We Keep Coding

Python script ran OK for weeks using cron job and it's now giving a KeyError

Here's the code I'm trying to run. Works when executed from PyCharm. I set up a cronjob and it worked wonders for weeks. It's now giving a KeyError out of the bloom. Can't find what's wrong since I haven't touched anything in the cronjob.
import csv
import json
import os
import random
import time
from urllib.parse import urlencode
import requests
API_URL = "https://community.koodomobile.com/widget/pointsLeaderboard?"
LEADERBOARD_FILE = "leaderboard_data.json"
def get_leaderboard(period: str = "allTime", max_results: int = 20) -> list:
payload = {"period": period, "maxResults": max_results}
return requests.get(f"{API_URL}{urlencode(payload)}").json()
def dump_leaderboard_data(leaderboard_data: dict) -> None:
with open("leaderboard_data.json", "w") as jf:
json.dump(leaderboard_data, jf, indent=4, sort_keys=True)
def read_leaderboard_data(data_file: str) -> dict:
with open(data_file) as f:
return json.load(f)
def parse_leaderboard(leaderboard: list) -> dict:
return {
item["name"]: {
"id": item["id"],
"score_data": {
time.strftime("%Y-%m-%d %H:%M"): item["points"],
},
"rank": item["leaderboardPosition"],
} for item in leaderboard
}
def update_leaderboard_data(target: dict, new_data: dict) -> dict:
for player, stats in new_data.items():
target[player]["rank"] = stats["rank"]
target[player]["score_data"].update(stats["score_data"])
return target
def leaderboard_to_csv(leaderboard: dict) -> None:
data_rows = [
[player] + list(stats["score_data"].values())
for player, stats in leaderboard.items()
]
random_player = random.choice(list(leaderboard.keys()))
dates = list(leaderboard[random_player]["score_data"])
with open("the_data.csv", "w") as output:
w = csv.writer(output)
w.writerow([""] + dates)
w.writerows(data_rows)
def script_runner():
if os.path.isfile(LEADERBOARD_FILE):
fresh_data = update_leaderboard_data(
target=read_leaderboard_data(LEADERBOARD_FILE),
new_data=parse_leaderboard(get_leaderboard()),
)
leaderboard_to_csv(fresh_data)
dump_leaderboard_data(fresh_data)
else:
dump_leaderboard_data(parse_leaderboard(get_leaderboard()))
if __name__ == "__main__":
script_runner()
Here's the error taht it gives me. Seems like there's a problem with dictionary hence the KeyError.
File "/Users/Rob/PycharmProjects/Koodo/TEST.Json.py", line 75, in <module>
script_runner()
File "/Users/Rob/PycharmProjects/Koodo/TEST.Json.py", line 64, in script_runner
fresh_data = update_leaderboard_data(
File "/Users/Rob/PycharmProjects/Koodo/TEST.Json.py", line 44, in update_leaderboard_data
target[player]["rank"] = stats["rank"]
KeyError: 'triggered123'
Here's the data in JSON file : https://pastebin.com/HQyL4Kyx

It looks to me like the first time your code is run, it caches the leaderboard.
On subsequent runs, it will update the existing leaderboard with the new values, by looping over each of the new entries, finding their username, and looking up that key in the older dictionary. However, if there's a new user, that key will not exist in the old dictionary.
You're getting the error because the player triggered123 is a new user to the leaderboard, and was listed after you first ran the script.
You need to update update_leaderboard_data to handle this case (by checking if the key exists in the dictionary before attempting to access it).

That's because the key named triggered123 is NOT present in the dictionary target.
Source: https://wiki.python.org/moin/KeyError
The problem is that in update_leaderboard_data you iterate over the new data and use them to lookup in the old data. If a new key does not already exists in the old data, you'll get the KeyError.
Try to print the dict target to see if the key triggered123 is in it.
Or use the get method of the dict with a default value: so no error wil be raised, and you'll be able to search this default value in your output.

Creating namedtuple valid for differents parameters

I'm trying to figure it out a way to create a namedtuple with variable fields depending on the data you receive, in my case, I'm using the data from StatCounter and not on all the periods are the same browsers. I tried this way but it is a bit ugly and I'm sure there is a better way to achieve it.
def namedtuple_fixed(name: str, fields: List[str]) -> namedtuple:
"""Check the fields of the namedtuple and changes the invalid ones."""
fields_fixed: List[str] = []
for field in fields:
field = field.replace(" ", "_")
if field[0].isdigit():
field = f"n{field}"
fields_fixed.append(field)
return namedtuple(name, fields_fixed)
Records: namedtuple = namedtuple("empty_namedtuple", "")
def read_file(file: str) -> List["Records"]:
"""
Read the file with info about the percentage of use of various browsers
"""
global Records
with open(file, encoding="UTF-8") as browsers_file:
reader: Iterator[List[str]] = csv.reader(browsers_file)
field_names: List[str] = next(reader)
Records = namedtuple_fixed("Record", field_names)
result: List[Records] = [
Records(
*[
dt.datetime.strptime(n, "%Y-%m").date()
if record.index(n) == 0
else float(n)
for n in record
]
)
for record in reader
]
return result
The "namedtuple_fixed" function is to fix the names that have invalid identifiers.
Basically, I want to create a named tuple that receives a variable number of parameters, depending on the file you want to analyze. And if it's with type checking incorporated (I mean using NamedTuple from the typing module), much better.
Thanks in advance.

This solves my problem, but just partially
class Record(SimpleNamespace):
def __repr__(self):
items = [f"{key}={value!r}" for key, value in self.__dict__.items()]
return f"Record({', '.join(items)})"
Using the types.SimpleSpace documentation
And it can cause problems, like for example if you initiallize a Record like the following:
foo = Record(**{"a": 1, "3a": 2})
print(foo.a) # Ok
print(foo.3a) # Syntax Error

How to Parse YAML Using PyYAML if there are '!' within the YAML

I have a YAML file that I'd like to parse the description variable only; however, I know that the exclamation points in my CloudFormation template (YAML file) are giving PyYAML trouble.
I am receiving the following error:
yaml.constructor.ConstructorError: could not determine a constructor for the tag '!Equals'
The file has many !Ref and !Equals. How can I ignore these constructors and get a specific variable I'm looking for -- in this case, the description variable.

If you have to deal with a YAML document with multiple different tags, and
are only interested in a subset of them, you should still
handle them all. If the elements you are intersted in are nested
within other tagged constructs you at least need to handle all of the "enclosing" tags
properly.
There is however no need to handle all of the tags individually, you
can write a constructor routine that can handle mappings, sequences
and scalars register that to PyYAML's SafeLoader using:
import yaml
inp = """\
MyEIP:
Type: !Join [ "::", [AWS, EC2, EIP] ]
Properties:
InstanceId: !Ref MyEC2Instance
"""
description = []
def any_constructor(loader, tag_suffix, node):
if isinstance(node, yaml.MappingNode):
return loader.construct_mapping(node)
if isinstance(node, yaml.SequenceNode):
return loader.construct_sequence(node)
return loader.construct_scalar(node)
yaml.add_multi_constructor('', any_constructor, Loader=yaml.SafeLoader)
data = yaml.safe_load(inp)
print(data)
which gives:
{'MyEIP': {'Type': ['::', ['AWS', 'EC2', 'EIP']], 'Properties': {'InstanceId': 'MyEC2Instance'}}}
(inp can also be a file opened for reading).
As you see above will also continue to work if an unexpected !Join tag shows up in your code,
as well as any other tag like !Equal. The tags are just dropped.
Since there are no variables in YAML, it is a bit of guesswork what
you mean by "like to parse the description variable only". If that has
an explicit tag (e.g. !Description), you can filter out the values by adding 2-3 lines
to the any_constructor, by matching the tag_suffix parameter.
if tag_suffix == u'!Description':
description.append(loader.construct_scalar(node))
It is however more likely that there is some key in a mapping that is a scalar description,
and that you are interested in the value associated with that key.
if isinstance(node, yaml.MappingNode):
d = loader.construct_mapping(node)
for k in d:
if k == 'description':
description.append(d[k])
return d
If you know the exact position in the data hierarchy, You can of
course also walk the data structure and extract anything you need
based on keys or list positions. Especially in that case you'd be better of
using my ruamel.yaml, was this can load tagged YAML in round-trip mode without
extra effort (assuming the above inp):
from ruamel.yaml import YAML
with YAML() as yaml:
data = yaml.load(inp)

You can define a custom constructors using a custom yaml.SafeLoader
import yaml
doc = '''
Conditions:
CreateNewSecurityGroup: !Equals [!Ref ExistingSecurityGroup, NONE]
'''
class Equals(object):
def __init__(self, data):
self.data = data
def __repr__(self):
return "Equals(%s)" % self.data
class Ref(object):
def __init__(self, data):
self.data = data
def __repr__(self):
return "Ref(%s)" % self.data
def create_equals(loader,node):
value = loader.construct_sequence(node)
return Equals(value)
def create_ref(loader,node):
value = loader.construct_scalar(node)
return Ref(value)
class Loader(yaml.SafeLoader):
pass
yaml.add_constructor(u'!Equals', create_equals, Loader)
yaml.add_constructor(u'!Ref', create_ref, Loader)
a = yaml.load(doc, Loader)
print(a)
Outputs:
{'Conditions': {'CreateNewSecurityGroup': Equals([Ref(ExistingSecurityGroup), 'NONE'])}}

Parsing a file with multiple xmls in it

Is there a way to parse a file which contains multiple xmls in it?
eg., if I have a file called stocks.xml and within the stocks.xml i have more than one xml content, is there any way to parse this xml file ?.
-- stocks.xml
<?xml version="1.0" encoding="ASCII"?><PRODUCT><ID>A001</ID>..</PRODUCT><SHOP-1><QUANTITY>nn</QUANITY><SHOP-1><QUANTITY>nn</QUANITY>
<?xml version="1.0" encoding="ASCII"?><PRODUCT><ID>A002</ID>..</PRODUCT><SHOP-1><QUANTITY>nn</QUANITY><SHOP-1><QUANTITY>nn</QUANITY>

If you can assume that each xml document begins with <?xml version="1.0" ..., simply read the file line-by-line looking for a lines that match that pattern (or, read all the data and then do a search through the data).
Once you find a line, keep it, and append subsequent lines until the next xml document is found or you hit EOF. lather, rinse, repeat.
You now have one xml document in a string. You can then parse the string using the normal XML parsing tools, or you write it to a file.
This will work fine in most cases, but of course it could fall down if one of your embedded xml documents contains data that exactly matches the same pattern as the beginning of a document. Most likely you don't have to worry about that, and if you do there are ways to avoid that with a little more cleverness.
The right solution really depends on your needs. If you're creating a general purpose must-work-at-all-times solution this might not be right for you. For real world, special purpose problems it's probably more than Good Enough, and often Good Enough is indeed Good Enough.

You should see this python program by Michiel de Hoon
And if you want to parse multiple files, then a rule to detect that we are in other xml must be developed, for example,at first you read <stocks> .... and at the end you must reead </stocks> when you find that then if there is something else,well, continue reading and do the same parser until reach eof.
# Copyright 2008 by Michiel de Hoon. All rights reserved.
# This code is part of the Biopython distribution and governed by its
# license. Please see the LICENSE file that should have been included
# as part of this package.
"""Parser for XML results returned by NCBI's Entrez Utilities. This
parser is used by the read() function in Bio.Entrez, and is not intended
be used directly.
"""
# The question is how to represent an XML file as Python objects. Some
# XML files returned by NCBI look like lists, others look like dictionaries,
# and others look like a mix of lists and dictionaries.
#
# My approach is to classify each possible element in the XML as a plain
# string, an integer, a list, a dictionary, or a structure. The latter is a
# dictionary where the same key can occur multiple times; in Python, it is
# represented as a dictionary where that key occurs once, pointing to a list
# of values found in the XML file.
#
# The parser then goes through the XML and creates the appropriate Python
# object for each element. The different levels encountered in the XML are
# preserved on the Python side. So a subelement of a subelement of an element
# is a value in a dictionary that is stored in a list which is a value in
# some other dictionary (or a value in a list which itself belongs to a list
# which is a value in a dictionary, and so on). Attributes encountered in
# the XML are stored as a dictionary in a member .attributes of each element,
# and the tag name is saved in a member .tag.
#
# To decide which kind of Python object corresponds to each element in the
# XML, the parser analyzes the DTD referred at the top of (almost) every
# XML file returned by the Entrez Utilities. This is preferred over a hand-
# written solution, since the number of DTDs is rather large and their
# contents may change over time. About half the code in this parser deals
# wih parsing the DTD, and the other half with the XML itself.
import os.path
import urlparse
import urllib
import warnings
from xml.parsers import expat
# The following four classes are used to add a member .attributes to integers,
# strings, lists, and dictionaries, respectively.
class IntegerElement(int):
def __repr__(self):
text = int.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "IntegerElement(%s, attributes=%s)" % (text, repr(attributes))
class StringElement(str):
def __repr__(self):
text = str.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "StringElement(%s, attributes=%s)" % (text, repr(attributes))
class UnicodeElement(unicode):
def __repr__(self):
text = unicode.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "UnicodeElement(%s, attributes=%s)" % (text, repr(attributes))
class ListElement(list):
def __repr__(self):
text = list.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "ListElement(%s, attributes=%s)" % (text, repr(attributes))
class DictionaryElement(dict):
def __repr__(self):
text = dict.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "DictElement(%s, attributes=%s)" % (text, repr(attributes))
# A StructureElement is like a dictionary, but some of its keys can have
# multiple values associated with it. These values are stored in a list
# under each key.
class StructureElement(dict):
def __init__(self, keys):
dict.__init__(self)
for key in keys:
dict.__setitem__(self, key, [])
self.listkeys = keys
def __setitem__(self, key, value):
if key in self.listkeys:
self[key].append(value)
else:
dict.__setitem__(self, key, value)
def __repr__(self):
text = dict.__repr__(self)
try:
attributes = self.attributes
except AttributeError:
return text
return "DictElement(%s, attributes=%s)" % (text, repr(attributes))
class NotXMLError(ValueError):
def __init__(self, message):
self.msg = message
def __str__(self):
return "Failed to parse the XML data (%s). Please make sure that the input data are in XML format." % self.msg
class CorruptedXMLError(ValueError):
def __init__(self, message):
self.msg = message
def __str__(self):
return "Failed to parse the XML data (%s). Please make sure that the input data are not corrupted." % self.msg
class ValidationError(ValueError):
"""Validating parsers raise this error if the parser finds a tag in the XML that is not defined in the DTD. Non-validating parsers do not raise this error. The Bio.Entrez.read and Bio.Entrez.parse functions use validating parsers by default (see those functions for more information)"""
def __init__(self, name):
self.name = name
def __str__(self):
return "Failed to find tag '%s' in the DTD. To skip all tags that are not represented in the DTD, please call Bio.Entrez.read or Bio.Entrez.parse with validate=False." % self.name
class DataHandler:
home = os.path.expanduser('~')
local_dtd_dir = os.path.join(home, '.biopython', 'Bio', 'Entrez', 'DTDs')
del home
from Bio import Entrez
global_dtd_dir = os.path.join(str(Entrez.__path__[0]), "DTDs")
del Entrez
def __init__(self, validate):
self.stack = []
self.errors = []
self.integers = []
self.strings = []
self.lists = []
self.dictionaries = []
self.structures = {}
self.items = []
self.dtd_urls = []
self.validating = validate
self.parser = expat.ParserCreate(namespace_separator=" ")
self.parser.SetParamEntityParsing(expat.XML_PARAM_ENTITY_PARSING_ALWAYS)
self.parser.XmlDeclHandler = self.xmlDeclHandler
def read(self, handle):
"""Set up the parser and let it parse the XML results"""
try:
self.parser.ParseFile(handle)
except expat.ExpatError, e:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, so we can be sure that
# we are parsing XML data. Most likely, the XML file is
# corrupted.
raise CorruptedXMLError(e)
else:
# We have not seen the initial <!xml declaration, so probably
# the input data is not in XML format.
raise NotXMLError(e)
try:
return self.object
except AttributeError:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, and expat didn't notice
# any errors, so self.object should be defined. If not, this is
# a bug.
raise RuntimeError("Failed to parse the XML file correctly, possibly due to a bug in Bio.Entrez. Please contact the Biopython developers at biopython-dev#biopython.org for assistance.")
else:
# We did not see the initial <!xml declaration, so probably
# the input data is not in XML format.
raise NotXMLError("XML declaration not found")
def parse(self, handle):
BLOCK = 1024
while True:
#Read in another block of the file...
text = handle.read(BLOCK)
if not text:
# We have reached the end of the XML file
if self.stack:
# No more XML data, but there is still some unfinished
# business
raise CorruptedXMLError
try:
for record in self.object:
yield record
except AttributeError:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, and expat
# didn't notice any errors, so self.object should be
# defined. If not, this is a bug.
raise RuntimeError("Failed to parse the XML file correctly, possibly due to a bug in Bio.Entrez. Please contact the Biopython developers at biopython-dev#biopython.org for assistance.")
else:
# We did not see the initial <!xml declaration, so
# probably the input data is not in XML format.
raise NotXMLError("XML declaration not found")
self.parser.Parse("", True)
self.parser = None
return
try:
self.parser.Parse(text, False)
except expat.ExpatError, e:
if self.parser.StartElementHandler:
# We saw the initial <!xml declaration, so we can be sure
# that we are parsing XML data. Most likely, the XML file
# is corrupted.
raise CorruptedXMLError(e)
else:
# We have not seen the initial <!xml declaration, so
# probably the input data is not in XML format.
raise NotXMLError(e)
if not self.stack:
# Haven't read enough from the XML file yet
continue
records = self.stack[0]
if not isinstance(records, list):
raise ValueError("The XML file does not represent a list. Please use Entrez.read instead of Entrez.parse")
while len(records) > 1: # Then the top record is finished
record = records.pop(0)
yield record
def xmlDeclHandler(self, version, encoding, standalone):
# XML declaration found; set the handlers
self.parser.StartElementHandler = self.startElementHandler
self.parser.EndElementHandler = self.endElementHandler
self.parser.CharacterDataHandler = self.characterDataHandler
self.parser.ExternalEntityRefHandler = self.externalEntityRefHandler
self.parser.StartNamespaceDeclHandler = self.startNamespaceDeclHandler
def startNamespaceDeclHandler(self, prefix, un):
raise NotImplementedError("The Bio.Entrez parser cannot handle XML data that make use of XML namespaces")
def startElementHandler(self, name, attrs):
self.content = ""
if name in self.lists:
object = ListElement()
elif name in self.dictionaries:
object = DictionaryElement()
elif name in self.structures:
object = StructureElement(self.structures[name])
elif name in self.items: # Only appears in ESummary
name = str(attrs["Name"]) # convert from Unicode
del attrs["Name"]
itemtype = str(attrs["Type"]) # convert from Unicode
del attrs["Type"]
if itemtype=="Structure":
object = DictionaryElement()
elif name in ("ArticleIds", "History"):
object = StructureElement(["pubmed", "medline"])
elif itemtype=="List":
object = ListElement()
else:
object = StringElement()
object.itemname = name
object.itemtype = itemtype
elif name in self.strings + self.errors + self.integers:
self.attributes = attrs
return
else:
# Element not found in DTD
if self.validating:
raise ValidationError(name)
else:
# this will not be stored in the record
object = ""
if object!="":
object.tag = name
if attrs:
object.attributes = dict(attrs)
if len(self.stack)!=0:
current = self.stack[-1]
try:
current.append(object)
except AttributeError:
current[name] = object
self.stack.append(object)
def endElementHandler(self, name):
value = self.content
if name in self.errors:
if value=="":
return
else:
raise RuntimeError(value)
elif name in self.integers:
value = IntegerElement(value)
elif name in self.strings:
# Convert Unicode strings to plain strings if possible
try:
value = StringElement(value)
except UnicodeEncodeError:
value = UnicodeElement(value)
elif name in self.items:
self.object = self.stack.pop()
if self.object.itemtype in ("List", "Structure"):
return
elif self.object.itemtype=="Integer" and value:
value = IntegerElement(value)
else:
# Convert Unicode strings to plain strings if possible
try:
value = StringElement(value)
except UnicodeEncodeError:
value = UnicodeElement(value)
name = self.object.itemname
else:
self.object = self.stack.pop()
return
value.tag = name
if self.attributes:
value.attributes = dict(self.attributes)
del self.attributes
current = self.stack[-1]
if current!="":
try:
current.append(value)
except AttributeError:
current[name] = value
def characterDataHandler(self, content):
self.content += content
def elementDecl(self, name, model):
"""This callback function is called for each element declaration:
<!ELEMENT name (...)>
encountered in a DTD. The purpose of this function is to determine
whether this element should be regarded as a string, integer, list
dictionary, structure, or error."""
if name.upper()=="ERROR":
self.errors.append(name)
return
if name=='Item' and model==(expat.model.XML_CTYPE_MIXED,
expat.model.XML_CQUANT_REP,
None, ((expat.model.XML_CTYPE_NAME,
expat.model.XML_CQUANT_NONE,
'Item',
()
),
)
):
# Special case. As far as I can tell, this only occurs in the
# eSummary DTD.
self.items.append(name)
return
# First, remove ignorable parentheses around declarations
while (model[0] in (expat.model.XML_CTYPE_SEQ,
expat.model.XML_CTYPE_CHOICE)
and model[1] in (expat.model.XML_CQUANT_NONE,
expat.model.XML_CQUANT_OPT)
and len(model[3])==1):
model = model[3][0]
# PCDATA declarations correspond to strings
if model[0] in (expat.model.XML_CTYPE_MIXED,
expat.model.XML_CTYPE_EMPTY):
self.strings.append(name)
return
# List-type elements
if (model[0] in (expat.model.XML_CTYPE_CHOICE,
expat.model.XML_CTYPE_SEQ) and
model[1] in (expat.model.XML_CQUANT_PLUS,
expat.model.XML_CQUANT_REP)):
self.lists.append(name)
return
# This is the tricky case. Check which keys can occur multiple
# times. If only one key is possible, and it can occur multiple
# times, then this is a list. If more than one key is possible,
# but none of them can occur multiple times, then this is a
# dictionary. Otherwise, this is a structure.
# In 'single' and 'multiple', we keep track which keys can occur
# only once, and which can occur multiple times.
single = []
multiple = []
# The 'count' function is called recursively to make sure all the
# children in this model are counted. Error keys are ignored;
# they raise an exception in Python.
def count(model):
quantifier, name, children = model[1:]
if name==None:
if quantifier in (expat.model.XML_CQUANT_PLUS,
expat.model.XML_CQUANT_REP):
for child in children:
multiple.append(child[2])
else:
for child in children:
count(child)
elif name.upper()!="ERROR":
if quantifier in (expat.model.XML_CQUANT_NONE,
expat.model.XML_CQUANT_OPT):
single.append(name)
elif quantifier in (expat.model.XML_CQUANT_PLUS,
expat.model.XML_CQUANT_REP):
multiple.append(name)
count(model)
if len(single)==0 and len(multiple)==1:
self.lists.append(name)
elif len(multiple)==0:
self.dictionaries.append(name)
else:
self.structures.update({name: multiple})
def open_dtd_file(self, filename):
path = os.path.join(DataHandler.local_dtd_dir, filename)
try:
handle = open(path, "rb")
except IOError:
pass
else:
return handle
path = os.path.join(DataHandler.global_dtd_dir, filename)
try:
handle = open(path, "rb")
except IOError:
pass
else:
return handle
return None
def externalEntityRefHandler(self, context, base, systemId, publicId):
"""The purpose of this function is to load the DTD locally, instead
of downloading it from the URL specified in the XML. Using the local
DTD results in much faster parsing. If the DTD is not found locally,
we try to download it. If new DTDs become available from NCBI,
putting them in Bio/Entrez/DTDs will allow the parser to see them."""
urlinfo = urlparse.urlparse(systemId)
#Following attribute requires Python 2.5+
#if urlinfo.scheme=='http':
if urlinfo[0]=='http':
# Then this is an absolute path to the DTD.
url = systemId
elif urlinfo[0]=='':
# Then this is a relative path to the DTD.
# Look at the parent URL to find the full path.
url = self.dtd_urls[-1]
source = os.path.dirname(url)
url = os.path.join(source, systemId)
self.dtd_urls.append(url)
# First, try to load the local version of the DTD file
location, filename = os.path.split(systemId)
handle = self.open_dtd_file(filename)
if not handle:
# DTD is not available as a local file. Try accessing it through
# the internet instead.
message = """\
Unable to load DTD file %s.
Bio.Entrez uses NCBI's DTD files to parse XML files returned by NCBI Entrez.
Though most of NCBI's DTD files are included in the Biopython distribution,
sometimes you may find that a particular DTD file is missing. While we can
access the DTD file through the internet, the parser is much faster if the
required DTD files are available locally.
For this purpose, please download %s from
%s
and save it either in directory
%s
or in directory
%s
in order for Bio.Entrez to find it.
Alternatively, you can save %s in the directory
Bio/Entrez/DTDs in the Biopython distribution, and reinstall Biopython.
Please also inform the Biopython developers about this missing DTD, by
reporting a bug on http://bugzilla.open-bio.org/ or sign up to our mailing
list and emailing us, so that we can include it with the next release of
Biopython.
Proceeding to access the DTD file through the internet...
""" % (filename, filename, url, self.global_dtd_dir, self.local_dtd_dir, filename)
warnings.warn(message)
try:
handle = urllib.urlopen(url)
except IOError:
raise RuntimeException("Failed to access %s at %s" % (filename, url))
parser = self.parser.ExternalEntityParserCreate(context)
parser.ElementDeclHandler = self.elementDecl
parser.ParseFile(handle)
handle.close()
self.dtd_urls.pop()
return 1

So you have a file containing multiple XML documents one after the other? Here is an example which strips out the <?xml ?> PIs and wraps the data in a root tag to parse the whole thing as a single XML document:
import re
import lxml.etree
re_strip_pi = re.compile('<\?xml [^?>]+\?>', re.M)
data = '<root>' + open('stocks.xml', 'rb').read() + '</root>'
match = re_strip_pi.search(data)
data = re_strip_pi.sub('', data)
tree = lxml.etree.fromstring(match.group() + data)
for prod in tree.xpath('//PRODUCT'):
print prod

You can't have multiple XML documents in one XML file. Split the documents - composed in whatever way - into single XML files and parse them one-by-one.

How do I check if a string is valid JSON in Python?

In Python, is there a way to check if a string is valid JSON before trying to parse it?
For example working with things like the Facebook Graph API, sometimes it returns JSON, sometimes it could return an image file.

You can try to do json.loads(), which will throw a ValueError if the string you pass can't be decoded as JSON.
In general, the "Pythonic" philosophy for this kind of situation is called EAFP, for Easier to Ask for Forgiveness than Permission.

Example Python script returns a boolean if a string is valid json:
import json
def is_json(myjson):
try:
json.loads(myjson)
except ValueError as e:
return False
return True
Which prints:
print is_json("{}") #prints True
print is_json("{asdf}") #prints False
print is_json('{ "age":100}') #prints True
print is_json("{'age':100 }") #prints False
print is_json("{\"age\":100 }") #prints True
print is_json('{"age":100 }') #prints True
print is_json('{"foo":[5,6.8],"foo":"bar"}') #prints True
Convert a JSON string to a Python dictionary:
import json
mydict = json.loads('{"foo":"bar"}')
print(mydict['foo']) #prints bar
mylist = json.loads("[5,6,7]")
print(mylist)
[5, 6, 7]
Convert a python object to JSON string:
foo = {}
foo['gummy'] = 'bear'
print(json.dumps(foo)) #prints {"gummy": "bear"}
If you want access to low-level parsing, don't roll your own, use an existing library: http://www.json.org/
Great tutorial on python JSON module: https://pymotw.com/2/json/
Is String JSON and show syntax errors and error messages:
sudo cpan JSON::XS
echo '{"foo":[5,6.8],"foo":"bar" bar}' > myjson.json
json_xs -t none < myjson.json
Prints:
, or } expected while parsing object/hash, at character offset 28 (before "bar}
at /usr/local/bin/json_xs line 183, <STDIN> line 1.
json_xs is capable of syntax checking, parsing, prittifying, encoding, decoding and more:
https://metacpan.org/pod/json_xs

I would say parsing it is the only way you can really entirely tell. Exception will be raised by python's json.loads() function (almost certainly) if not the correct format. However, the the purposes of your example you can probably just check the first couple of non-whitespace characters...
I'm not familiar with the JSON that facebook sends back, but most JSON strings from web apps will start with a open square [ or curly { bracket. No images formats I know of start with those characters.
Conversely if you know what image formats might show up, you can check the start of the string for their signatures to identify images, and assume you have JSON if it's not an image.
Another simple hack to identify a graphic, rather than a text string, in the case you're looking for a graphic, is just to test for non-ASCII characters in the first couple of dozen characters of the string (assuming the JSON is ASCII).

I came up with an generic, interesting solution to this problem:
class SafeInvocator(object):
def __init__(self, module):
self._module = module
def _safe(self, func):
def inner(*args, **kwargs):
try:
return func(*args, **kwargs)
except:
return None
return inner
def __getattr__(self, item):
obj = getattr(self.module, item)
return self._safe(obj) if hasattr(obj, '__call__') else obj
and you can use it like so:
safe_json = SafeInvocator(json)
text = "{'foo':'bar'}"
item = safe_json.loads(text)
if item:
# do something

An effective, and reliable way to check for valid JSON. If the 'get' accessor does't throw an AttributeError then the JSON is valid.
import json
valid_json = {'type': 'doc', 'version': 1, 'content': [{'type': 'paragraph', 'content': [{'text': 'Request for widget', 'type': 'text'}]}]}
invalid_json = 'opo'
def check_json(p, attr):
doc = json.loads(json.dumps(p))
try:
doc.get(attr) # we don't care if the value exists. Only that 'get()' is accessible
return True
except AttributeError:
return False
To use, we call the function and look for a key.
# Valid JSON
print(check_json(valid_json, 'type'))
Returns 'True'
# Invalid JSON / Key not found
print(check_json(invalid_json, 'type'))
Returns 'False'

Much simple in try block. You can then validate if the body is a valid JSON
async def get_body(request: Request):
try:
body = await request.json()
except:
body = await request.body()
return body