Class CustomHTML2Text

crawl4ai/utils.py:181–223

    return s

class CustomHTML2Text(HTML2Text):
    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        self.inside_pre = False
        self.inside_code = False
        
        self.skip_internal_links = False
        self.single_line_break = False
        self.mark_code = False
        self.include_sup_sub = False
        self.body_width = 0
        self.ignore_mailto_links = True
        self.ignore_links = False
        self.escape_backslash = False
        self.escape_dot = False
        self.escape_plus = False
        self.escape_dash = False
        self.escape_snob = False


    def handle_tag(self, tag, attrs, start):
        if tag == 'pre':
            if start:
                self.o('```\n')
                self.inside_pre = True
            else:
                self.o('\n```')
                self.inside_pre = False
        elif tag in ["h1", "h2", "h3", "h4", "h5", "h6"]:
            pass


        # elif tag == 'code' and not self.inside_pre:
        #     if start:
        #         if not self.inside_pre:
        #             self.o('`')
        #         self.inside_code = True
        #     else:
        #         if not self.inside_pre:
        #             self.o('`')
        #         self.inside_code = False

        super().handle_tag(tag, attrs, start)

def replace_inline_tags(soup, tags, only_text=False):
    tag_replacements = {