def get_forecast_from_api():
"""
Using api.met.no to get the weather forecast
:return data: data dictionary with relevant data from the api
"""
# Define endpoint and parameters
# (lat and lon are for the weather station at Bygdøy used for weather forecast at Fornebu)
endpoint = "https://api.met.no/weatherapi/locationforecast/1.9/"
parameters = {"lat": 59.90, "lon": 10.69, "msl": 15}
try:
# Issue an HTTP GET request
r = requests.get(endpoint, parameters)
except requests.exceptions.RequestException as e:
print("Not possible to get the weather forecast from api.met.no")
print(e)
sys.exit()
# Handling the XML response
bf = BadgerFish()
json_string = json.dumps(bf.data(et.fromstring(
r.content))) # creating json string
json_dict = json.loads(json_string) # creating json dict
data = json_dict["weatherdata"]["product"][
"time"] # collecting the relevant part of the response
return data
def get_reports():
bf = BadgerFish(dict_type=dict)
reports = []
for file in listdir(path_r):
file = path_r + '/' + file
with open(file, "r") as xml:
reports.append(bf.data(fromstring(xml.read())))
return reports
def convertXmlToDict(xmlContent): import xml.etree.ElementTree as ET from xmljson import BadgerFish from collections import OrderedDict # parse XML DOM into dictionary bf = BadgerFish(dict_type=OrderedDict, xml_fromstring=False) # dump into dict string, then load back to dict return json.loads(json.dumps(bf.data(ET.fromstring(xmlContent))))
def xmlToJson(data):
"""
The Badgerfish notation is used to convert xml into dictionary or json
This notation uses "$" for xml text content and @ to prefix xml attributes
"""
dataText = data.text
# deleting namespace from xml because of long string repetition
dataWithoutNameSpace = re.sub(' xmlns="[^"]+"', '', dataText, count=1)
bf = BadgerFish(dict_type=dict)
dataDict = bf.data(fromstring(dataWithoutNameSpace))
return dataDict
def hpfeedsend(self, eformat):
""" workaround if hpfeeds broker is offline as otherwise hpfeeds lib will loop connection attempt """
sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
sock.settimeout(2)
result = sock.connect_ex((self.ECFG["host"], int(self.ECFG["port"])))
sock.close()
if result != 0:
""" broker unavailable """
self.logger.warning(
f"HPFEEDS broker is configured to {self.ECFG['host']}:{self.ECFG['port']} but is currently unavailable. Disabling hpfeeds submission for this round!",
'2')
return (False)
try:
hpc = ''
if self.ECFG["tlscert"].lower() != "none":
hpc = hpfeeds.new(self.ECFG["host"],
int(self.ECFG["port"]),
self.ECFG["ident"],
self.ECFG["secret"],
certfile=self.ECFG["tlscert"],
reconnect=False)
print(
f' -> Connecting to {hpc.brokername}/{self.ECFG["host"]}:{self.ECFG["port"]} via TLS'
)
else:
hpc = hpfeeds.new(self.ECFG["host"],
int(self.ECFG["port"]),
self.ECFG["ident"],
self.ECFG["secret"],
reconnect=False)
print(
f' -> Connecting to {hpc.brokername}/{self.ECFG["host"]}:{self.ECFG["port"]} via none TLS'
)
""" remove auth header """
etree.strip_elements(self.esm, "Authentication")
for i in range(0, len(self.esm)):
if eformat == "xml":
hpc.publish(
self.ECFG["channels"],
etree.tostring(self.esm[i], pretty_print=False))
if eformat == "json":
bf = BadgerFish(dict_type=OrderedDict)
hpc.publish(self.ECFG["channels"],
json.dumps(bf.data(self.esm[i])))
return (True)
except hpfeeds.FeedException as e:
self.logger.error(f"HPFeeds Error ({e})", '2')
return (False)
def xml2json(element, conv='parker'):
"""Takes an XML record and returns the json representation of it."""
if conv == 'bf':
convention = BadgerFish(xml_fromstring=str)
elif conv == 'parker':
convention = Parker(xml_fromstring=str)
else:
logging.critical('Invalid XML2JSON Convention: ' + conv)
raise ValueError('The parameter @conv should be "bf" or "parker" not ' + conv)
data = convention.data(element)
return json.dumps(data, indent=' ', ensure_ascii=False)
def listen_enter(opts, vars):
vars['bf'] = BadgerFish(
dict_type=
OrderedDict, # pick dict class to preserve order of attributes and children
xml_fromstring=opts['convert']) # convert strings if possible
pass
def get_building_info(self, prop_id):
"""
Get the building info based on a property
Args:
prop_id : the property ID
Returns:
Dictionary : BadgerFish output of XML
"""
resource = '{0}/building/{1}'.format(self.domain, prop_id)
self.logger.debug("Pulling data from {0}".format(resource))
response = self.session.get(resource)
if response.status_code != requests.codes.ok:
return response.raise_for_status()
root = Et.fromstring(response.text)
bf = BadgerFish(dict_type=dict)
building_info = bf.data(root)
return building_info
def get_account_info(self):
"""
Get Account information for the current user
Returns:
Dictionary : BadgerFish style representation of Energy Star response
e.g.:
account_info = client.get_account_info()
account_id = account_info["account"]["id"]["$"]
Notes:
BadgerFish : http://www.sklar.com/badgerfish/
"""
resource = self.domain + "/account"
self.logger.debug("Pulling data from {0}".format(resource))
response = self.session.get(resource)
if response.status_code != requests.codes.ok:
return response.raise_for_status()
data = response.text
root = Et.fromstring(data)
bf = BadgerFish(dict_type=dict)
account_info = bf.data(root)
return account_info
def xmlToJson(data):
bf = BadgerFish(dict_type=OrderedDict)
xml = lxml.html.fromstring(data)
data = bf.data(xml)
return data
return new_sent
def is_ascii(s):
return all(ord(c) < 128 for c in s)
wordDict = {}
revWordDict = {}
lemmaDict = {}
revLemmaDict = {}
if __name__ == '__main__':
bf = BadgerFish(dict_type=OrderedDict)
trainFile = open("WikiQA-train.tsv")
trainFiles = [trainFile]
testFile = open("WikiQA-test.tsv")
testFiles = [testFile]
validFile = open("WikiQA-dev.tsv")
validFiles = [validFile]
fileList = [trainFiles,testFiles,validFiles]
debugFile = open("debug","w")
from pytorch_pretrained_bert import BertTokenizer, BertForNextSentencePrediction, BertConfig
import requests
import pandas as pd
import regex as re
from sklearn.model_selection import train_test_split
import time
from fastprogress import progress_bar
from xmljson import BadgerFish
from xml.etree.ElementTree import fromstring
# Use the HTTP GET method of requests library to get the xml dataset and decode it to string format
r = requests.get('https://rss.nytimes.com/services/xml/rss/nyt/Technology.xml'
).content.decode()
# Initialize the badgerfish class of xmljson package to convert xml data to dictionary format
bf = BadgerFish(dict_type=dict)
# Convert the xml data to python dictionary format
xml_dict = dict(bf.data(fromstring(r)))
title_list = []
# Get the title data from the rss feed and append to a list
for title in xml_dict['rss']['channel']['item']:
title_list.append(title['title']['$'])
print(title_list[:10])
print(len(title_list))
desc_list = []
# Get the descriptio data corresponding to the title and append to another list
for desc in xml_dict['rss']['channel']['item']:
desc_list.append(desc['description']['$'])
def _get_collection_data(filename):
path = Path(filename)
assert path.is_file()
bf = BadgerFish(dict_type=OrderedDict)
return path, bf.data(fromstring(open(path, 'rb').read()))
logging.info("New KMZ files are added",extra={"verbosity":1})
ll=len(added)
for zk in range(ll):
print ("Added: ", ", ".join (added))
dir=config.get("Section1","path1")
fname=os.path.join(dir,added[zk])
logging.info("KMZ file is passed as argument to kmz_to_kml function",extra={"verbosity":1})
kmlfile=kmz_to_kml(fname)
dom = md.parse(kmlfile)
root = dom.documentElement
logging.info("Obtained kml file is generically parsed",extra={"verbosity":1})
print_node(root)
tree = ET.parse(kmlfile)
root1 = tree.getroot()
xmlstr = ET.tostring(root1, encoding='utf8', method='xml')
bf = BadgerFish(dict_type=OrderedDict)
bf_str = BadgerFish(xml_fromstring=False)
t_n = os.path.splitext(config.get("Section2","path1"))[0] + os.path.splitext(basename(fname))[0] + ".geojson"
f_file = open(t_n, 'w')
logging.info("kml file is converted to geojson format1",extra={"verbosity":1})
f_file.write(dumps(bf_str.data(fromstring(xmlstr))))
f_file.close()
o = xmltodict.parse(xmlstr)
t_s = os.path.splitext(config.get("Section2","path2"))[0] + os.path.splitext(basename(fname))[0] + ".geojson"
g_file = open(t_s, 'w')
rr = json.dumps(o)
logging.info("kml file is converted to geojson format2",extra={"verbosity":1})
g_file.write(json.dumps(o, sort_keys=False, indent=4, separators=(',', ': ')))
g_file.close()
t_k = os.path.splitext(config.get("Section2","path3"))[0] + os.path.splitext(basename(fname))[0] + ".geojson"
h_file = open(t_k, 'w')
def xml2json(xmlfile):
bf = BadgerFish(dict_type=OrderedDict)
return bf.data(lxml.etree.fromstring(open(xmlfile).read()))
logging.info("output file is : %s", outfile)
if not os.path.exists(dir_data):
os.makedirs(dir_data)
if limit != 0:
logging.info("input file limit activated %s definitions", str(limit))
# check input file presency
if not os.path.exists(infile):
logging.error("input file %s not found", infile)
sys.exit(8)
bf = BadgerFish(dict_type=OrderedDict, xml_fromstring=False)
# read xml structure
with open(infile) as fd:
text = fd.read()
xml_json = bf.data(ET.fromstring(text))
# test purpose : print json structure
# json_print(xml_json, 0)
attr = {}
attr.update(
{"Topology_Container": ["@name", "@model_type", "@model_handle"]})
attr.update({
"Device":
["@name", "@network_address", "@model_type", "@model_handle"]
#!/usr/bin/env python2
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
from optparse import OptionParser
import os
import sys
import codecs
import lxml
from lxml.etree import tostring, Element
from lxml import etree
import re
from xmljson import BadgerFish
from collections import OrderedDict, defaultdict, Counter
bf = BadgerFish(dict_type=dict)
"""
Module for converting the ABSA XML data into a tokenized vertical format
"""
sys.stdout = codecs.getwriter('utf-8')(sys.__stdout__)
sys.stderr = codecs.getwriter('utf-8')(sys.__stderr__)
sys.stdin = codecs.getreader('utf-8')(sys.__stdin__)
# Tokenizer pattern
pattern = r'''(?x)(?u) # set flag (?x) to allow verbose regexps
def xml_to_dict(path_xml):
with open(path_xml, 'r', encoding='utf-8') as r:
ss = r.read()
print(ss)
return BadgerFish(dict_type=dict).data(fromstring(ss))
