Process crashed with `AttributeError: 'MyHTMLParser' object has no attribute 'attrs'`

[brlin-tw]

The program seems to be downloading attached images or something.

This is a Ubuntu 20.10 desktop, run by Python 3.8.6 in a Python venv.

Traceback (most recent call last)

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 2464, in __call__

    def __call__(self, environ, start_response):
  
    """The WSGI server calls the Flask application object as the
  
    WSGI application. This calls :meth:`wsgi_app` which can be
  
    wrapped to applying middleware."""
  
    return self.wsgi_app(environ, start_response)
  
  
  
    def __repr__(self):
  
    return "<%s %r>" % (self.__class__.__name__, self.name)
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 2450, in wsgi_app

    try:
  
    ctx.push()
  
    response = self.full_dispatch_request()
  
    except Exception as e:
  
    error = e
  
    response = self.handle_exception(e)
  
    except:  # noqa: B001
  
    error = sys.exc_info()[1]
  
    raise
  
    return response(environ, start_response)
  
    finally:
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 1867, in handle_exception

    # if we want to repropagate the exception, we can attempt to
  
    # raise it with the whole traceback in case we can do that
  
    # (the function was actually called from the except part)
  
    # otherwise, we just raise the error again
  
    if exc_value is e:
  
    reraise(exc_type, exc_value, tb)
  
    else:
  
    raise e
  
  
  
    self.log_exception((exc_type, exc_value, tb))
  
    server_error = InternalServerError()
  

• File "/venv/lib/python3.8/site-packages/flask/_compat.py", line 39, in reraise

    import collections.abc as collections_abc
  
  
  
    def reraise(tp, value, tb=None):
  
    if value.__traceback__ is not tb:
  
    raise value.with_traceback(tb)
  
    raise value
  
  
  
    implements_to_string = _identity
  
  
  
    ![Open an interactive python shell in this frame][img41]else:
  
    iterkeys = lambda d: d.iterkeys()
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 2447, in wsgi_app

    ctx = self.request_context(environ)
  
    error = None
  
    try:
  
    try:
  
    ctx.push()
  
    response = self.full_dispatch_request()
  
    except Exception as e:
  
    error = e
  
    response = self.handle_exception(e)
  
    except:  # noqa: B001
  
    error = sys.exc_info()[1]
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 1952, in full_dispatch_request

    request_started.send(self)
  
    rv = self.preprocess_request()
  
    if rv is None:
  
    rv = self.dispatch_request()
  
    except Exception as e:
  
    rv = self.handle_user_exception(e)
  
    return self.finalize_request(rv)
  
  
  
    def finalize_request(self, rv, from_error_handler=False):
  
    """Given the return value from a view function this finalizes
  
    the request by converting it into a response and invoking the
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 1821, in handle_user_exception

    return self.handle_http_exception(e)
  
  
  
    handler = self._find_error_handler(e)
  
  
  
    if handler is None:
  
    reraise(exc_type, exc_value, tb)
  
    return handler(e)
  
  
  
    def handle_exception(self, e):
  
    """Handle an exception that did not have an error handler
  
    associated with it, or that was raised from an error handler.
  

• File "/venv/lib/python3.8/site-packages/flask/_compat.py", line 39, in reraise

    import collections.abc as collections_abc
  
  
  
    def reraise(tp, value, tb=None):
  
    if value.__traceback__ is not tb:
  
    raise value.with_traceback(tb)
  
    raise value
  
  
  
    implements_to_string = _identity
  
  
  
    ![Open an interactive python shell in this frame][img85]else:
  
    iterkeys = lambda d: d.iterkeys()
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 1950, in full_dispatch_request

    self.try_trigger_before_first_request_functions()
  
    try:
  
    request_started.send(self)
  
    rv = self.preprocess_request()
  
    if rv is None:
  
    rv = self.dispatch_request()
  
    except Exception as e:
  
    rv = self.handle_user_exception(e)
  
    return self.finalize_request(rv)
  
  
  
    def finalize_request(self, rv, from_error_handler=False):
  

• File "/venv/lib/python3.8/site-packages/flask/app.py", line 1936, in dispatch_request

    getattr(rule, "provide_automatic_options", False)
  
    and req.method == "OPTIONS"
  
    ):
  
    return self.make_default_options_response()
  
    # otherwise dispatch to the handler for that endpoint
  
    return self.view_functions[rule.endpoint](**req.view_args)
  
  
  
    def full_dispatch_request(self):
  
    """Dispatches the request and on top of that performs request
  
    pre and postprocessing as well as HTTP exception catching and
  
    error handling.
  

• File "/onenote_export.py", line 236, in main_logic

    ![Open an interactive python shell in this frame][img109]def main_logic():
  
    code = flask.request.args['code']
  
    token = application.acquire_token_by_authorization_code(code, scopes=scopes,
  
    redirect_uri=redirect_uri)
  
    graph_client = OAuth2Session(token=token)
  
    download_notebooks(graph_client, app.config['output_path'], app.config['select_path'], indent=0)
  
    print("Done!")
  
    return flask.render_template_string('<html>'
  
    '<head><title>Done</title></head>'
  
    '<body><p1><b>Done</b></p1></body>'
  
    '</html>')
  

• File "/onenote_export.py", line 175, in download_notebooks

    nb_name = nb["displayName"]
  
    indent_print(indent, f'Opening notebook {nb_name}')
  
    sections = get_json(graph_client, nb['sectionsUrl'])
  
    section_groups = get_json(graph_client, nb['sectionGroupsUrl'])
  
    indent_print(indent + 1, f'Got {len(sections)} sections and {len(section_groups)} section groups.')
  
    download_sections(graph_client, sections, path / nb_name, select, indent=indent + 1)
  
    download_section_groups(graph_client, section_groups, path / nb_name, select, indent=indent + 1)
  
  
  
  
  
    ![Open an interactive python shell in this frame][img129]def download_section_groups(graph_client, section_groups, path, select=None, indent=0):
  
    section_groups, select = filter_items(section_groups, select, 'section groups', indent)
  

• File "/onenote_export.py", line 196, in download_sections

    for sec in sections:
  
    sec_name = sec["displayName"]
  
    indent_print(indent, f'Opening section {sec_name}')
  
    pages = get_json(graph_client, sec['pagesUrl'] + '?pagelevel=true')
  
    indent_print(indent + 1, f'Got {len(pages)} pages.')
  
    download_pages(graph_client, pages, path / sec_name, select, indent=indent + 1)
  
  
  
  
  
    ![Open an interactive python shell in this frame][img139]def download_pages(graph_client, pages, path, select=None, indent=0):
  
    pages, select = filter_items(pages, select, 'pages', indent)
  
    pages = sorted([(page['order'], page) for page in pages])
  

• File "/onenote_export.py", line 212, in download_pages

    if level == 0:
  
    page_dir = path / page_title
  
    else:
  
    page_dir = level_dirs[level - 1] / page_title
  
    level_dirs[level] = page_dir
  
    download_page(graph_client, page['contentUrl'], page_dir, indent=indent + 1)
  
  
  
  
  
    ![Open an interactive python shell in this frame][img150]def download_page(graph_client, page_url, path, indent=0):
  
    out_html = path / 'main.html'
  
    if out_html.exists():
  

• File "/onenote_export.py", line 225, in download_page

    path.mkdir(parents=True, exist_ok=True)
  
    response = get(graph_client, page_url, indent=indent)
  
    if response is not None:
  
    content = response.text
  
    indent_print(indent, f'Got content of length {len(content)}')
  
    content = download_attachments(graph_client, content, path, indent=indent)
  
    with open(out_html, "w", encoding='utf-8') as f:
  
    f.write(content)
  
  
  
  
  
    ![Open an interactive python shell in this frame][img163]@app.route("/getToken")
  

• File "/onenote_export.py", line 146, in download_attachments

    with open(attachment_dir / file_name, "wb") as f:
  
    f.write(data)
  
    props['data'] = "attachments/" + file_name
  
    return generate_html('object', props)
  
  
  
    content = re.sub(r"<img .*?\\/>", download_image, content, flags=re.DOTALL)
  
    content = re.sub(r"<object .*?\\/>", download_attachment, content, flags=re.DOTALL)
  
    return content
  
  
  
  
  
    ![Open an interactive python shell in this frame][img174]def indent_print(depth, text):
  

• File "/usr/lib/python3.8/re.py", line 210, in sub

    non-overlapping occurrences of the pattern in string by the
  
    replacement repl.  repl can be either a string or a callable;
  
    if a string, backslash escapes in it are processed.  If it is
  
    a callable, it's passed the Match object and must return
  
    a replacement string to be used."""
  
    return _compile(pattern, flags).sub(repl, string, count)
  
  
  
    ![Open an interactive python shell in this frame][img182]def subn(pattern, repl, string, count=0, flags=0):
  
    """Return a 2-tuple containing (new_string, number).
  
    new_string is the string obtained by replacing the leftmost
  
    non-overlapping occurrences of the pattern in the source
  

• File "/onenote_export.py", line 108, in download_image

    def download_image(tag_match):
  
    # <img width="843" height="218.5" src="..." data-src-type="image/png" data-fullres-src="..."
  
    # data-fullres-src-type="image/png" />
  
    parser = MyHTMLParser()
  
    parser.feed(tag_match[0])
  
    props = parser.attrs
  
    image_url = props.get('data-fullres-src', props['src'])
  
    image_type = props.get('data-fullres-src-type', props['data-src-type']).split("/")[-1]
  
    file_name = ''.join(random.choice(string.ascii_lowercase) for _ in range(10)) + '.' + image_type
  
    req = get(graph_client, image_url, indent=indent)
  
    if req is None:
  

AttributeError: 'MyHTMLParser' object has no attribute 'attrs'

[maphew]

It looks to me like this is a bug in the upstream html parser. I was able to work around the issue by: Opening Onenote,

• finding the image with the problematic alt text and
• editing it to remove the html code fragments, or more precisely: the angle brrackets and quotes <>' ".
  • (Select image >> r-click >> Alt text...)