
                # TODO: We get rid of markupMassage so that the
                # soup object can be deepcopied later on. Some
                # Python installations can't copy regexes. If anyone
                # was relying on the existence of markupMassage, this
                # might cause problems.
                del(self.markupMassage)
        self.reset()

        SGMLParser.feed(self, markup)
        # Close out any unfinished strings and close all the open tags.
        self.endData()
        while self.currentTag.name != self.ROOT_TAG_NAME:
            self.popTag()