create a dictionary from file python - python

I am new to python and am trying to read a file and create a dictionary from it.
The format is as follows:
.1.3.6.1.4.1.14823.1.1.27 {
TYPE = Switch
VENDOR = Aruba
MODEL = ArubaS3500-48T
CERTIFICATION = CERTIFIED
CONT = Aruba-Switch
HEALTH = ARUBA-Controller
VLAN = Dot1q INSTRUMENTATION:
Card-Fault = ArubaController:DeviceID
CPU/Memory = ArubaController:DeviceID
Environment = ArubaSysExt:DeviceID
Interface-Fault = MIB2
Interface-Performance = MIB2
Port-Fault = MIB2
Port-Performance = MIB2
}
The first line OID (.1.3.6.1.4.1.14823.1.1.27 { ) I want this to be the key and the remaining lines are the values until the }
I have tried a few combinations but am not able to get the correct regex to match these
Any help please?
I have tried something like
lines = cache.readlines()
for line in lines:
searchObj = re.search(r'(^.\d.*{)(.*)$', line)
if searchObj:
(oid, cert ) = searchObj.groups()
results[searchObj(oid)] = ", ".join(line[1:])
print("searchObj.group() : ", searchObj.group(1))
print("searchObj.group(1) : ", searchObj.group(2))

You can try this:
import re
data = open('filename.txt').read()
the_key = re.findall("^\n*[\.\d]+", data)
values = [re.split("\s+\=\s+", i) for i in re.findall("[a-zA-Z0-9]+\s*\=\s*[a-zA-Z0-9]+", data)]
final_data = {the_key[0]:dict(values)}
Output:
{'\n.1.3.6.1.4.1.14823.1.1.27': {'VENDOR': 'Aruba', 'CERTIFICATION': 'CERTIFIED', 'Fault': 'MIB2', 'VLAN': 'Dot1q', 'Environment': 'ArubaSysExt', 'HEALTH': 'ARUBA', 'Memory': 'ArubaController', 'Performance': 'MIB2', 'CONT': 'Aruba', 'MODEL': 'ArubaS3500', 'TYPE': 'Switch'}}

You could use a nested dict comprehension along with an outer and inner regex.
Your blocks can be separated by
.numbers...numbers.. {
// values here
}
In terms of regular expression this can be formulated as
^\s* # start of line + whitespaces, eventually
(?P<key>\.[\d.]+)\s* # the key
{(?P<values>[^{}]+)} # everything between { and }
As you see, we split the parts into key/value pairs.
Your "inner" structure can be formulated like
(?P<key>\b[A-Z][-/\w]+\b) # the "inner" key
\s*=\s* # whitespaces, =, whitespaces
(?P<value>.+) # the value
Now let's build the "outer" and "inner" expressions together:
rx_outer = re.compile(r'^\s*(?P<key>\.[\d.]+)\s*{(?P<values>[^{}]+)}', re.MULTILINE)
rx_inner = re.compile(r'(?P<key>\b[A-Z][-/\w]+\b)\s*=\s*(?P<value>.+)')
result = {item.group('key'):
{match.group('key'): match.group('value')
for match in rx_inner.finditer(item.group('values'))}
for item in rx_outer.finditer(string)}
print(result)
A demo can be found on ideone.com.

Related

How to parse file with different structures in python

I am working on a file where data with a lot of structures. But I cannot figure out an efficient way to handle all of these. My idea is read line by line and find paratheses in pair. Is there any efficient way to match paratheses then I handle each type in specific logic?
Here is the file I am facing:
.....
# some header info that can be discarded
object node {
name R2-12-47-3_node_453;
phases ABCN;
voltage_A 7200+0.0j;
voltage_B -3600-6235j;
voltage_C -3600+6235j;
nominal_voltage 7200;
bustype SWING;
}
...
# a lot of objects node
object triplex_meter {
name R2-12-47-3_tm_403;
phases AS;
voltage_1 120;
voltage_2 120;
voltage_N 0;
nominal_voltage 120;
}
....
# a lot of object triplex_meter
object triplex_line {
groupid Triplex_Line;
name R2-12-47-3_tl_409;
phases AS;
from R2-12-47-3_tn_409;
to R2-12-47-3_tm_409;
length 30;
configuration triplex_line_configuration_1;
}
...
# a lot of object triplex_meter
#some nested objects...awh...
So my question is there way to quickly match "{" and "}" so that I can focus on the type inside.
I am expecting some logic like after parsing the file:
if obj_type == "node":
# to do 1
elif obj_type == "triplex_meter":
# to do 2
It seems easy to deal with this structure, but I am not sure exactly where to get started.
Code with comments
file = """
object node {
name R2-12-47-3_node_453
phases ABCN
voltage_A 7200+0.0j
voltage_B - 3600-6235j
voltage_C - 3600+6235j
nominal_voltage 7200
bustype SWING
}
object triplex_meter {
name R2-12-47-3_tm_403
phases AS
voltage_1 120
voltage_2 120
voltage_N 0
nominal_voltage 120
}
object triplex_line {
groupid Triplex_Line
name R2-12-47-3_tl_409
phases AS
from R2-12-47-3_tn_409
to R2-12-47-3_tm_409
length 30
configuration triplex_line_configuration_1
}"""
# New python dict
data = {}
# Generate a list with all object taken from file
x = file.replace('\n', '').replace(' - ', ' ').strip().split('object ')
for i in x:
# Exclude null items in the list to avoid errors
if i != '':
# Hard split
a, b = i.split('{')
c = b.split(' ')
# Generate a new list with non null elements
d = [e.replace('}', '') for e in c if e != '' and e != ' ']
# Needing a sub dict here for paired values
sub_d = {}
# Iterating over list to get paired values
for index in range(len(d)):
# We are working with paired values so we unpack only pair indexes
if index % 2 == 0:
# Inserting paired values in sub_dict
sub_d[d[index]] = d[index+1]
# Inserting sub_dict in main dict "data" using object name
data[a.strip()] = sub_d
print(data)
Output
{'node': {'name': 'R2-12-47-3_node_453', 'phases': 'ABCN', 'voltage_A': '7200+0.0j', 'voltage_B': '3600-6235j', 'voltage_C': '3600+6235j', 'nominal_voltage': '7200', 'bustype': 'SWING'}, 'triplex_meter': {'name': 'R2-12-47-3_tm_403', 'phases': 'AS', 'voltage_1': '120', 'voltage_2': '120', 'voltage_N': '0', 'nominal_voltage': '120'}, 'triplex_line': {'groupid': 'Triplex_Line', 'name': 'R2-12-47-3_tl_409', 'phases': 'AS', 'from': 'R2-12-47-3_tn_409', 'to': 'R2-12-47-3_tm_409', 'length': '30', 'configuration': 'triplex_line_configuration_1'}}
You can now use the python dict how you want.
For e.g.
print(data['triplex_meter']['name'])
EDIT
If you have got lots of "triplex_meter" objects in your file group it in a Python list before inserting them in the main dict

How can I refactor my code to return a collection of dictionaries?

def read_data(service_client):
data = list_data(domain, realm) # This returns a data frame
building_data = []
building_names = {}
all_buildings = {}
for elem in data.iterrows():
building = elem[1]['building_name']
region_id = elem[1]['region_id']
bandwith = elem[1]['bandwith']
building_id = elem[1]['building_id']
return {
'Building': building,
'Region Id': region_id,
'Bandwith': bandwith,
'Building Id': building_id,
}
Basically I am able to return a single dictionary value upon a iteration here in this example. I have tried printing it as well and others.
I am trying to find a way to store multiple dictionary values on each iteration and return it, instead of just returning one.. Does anyone know any ways to achieve this?
You may replace your for-loop with the following to get all dictionaries in a list.
naming = {
'building_name': 'Building',
'region_id': 'Region Id',
'bandwith': 'Bandwith',
'building_id': 'Building Id',
}
return [
row[list(naming.values())].to_dict()
for idx, row in data.rename(naming, axis=1).iterrows()
]

Converting dictionary into a list of dictionaries

So, I've been tasked with converting a string into a dict (has to be using regex). I've done a findall to separate each element but not sure how to put it together.
I have the following code:
import re
def edata():
with open("employeedata.txt", "r") as file:
employeedata = file.read()
IP_field = re.findall(r"\d+[.]\d+[.]\d+[.]\d+", employeedata)
username_field = re.findall (r"[a-z]+\d+|- -", employeedata)
date_field = re.findall (r"\d+\/[A-Z][a-z][0-9]+\/\d\d\d\d:\d+:\d+:\d+ -\d+", employeedata)
type_field = re.findall (r'"(.*)?"', employeedata)
Fields = ["IP","username","date","type"]
Fields2 = IP_field, username_field, date_field, type_field
dictionary = dict(zip(Fields,Fields2))
return dictionary
print(edata())
Current output:
{ "IP": ["190.912.120.151", "190.912.120.151"], "username": ["skynet10001", "skynet10001"] etc }
Expected output:
[{ "IP": "190.912.120.151", "username": "skynet10001" etc },
{ "IP": "190.912.120.151", "username": "skynet10001" etc }]
Another solution that uses the dictionary that you have already constructed. This code uses list comprehension and the zip function to produce a list of dictionaries from the existing dictionary variable.
import re
def edata():
with open("employeedata.txt", "r") as file:
employeedata = file.read()
IP_field = re.findall(r"\d+[.]\d+[.]\d+[.]\d+", employeedata)
username_field = re.findall (r"[a-z]+\d+|- -", employeedata)
date_field = re.findall (r"\[(.*?)\]", employeedata) ## changed your regex for the date field
type_field = re.findall (r'"(.*)?"', employeedata)
Fields = ["IP","username","date","type"]
Fields2 = IP_field, username_field, date_field, type_field
dictionary = dict(zip(Fields,Fields2))
result_dictionary = [dict(zip(dictionary, i)) for i in zip(*dictionary.values())] ## convert to list of dictionaries
return result_dictionary
print(edata())
You can use
import re
rx = re.compile(r'^(?P<IP>\d+(?:\.\d+){3})\s+\S+\s+(?P<Username>[a-z]+\d+)\s+\[(?P<Date>[^][]+)]\s+"(?P<Type>[^"]*)"')
def edata():
results = []
with open("downloads/employeedata.txt", "r") as file:
for line in file:
match = rx.search(line)
if match:
results.append(match.groupdict())
return results
print(edata())
See the online Python demo. For the file = ['190.912.120.151 - skynet10001 [19/Jan/2012] "Temp"', '221.143.119.260 - terminator002 [16/Feb/2021] "Temp 2"'] input, the output will be:
[{'IP': '190.912.120.151', 'Username': 'skynet10001', 'Date': '19/Jan/2012', 'Type': 'Temp'}, {'IP': '221.143.119.260', 'Username': 'terminator002', 'Date': '16/Feb/2021', 'Type': 'Temp 2'}]
The regex is
^(?P<IP>\d+(?:\.\d+){3})\s+\S+\s+(?P<Username>[a-z]+\d+)\s+\[(?P<Date>[^][]+)]\s+"(?P<Type>[^"]*)"
See the regex demo. Details:
^ - start of string
(?P<IP>\d+(?:\.\d+){3}) - Group "IP": one or more digits and then three occurrences of a . and one or more digits
\s+\S+\s+ - one or more non-whitespace chars enclosed with one or more whitespace chars on both ends
(?P<Username>[a-z]+\d+) - Group "Username": one or more lowercase ASCII letters and then one or more digits
\s+ - one or more whitespaces
\[ - a [ char
(?P<Date>[^][]+) - Group "Date": one or more chars other than [ and ]
]\s+" - a ] char, one or more whitespaces, "
(?P<Type>[^"]*) - Group "Type": zero or more chars other than "
" - a " char.

Using regex to search for text that follows a specific word

I am searching a string of text which contains dictionaries that look like so:
soup_string = """{"loadType":"","shiftId":"ROVR-DUMMY-SHIFTID","carbonFriendly":"no","cost":"£2.00","initialSlotPrice":"","timeSlotISO":"2019-06-13T12:00+01:00/13:00+01:00","isSameDayPremium":"false","stopId":"10446315588190612134701380","availability":"full","slotDiscountedByDP":"false","slotId":"1hr-12-13-20190613","time":"12:00pm - 1:00pm","rawSlotPrice":"","slotDiscounted":"false"},
{"loadType":"","shiftId":"ROVR-DUMMY-SHIFTID","carbonFriendly":"no","cost":"£2.00","initialSlotPrice":"","timeSlotISO":"2019-06-13T12:30+01:00/13:30+01:00","isSameDayPremium":"false","stopId":"10446315588190612134701380","availability":"available","slotDiscountedByDP":"false","slotId":"1hr-12:30-13:30-20190613","time":"12:30pm - 1:30pm","rawSlotPrice":"","slotDiscounted":"false"}"""
I am looking to return the string which follows each key in the 'dictionaries'.
I have decided an appropriate method is to use Regex expressions. I can return each times and costs using
Costs = re.findall(r"\£[0-9]\.[0-9][0-9]", soup_string)
times = re.findall(r'\"(time)\"\:\"(.{14,16})\"\,', soup_string)
Essentially I would like to be able to look for each key in the dictionary, and search for a specific string then return the value.
The end goal is to create a dictionary with the 'Cost', 'Availability' and 'time'.
Full code:
import requests
from bs4 import BeautifulSoup
import json
postcode = "L4 0TH"
ASDA_url = "https://groceries.asda.com/api/user/checkpostcode?postcode="+ postcode + "&requestorigin=gi"
ASDA_url2 = "https://groceries.asda.com/api/slot/view?startdate=12%2F06%2F2019&deliveryoption=homedelivery&requestorigin=gi&_="
client = requests.Session()
r = client.get(ASDA_url)
r2 = client.get(ASDA_url2)
soup = BeautifulSoup(r2.text, 'html.parser')
soup_string = str(soup)
soup_dicts = json.loads('[' + soup_string + ']')
keep_keys = ('cost', 'availability', 'time')
filtered = [{k:soup_dict[k] for k in keep_keys} for soup_dict in soup_dicts]```
Given that you have multiple dictionaries, I'm not exactly sure what you're trying to obtain, but from my understanding this should help:
import json
soup_string = ''' ... ''' # As it is in the question
soup_dicts = json.loads('[' + soup_string + ']')
keep_keys = ('cost', 'availability', 'time')
filtered = [{k:soup_dict[k] for k in keep_keys} for soup_dict in soup_dicts]
It treats your string of dictionaries as a list of JSON dictionaries, and uses the json module to parse it. Then it filters out everything except the key/value pairs you need. The result is a list of the filtered dictionaries.
Output (i.e. value of filtered):
[
{'cost': '£2.00', 'availability': 'full', 'time': '12:00pm - 1:00pm'},
{'cost': '£2.00', 'availability': 'available', 'time': '12:30pm - 1:30pm'}
]
EDIT:
In response to you providing your code, I can see that you're calling str on the results from BeautifulSoup. Rather than doing that, you can just process the client.get() results directly:
import json
import requests
postcode = "L4 0TH"
ASDA_url = "https://groceries.asda.com/api/user/checkpostcode?postcode="+ postcode + "&requestorigin=gi"
ASDA_url2 = "https://groceries.asda.com/api/slot/view?startdate=12%2F06%2F2019&deliveryoption=homedelivery&requestorigin=gi&_="
client = requests.Session()
r = client.get(ASDA_url)
r2 = client.get(ASDA_url2)
dicts = r2.json()['slotHeader'][0]['slots']
keep_keys = ('cost', 'availability', 'time')
filtered = [{k:d[k] for k in keep_keys} for d in dicts]
First you need to put your data into a list and create a dictionary with key: data. (see my example below). Then use json to convert it as a dictionary of dictionaries. Then extract cost, availability and time per dictionary on a loop.
import json
soup_string = """{"data": [{"loadType":"","shiftId":"ROVR-DUMMY-SHIFTID","carbonFriendly":"no","cost":"£2.00","initialSlotPrice":"","timeSlotISO":"2019-06-13T12:00+01:00/13:00+01:00","isSameDayPremium":"false","stopId":"10446315588190612134701380","availability":"full","slotDiscountedByDP":"false","slotId":"1hr-12-13-20190613","time":"12:00pm - 1:00pm","rawSlotPrice":"","slotDiscounted":"false"}, {"loadType":"","shiftId":"ROVR-DUMMY-SHIFTID","carbonFriendly":"no","cost":"£2.00","initialSlotPrice":"","timeSlotISO":"2019-06-13T12:30+01:00/13:30+01:00","isSameDayPremium":"false","stopId":"10446315588190612134701380","availability":"available","slotDiscountedByDP":"false","slotId":"1hr-12:30-13:30-20190613","time":"12:30pm - 1:30pm","rawSlotPrice":"","slotDiscounted":"false"}]}"""
d = json.loads(soup_string)
result = []
cost, avail, time = [], [], []
for data in d['data']:
tmp = {}
tmp['Cost'] = data['cost']
tmp['Availability'] = data['availability']
tmp['Time'] = data['time']
result.append(tmp)
result
Output:
[{'Cost': '£2.00', 'Availability': 'full', 'Time': '12:00pm - 1:00pm'},
{'Cost': '£2.00', 'Availability': 'available', 'Time': '12:30pm - 1:30pm'}]

Turn a simple dictionary into dictionary with nested lists

Given the following data received from a web form:
for key in request.form.keys():
print key, request.form.getlist(key)
group_name [u'myGroup']
category [u'social group']
creation_date [u'03/07/2013']
notes [u'Here are some notes about the group']
members[0][name] [u'Adam']
members[0][location] [u'London']
members[0][dob] [u'01/01/1981']
members[1][name] [u'Bruce']
members[1][location] [u'Cardiff']
members[1][dob] [u'02/02/1982']
How can I turn it into a dictionary like this? It's eventually going to be used as JSON but as JSON and dictionaries are easily interchanged my goal is just to get to the following structure.
event = {
group_name : 'myGroup',
notes : 'Here are some notes about the group,
category : 'social group',
creation_date : '03/07/2013',
members : [
{
name : 'Adam',
location : 'London',
dob : '01/01/1981'
}
{
name : 'Bruce',
location : 'Cardiff',
dob : '02/02/1982'
}
]
}
Here's what I have managed so far. Using the following list comprehension I can easily make sense of the ordinary fields:
event = [ (key, request.form.getlist(key)[0]) for key in request.form.keys() if key[0:7] != "catches" ]
but I'm struggling with the members list. There can be any number of members. I think I need to separately create a list for them and add that to a dictionary with the non-iterative records. I can get the member data like this:
tmp_members = [(key, request.form.getlist(key)) for key in request.form.keys() if key[0:7]=="members"]
Then I can pull out the list index and field name:
member_arr = []
members_orig = [ (key, request.form.getlist(key)[0]) for key in request.form.keys() if key[0:7] ==
"members" ]
for i in members_orig:
p1 = i[0].index('[')
p2 = i[0].index(']')
members_index = i[0][p1+1:p2]
p1 = i[0].rfind('[')
members_field = i[0][p1+1:-1]
But how do I add this to my data structure. The following won't work because I could be trying to process members[1][name] before members[0][name].
members_arr[int(members_index)] = {members_field : i[1]}
This seems very convoluted. Is there a simper way of doing this, and if not how can I get this working?
You could store the data in a dictionary and then use the json library.
import json
json_data = json.dumps(dict)
print(json_data)
This will print a json string.
Check out the json library here
Yes, convert it to a dictionary, then use json.dumps(), with some optional parameters, to print out the JSON in the format you need:
eventdict = {
'group_name': 'myGroup',
'notes': 'Here are some notes about the group',
'category': 'social group',
'creation_date': '03/07/2013',
'members': [
{'name': 'Adam',
'location': 'London',
'dob': '01/01/1981'},
{'name': 'Bruce',
'location': 'Cardiff',
'dob': '02/02/1982'}
]
}
import json
print json.dumps(eventdict, indent=4)
The order of the key:value pairs is not always consistent, but if you're just looking for pretty-looking JSON that can be parsed by a script, while remaining human-readable, this should work. You can also sort the keys alphabetically, using:
print json.dumps(eventdict, indent=4, sort_keys=True)
The following python functions can be used to create a nested dictionary from the flat dictionary. Just pass in the html form output to decode().
def get_key_name(str):
first_pos = str.find('[')
return str[:first_pos]
def get_subkey_name(str):
'''Used with lists of dictionaries only'''
first_pos = str.rfind('[')
last_pos = str.rfind(']')
return str[first_pos:last_pos+1]
def get_key_index(str):
first_pos = str.find('[')
last_pos = str.find(']')
return str[first_pos:last_pos+1]
def decode(idic):
odic = {} # Initialise an empty dictionary
# Scan all the top level keys
for key in idic:
# Nested entries have [] in their key
if '[' in key and ']' in key:
if key.rfind('[') == key.find('[') and key.rfind(']') == key.find(']'):
print key, 'is a nested list'
key_name = get_key_name(key)
key_index = int(get_key_index(key).replace('[','',1).replace(']','',1))
# Append can't be used because we may not get the list in the correct order.
try:
odic[key_name][key_index] = idic[key][0]
except KeyError: # List doesn't yet exist
odic[key_name] = [None] * (key_index + 1)
odic[key_name][key_index] = idic[key][0]
except IndexError: # List is too short
odic[key_name] = odic[key_name] + ([None] * (key_index - len(odic[key_name]) + 1 ))
# TO DO: This could be a function
odic[key_name][key_index] = idic[key][0]
else:
key_name = get_key_name(key)
key_index = int(get_key_index(key).replace('[','',1).replace(']','',1))
subkey_name = get_subkey_name(key).replace('[','',1).replace(']','',1)
try:
odic[key_name][key_index][subkey_name] = idic[key][0]
except KeyError: # Dictionary doesn't yet exist
print "KeyError"
# The dictionaries must not be bound to the same object
odic[key_name] = [{} for _ in range(key_index+1)]
odic[key_name][key_index][subkey_name] = idic[key][0]
except IndexError: # List is too short
# The dictionaries must not be bound to the same object
odic[key_name] = odic[key_name] + [{} for _ in range(key_index - len(odic[key_name]) + 1)]
odic[key_name][key_index][subkey_name] = idic[key][0]
else:
# This can be added to the output dictionary directly
print key, 'is a simple key value pair'
odic[key] = idic[key][0]
return odic

Categories

Resources