Method get_title

newspaper/extractors.py:224–267

Fetch the article title and analyze it

(self, doc)

        return None

    def get_title(self, doc):
        """Fetch the article title and analyze it
        """
        title = ''
        title_element = self.parser.getElementsByTag(doc, tag='title')
        # no title found
        if title_element is None or len(title_element) == 0:
            return title

        # title elem found
        title_text = self.parser.getText(title_element[0])
        used_delimeter = False

        # split title with |
        if '|' in title_text:
            title_text = self.split_title(title_text, PIPE_SPLITTER)
            used_delimeter = True

        # split title with -
        if not used_delimeter and '-' in title_text:
            title_text = self.split_title(title_text, DASH_SPLITTER)
            used_delimeter = True

        # split title with _
        if not used_delimeter and '_' in title_text:
            title_text = self.split_title(title_text, UNDERSCORE_SPLITTER)

        # split title with /
        if not used_delimeter and '/' in title_text:
            title_text = self.split_title(title_text, SLASH_SPLITTER)
            used_delimeter = True

        # split title with »
        if not used_delimeter and '»' in title_text:
            title_text = self.split_title(title_text, ARROWS_SPLITTER)
            used_delimeter = True

        # split title with :
        if not used_delimeter and ':' in title_text:
            title_text = self.split_title(title_text, COLON_SPLITTER)
            used_delimeter = True

        title = MOTLEY_REPLACEMENT.replaceAll(title_text)
        return title

    def split_title(self, title, splitter):
        """Split the title to best part possible