Python json.html方法代码示例

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def json_to_dict(data):
    """Convert JSON to a dict().

    See more about the json module at
    https://docs.python.org/3.5/library/json.html

    Parameters
    ----------
    data : string
        Data as a json-formatted string.

    Returns
    -------
    dict
        Data as Python Dictionary.

    """
    try:
        return json.loads(data)
    except Exception as e:
        raise e 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def dict_to_json(data):
    """Convert dict() to JSON-formatted string.

    See more about the json module at
    https://docs.python.org/3.5/library/json.html

    Parameters
    ----------
    data : dict
        Data as Python Dictionary.

    Returns
    -------
    string
        Data as a json-formatted string.

    """
    try:
        return json.dumps(data, ensure_ascii=True, indent=2)
    except Exception as e:
        raise e 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def read_file(filename, mode='r'):
    """Read in a file.

    Parameters
    ----------
    filename : string
        Filename with full path.
    mode : string
        Read mode of file. Defaults to `r`. See more at
        https://docs.python.org/3.5/library/functions.html#open

    Returns
    -------
    string
        Returns data as string.

    """
    try:
        with open(filename, mode) as f:
            data = f.read()
        return data
    except IOError:
        print('An error occured trying to read the file {}.'.format(filename))
    except Exception as e:
        raise e 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def write_file(filename, data, mode='w'):
    """Write data in a file.

    Parameters
    ----------
    filename : string
        Filename with full path.
    data : string
        Data to be stored.
    mode : string
        Read mode of file. Defaults to `w`. See more at
        https://docs.python.org/3.5/library/functions.html#open

    """
    try:
        with open(filename, mode) as f:
            f.write(data)
    except IOError:
        print('An error occured trying to write the file {}.'.format(filename))
    except Exception as e:
        raise e 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def read_file_json(filename):
    """Read in a json file.

    See more about the json module at
    https://docs.python.org/3.5/library/json.html

    Parameters
    ----------
    filename : string
        Filename with full path.

    Returns
    -------
    dict
        Data as a json-formatted string.

    """
    try:
        return json_to_dict(read_file(filename, 'r'))
    except Exception as e:
        raise e 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def read_file_csv(filename):
    """Read in CSV file.

    See more at `csv.reader() <https://docs.python.org/3.5/library/csv.html>`_.

    Parameters
    ----------
    filename : string
        Full filename with path of file.

    Returns
    -------
    reader
        Reader object, which can be iterated over.

    """
    try:
        with open(filename, newline='') as csvfile:
            return csv.reader(csvfile, delimiter=',', quotechar='"')
    except Exception as e:
        raise e
    finally:
        csvfile.close() 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def dump(obj, fp, *args, **kwargs):
    """Serialize ``obj`` as a JSON formatted stream to ``fp``

    :param obj: object to be serialized
    :param fp: a ``.write()``-supporting file-like object
    :param default: function that returns a serializable version of an object,
                    :func:`to_primitive` is used by default.
    :param args: extra arguments, please see documentation \
    of `json.dump <https://docs.python.org/2/library/json.html#basic-usage>`_
    :param kwargs: extra named parameters, please see documentation \
    of `json.dump <https://docs.python.org/2/library/json.html#basic-usage>`_

    .. versionchanged:: 1.3
       The *default* parameter now uses :func:`to_primitive` by default.
    """
    default = kwargs.get('default', to_primitive)
    return json.dump(obj, fp, default=default, *args, **kwargs) 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def default(self, obj):
        """Handle special types for json.dumps.

        If obj is a model from dokomoforms.models, return a dictionary
        representation.

        If obj is a datetime.date or datetime.time, return an
        ISO 8601 representation string.

        If obj is a psycpg2 Range, return its string representation.

        Otherwise, throw a TypeError.

        See
        https://docs.python.org/3/library/json.html#json.JSONEncoder.default
        """
        try:
            return jsonify(obj, raise_exception=True)
        except NotJSONifiableError:
            return super().default(obj) 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def _json_default(obj):
    """
    Coerce everything to strings.

    All objects representing time get output as ISO8601.
    """
    if isinstance(obj, (datetime.date, datetime.time, datetime.datetime)):
        return obj.isoformat()

    elif isinstance(obj, Exception):
        return "Exception: %s" % str(obj)

    return str(obj)


# skip natural LogRecord attributes
# http://docs.python.org/library/logging.html#logrecord-attributes 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def __init__(self, *args, **kwargs):
        """
        :param json_default: a function for encoding non-standard objects
            as outlined in http://docs.python.org/2/library/json.html
        :param json_encoder: optional custom encoder
        :param json_serializer: a :meth:`json.dumps`-compatible callable
            that will be used to serialize the log record.
        :param prefix: an optional key prefix to nest logs
        """
        self.json_default = kwargs.pop("json_default", _json_default)
        self.json_encoder = kwargs.pop("json_encoder", None)
        self.json_serializer = kwargs.pop("json_serializer", json.dumps)
        self.default_values = kwargs.pop("default_extra", {})
        self.prefix_key = kwargs.pop("prefix_key", "data")

        logging.Formatter.__init__(self, *args, **kwargs)

        self._fmt_parameters = self._parse_format_string()
        self._skip_fields = set(self._fmt_parameters)
        self._skip_fields.update(RESERVED_ATTRS) 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def default(self, o: Any) -> Any:  # pragma: no cover
        """Return serializable robot objects."""
        # TODO: use @overload to split function
        # BODY: Reduces cyclomatic complexity; but requires NumPy typing
        if isinstance(o, np.ndarray):
            return o.tolist()
        elif isinstance(o, np.random.RandomState):
            return None
        elif isinstance(o, np.generic):
            return str(o)
        else:
            try:
                o = o.__dict__
            except AttributeError:
                pass
            else:
                return o

        # let the base class default method raise the TypeError
        # https://docs.python.org/3/library/json.html
        return json.JSONEncoder.default(self, o) 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def clean_doi(dirty_doi, return_none_if_error=False):
    if not dirty_doi:
        if return_none_if_error:
            return None
        else:
            raise NoDoiException("There's no DOI at all.")

    dirty_doi = dirty_doi.strip()
    dirty_doi = dirty_doi.lower()

    # test cases for this regex are at https://regex101.com/r/zS4hA0/1
    p = re.compile(ur'(10\.\d+\/[^\s]+)')

    matches = re.findall(p, dirty_doi)
    if len(matches) == 0:
        if return_none_if_error:
            return None
        else:
            raise NoDoiException("There's no valid DOI.")

    match = matches[0]
    match = remove_nonprinting_characters(match)

    try:
        resp = unicode(match, "utf-8")  # unicode is valid in dois
    except (TypeError, UnicodeDecodeError):
        resp = match

    # remove any url fragments
    if u"#" in resp:
        resp = resp.split(u"#")[0]

    # remove double quotes, they shouldn't be there as per http://www.doi.org/syntax.html
    resp = resp.replace('"', '')

    # remove trailing period, comma -- it is likely from a sentence or citation
    if resp.endswith(u",") or resp.endswith(u"."):
        resp = resp[:-1]

    return resp 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def get_random_dois(n, from_date=None, only_journal_articles=True):
    dois = []
    while len(dois) < n:
        # api takes a max of 100
        number_this_round = min(n, 100)
        url = u"https://api.crossref.org/works?sample={}".format(number_this_round)
        if only_journal_articles:
            url += u"&filter=type:journal-article"
        if from_date:
            url += u",from-pub-date:{}".format(from_date)
        print url
        print "calling crossref, asking for {} dois, so far have {} of {} dois".format(
            number_this_round, len(dois), n)
        r = requests.get(url)
        items = r.json()["message"]["items"]
        dois += [item["DOI"].lower() for item in items]
    return dois


# from https://github.com/elastic/elasticsearch-py/issues/374
# to work around unicode problem
# class JSONSerializerPython2(elasticsearch.serializer.JSONSerializer):
#     """Override elasticsearch library serializer to ensure it encodes utf characters during json dump.
#     See original at: https://github.com/elastic/elasticsearch-py/blob/master/elasticsearch/serializer.py#L42
#     A description of how ensure_ascii encodes unicode characters to ensure they can be sent across the wire
#     as ascii can be found here: https://docs.python.org/2/library/json.html#basic-usage
#     """
#     def dumps(self, data):
#         # don't serialize strings
#         if isinstance(data, elasticsearch.compat.string_types):
#             return data
#         try:
#             return json.dumps(data, default=self.default, ensure_ascii=True)
#         except (ValueError, TypeError) as e:
#             raise elasticsearch.exceptions.SerializationError(data, e) 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def get_tree(page):
    page = page.replace(" ", " ")  # otherwise starts-with for lxml doesn't work
    try:
        tree = html.fromstring(page)
    except (etree.XMLSyntaxError, etree.ParserError) as e:
        print u"not parsing, beause etree error in get_tree: {}".format(e)
        tree = None
    return tree 

# 需要导入模块: import json [as 别名]
# 或者: from json import html [as 别名]
def consume(self, subscription_name, callback, scheduler):
        """Begin listening to topic from the SubscriberClient.

        :param subscription_name: str Subscription name
        :param callback: Function which act on a topic message
        :param scheduler: `Thread pool-based scheduler.<https://googleapis.dev/python/pubsub/latest/subscriber/api/scheduler.html?highlight=threadscheduler#google.cloud.pubsub_v1.subscriber.scheduler.ThreadScheduler>`_  # noqa
        :return: `Future <https://googleapis.github.io/google-cloud-python/latest/pubsub/subscriber/api/futures.html>`_  # noqa
        """
        subscription_path = self._client.subscription_path(
            self._gc_project_id, subscription_name
        )
        return self._client.subscribe(
            subscription_path, callback=callback, scheduler=scheduler
        )