• 设为首页
  • 点击收藏
  • 手机版
    手机扫一扫访问
    迪恩网络手机版
  • 关注官方公众号
    微信扫一扫关注
    迪恩网络公众号

Python html_parser.HTMLParser类代码示例

原作者: [db:作者] 来自: [db:来源] 收藏 邀请

本文整理汇总了Python中six.moves.html_parser.HTMLParser的典型用法代码示例。如果您正苦于以下问题:Python HTMLParser类的具体用法?Python HTMLParser怎么用?Python HTMLParser使用的例子?那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。



在下文中一共展示了HTMLParser类的20个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于我们的系统推荐出更棒的Python代码示例。

示例1: feed

 def feed(self, data):
     data = re.compile(r'<!((?!DOCTYPE|--|\[))', re.IGNORECASE).sub(r'&lt;!\1', data)
     data = re.sub(r'<([^<>\s]+?)\s*/>', self._shorttag_replace, data)
     data = data.replace('&#39;', "'")
     data = data.replace('&#34;', '"')
     HTMLParser.feed(self, data)
     HTMLParser.close(self)
开发者ID:ImmPortDB,项目名称:immport-galaxy,代码行数:7,代码来源:page.py


示例2: __init__

    def __init__(self):
        HTMLParser.__init__(self)
        self.links = []

        self.in_anchor = False
        self.attrs = None
        self.title = ''
开发者ID:AlexPerrot,项目名称:mkdocs,代码行数:7,代码来源:toc.py


示例3: __init__

    def __init__(self, *args, **kwargs):
        if sys.version_info > (3,4):  #pragma: no cover
            HTMLParser.__init__(self, convert_charrefs=False)
        else:  #pragma: no cover
            HTMLParser.__init__(self)

        super(HTMLRewriter, self).__init__(*args, **kwargs)
开发者ID:daleathan,项目名称:pywb,代码行数:7,代码来源:html_rewriter.py


示例4: feed

 def feed(self, string):
     try:
         HTMLParser.feed(self, string)
     except Exception as e:  # pragma: no cover
         import traceback
         traceback.print_exc()
         self.out.write(string)
开发者ID:daleathan,项目名称:pywb,代码行数:7,代码来源:html_rewriter.py


示例5: display_link_prompt

def display_link_prompt(args, urls, titles):
    """Print URLs and their descriptions alongside a prompt.

    Keyword arguments:
    args -- program arguments (dict)
    urls -- search URLs found (list)
    titles -- descriptions of search URLs found (list)
    """
    while 1:
        print('\n{0}'.format(BORDER))
        for i in range(len(urls)):
            link = HTMLParser().unescape(titles[i])
            print('{0}. {1}'.format(i+1, link.encode('utf-8') if PY2 else link))
        print(BORDER)

        # Handle link prompt input
        try:
            link_input = [inp.strip() for inp in input(': ').split()]
            if not link_input:
                continue
            utils.check_input(link_input)  # Check input in case of quit
            print('\n')
            exec_prompt_cmd(args, urls, link_input[0], link_input[1:])
        except (KeyboardInterrupt, EOFError, ValueError, IndexError):
            return False
开发者ID:huntrar,项目名称:cliquery,代码行数:25,代码来源:cliquery.py


示例6: original_unescape

 def original_unescape(self, s):
     """Since we need to use this sometimes"""
     if isinstance(s, basestring):
         return unicode(HTMLParser.unescape(self, s))
     elif isinstance(s, list):
         return [unicode(HTMLParser.unescape(self, item)) for item in s]
     else:
         return s
开发者ID:Parsely,项目名称:schemato,代码行数:8,代码来源:parselypage.py


示例7: __init__

    def __init__(self, style, styles = None):
        HTMLParser.__init__(self)

        self.s = ''
        self.style = style

        self.styles = styles if styles else default_styles
        self.style_stack = []
开发者ID:schwa,项目名称:punic,代码行数:8,代码来源:styling.py


示例8: __init__

    def __init__(self, media_locator, link_handler):
        HTMLParser.__init__(self)
        self.handlers_start = StartRules(media_locator, link_handler)
        self.handlers_startend = StartEndRules(media_locator, link_handler)
        self.handlers_end = EndRules()

        self.new_buffer()
        self.stack = deque()
        self.stack.append([])
开发者ID:cecedille1,项目名称:PDF_generator,代码行数:9,代码来源:from_html.py


示例9: __init__

    def __init__(self, max_words):
        # In Python 2, HTMLParser is not a new-style class,
        # hence super() cannot be used.
        HTMLParser.__init__(self)

        self.max_words = max_words
        self.words_found = 0
        self.open_tags = []
        self.truncate_at = None
开发者ID:joetboole,项目名称:pelican,代码行数:9,代码来源:utils.py


示例10: feed

 def feed(self, *args, **kwargs):
     try:
         # With Python 2, super() cannot be used.
         # See the comment for __init__().
         HTMLParser.feed(self, *args, **kwargs)
     except self.TruncationCompleted as exc:
         self.truncate_at = exc.truncate_at
     else:
         self.truncate_at = None
开发者ID:52M,项目名称:pelican,代码行数:9,代码来源:utils.py


示例11: __init__

 def __init__(self):
     HTMLParser.__init__(self)
     self._ignore = False
     self._ignorePath = None
     self._lasttag = None
     self._depth = 0
     self.depthText = {} # path:text
     self.counting = 0
     self.lastN = 0
开发者ID:Mondego,项目名称:pyreco,代码行数:9,代码来源:allPythonContent.py


示例12: __init__

    def __init__(self):
        HTMLParser.__init__(self)

        self.text_name = None
        self.original_value = None
        self.new_value = None

        self.in_tag = False
        self.read_buffer = six.StringIO()
开发者ID:Nitrate,项目名称:Nitrate,代码行数:9,代码来源:0003_migrate_logs_to_new_fields.py


示例13: cmd_genpot

def cmd_genpot(config, options):
    """Generate the gettext pot file"""

    os.chdir(config.source_dir)

    po_path = os.path.join(config.source_dir, 'po')
    if not os.path.isdir(po_path):
        os.mkdir(po_path)

    python_files = []
    for root, dirs_dummy, files in os.walk(config.source_dir):
        for file_name in files:
            if file_name.endswith('.py'):
                file_path = os.path.relpath(os.path.join(root, file_name),
                                            config.source_dir)
                python_files.append(file_path)
    python_files.sort()

    # First write out a stub .pot file containing just the translated
    # activity name, then have xgettext merge the rest of the
    # translations into that. (We can't just append the activity name
    # to the end of the .pot file afterwards, because that might
    # create a duplicate msgid.)
    pot_file = os.path.join('po', '%s.pot' % config.bundle_name)
    escaped_name = _po_escape(config.activity_name)
    f = open(pot_file, 'w')
    f.write('#: activity/activity.info:2\n')
    f.write('msgid "%s"\n' % escaped_name)
    f.write('msgstr ""\n')
    if config.summary is not None:
        escaped_summary = _po_escape(config.summary)
        f.write('#: activity/activity.info:3\n')
        f.write('msgid "%s"\n' % escaped_summary)
        f.write('msgstr ""\n')

    if config.description is not None:
        parser = HTMLParser()
        strings = []
        parser.handle_data = strings.append
        parser.feed(config.description)

        for s in strings:
            s = s.strip()
            if s:
                f.write('#: activity/activity.info:4\n')
                f.write('msgid "%s"\n' % _po_escape(s))
                f.write('msgstr ""\n')
    f.close()

    args = ['xgettext', '--join-existing', '--language=Python',
            '--keyword=_', '--add-comments=TRANS:', '--output=%s' % pot_file]

    args += python_files
    retcode = subprocess.call(args)
    if retcode:
        print('ERROR - xgettext failed with return code %i.' % retcode)
开发者ID:sugarlabs,项目名称:sugar-toolkit-gtk3,代码行数:56,代码来源:bundlebuilder.py


示例14: logged_in

 def logged_in(self, y):
     if all([None is y or 'logout' in y,
             bool(filter(lambda c: 'remember_web_' in c, self.session.cookies.keys()))]):
         if None is not y:
             self.shows = dict(re.findall('<option value="(\d+)">(.*?)</option>', y))
             h = HTMLParser()
             for k, v in self.shows.items():
                 self.shows[k] = sanitizeSceneName(h.unescape(unidecode(v.decode('utf-8'))))
         return True
     return False
开发者ID:JackDandy,项目名称:SickGear,代码行数:10,代码来源:showrss.py


示例15: add_set

 def add_set(self, title, description, index=-1):
     widget = QtWidgets.QCheckBox(title.replace('&', '&&'))
     if description:
         h = HTMLParser()
         widget.setToolTip(h.unescape(description))
     if index >= 0:
         self.sets_widget.layout().insertWidget(index, widget)
     else:
         self.sets_widget.layout().addWidget(widget)
     return widget
开发者ID:jim-easterbrook,项目名称:Photini,代码行数:10,代码来源:flickr.py


示例16: check_bz_bug

def check_bz_bug(b):
    ''' Return status of a bug in BZ'''
    html = get_html(b)
    if html:
        text = html.content.decode('utf-8')
        name = TITLE.search(text).group(1) if TITLE.search(text) else ''
        h = HTMLParser()
        name = h.unescape(name)
    else:
        name = ''
    return name, None
开发者ID:sshnaidm,项目名称:various,代码行数:11,代码来源:check_tests.py


示例17: __init__

    def __init__(self, *args, **kwargs):
        if sys.version_info > (3,):
            super(AnchorParser, self).__init__(*args, **kwargs)
        else:   # pragma: no cover
            # HTMLParser is still an old style object and so super doesn't
            # work
            HTMLParser.__init__(self, *args, **kwargs)

        self.capture = 0
        self.url = ''
        self.text = ''
开发者ID:cltrudeau,项目名称:wrench,代码行数:11,代码来源:utils.py


示例18: get_formatted_value

def get_formatted_value(value, field):
	'''Prepare field from raw data'''

	from six.moves.html_parser import HTMLParser

	if(getattr(field, 'fieldtype', None) in ["Text", "Text Editor"]):
		h = HTMLParser()
		value = h.unescape(value)
		value = (re.subn(r'<[\s]*(script|style).*?</\1>(?s)', '', text_type(value))[0])
		value = ' '.join(value.split())
	return field.label + " : " + strip_html_tags(text_type(value))
开发者ID:vhrspvl,项目名称:vhrs-frappe,代码行数:11,代码来源:global_search.py


示例19: get_email_subject

 def get_email_subject(self):
     """
     WARNING: It is MANDATORY to override method if you are going to
     send email using the  `send_notification_email` method.
     Your class must define an `email_subject_tmpl` attribute
     containing a template path to a file that has your email subject.
     """
     # Convert the html back to plaintext after rendering it using template
     # to get rid of html ampersand character codes
     parser = HTMLParser()
     html_email = self._get_email_field('email_subject_tmpl', 'get_email_subject')
     return parser.unescape(html_email)
开发者ID:Nomadblue,项目名称:django-nomad-notifier,代码行数:12,代码来源:models.py


示例20: __init__

    def __init__(self, tag="a", attr="href", process=None, unique=False):
        HTMLParser.__init__(self)

        warnings.warn(
            "HtmlParserLinkExtractor is deprecated and will be removed in "
            "future releases. Please use scrapy.linkextractors.LinkExtractor",
            ScrapyDeprecationWarning, stacklevel=2,
        )

        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_attr = process if callable(process) else lambda v: v
        self.unique = unique
开发者ID:CPoirot3,项目名称:scrapy,代码行数:13,代码来源:htmlparser.py



注:本文中的six.moves.html_parser.HTMLParser类示例由纯净天空整理自Github/MSDocs等源码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。


鲜花

握手

雷人

路过

鸡蛋
该文章已有0人参与评论

请发表评论

全部评论

专题导读
上一篇:
Python http_client.HTTPConnection类代码示例发布时间:2022-05-27
下一篇:
Python configparser.SafeConfigParser类代码示例发布时间:2022-05-27
热门推荐
阅读排行榜

扫描微信二维码

查看手机版网站

随时了解更新最新资讯

139-2527-9053

在线客服(服务时间 9:00~18:00)

在线QQ客服
地址:深圳市南山区西丽大学城创智工业园
电邮:jeky_zhao#qq.com
移动电话:139-2527-9053

Powered by 互联科技 X3.4© 2001-2213 极客世界.|Sitemap