htmlToPython.py

from camel import CamelRegistry, Camel
from bs4 import BeautifulSoup
import bs4

html_types = CamelRegistry()

@html_types.dumper(BeautifulSoup, 'xml', version=1)
@html_types.dumper(bs4.element.Tag, 'xml', version=1)
def _dump_tag(tag):
    out = dict(
        tagName= str(tag.name),
        children = list(tag.children),
        **{k:v for k,v in tag.attrs.items() if v}
    )
    return {k:v for k,v in out.items() if v}


@html_types.dumper(bs4.element.NavigableString, 'NavigableString', version=1)
@html_types.dumper(bs4.element.CharsetMetaAttributeValue, 'CharsetMetaAttributeValue', version=1)
@html_types.dumper(bs4.element.ContentMetaAttributeValue, 'ContentMetaAttributeValue', version=1)
@html_types.dumper(bs4.element.ProcessingInstruction, 'ProcessingInstruction', version=1)
@html_types.dumper(bs4.element.Doctype, 'Doctype', version=1)
@html_types.dumper(bs4.element.Declaration, 'Declaration', version=1)
@html_types.dumper(bs4.element.CData, 'CData', version=1)
@html_types.dumper(bs4.element.Comment, 'Comment', version=1)
def dump_ContentString(string):
    return str(string).strip()

@html_types.loader('xml', version=1)
@html_types.loader('NavigableString', version=1)
@html_types.loader('CharsetMetaAttributeValue', version=1)
@html_types.loader('ContentMetaAttributeValue', version=1)
@html_types.loader('ProcessingInstruction', version=1)
@html_types.loader('Doctype', version=1)
@html_types.loader('Declaration', version=1)
@html_types.loader('CData', version=1)
@html_types.loader('Comment', version=1)
def _load_table(data, version):
    return data

import requests

soup = BeautifulSoup(requests.get("https://forums.sufficientvelocity.com/threads/marked-for-death-a-rational-naruto-quest.24481/page-4574").text, 'html5lib')

foo = Camel([html_types,]).dump(soup)
#foo = Camel([html_types,]).load(open('./test.yaml','r').read())
print(foo)