def test_sightings(self):
if python_version == 3:
key = input("Testing Sightings: What's your API Key?\n")
elif python_version == 2:
key = raw_input("What's your API Key?\n")
hatebase = HatebaseAPI({"key": key, "debug": False})
filters = {
'is_about_nationality': '1',
'language': 'eng',
'country_id': 'US'
}
output = "json"
# get sightings
response = hatebase.getSightings(filters=filters, format=output)
# get some details from response
results = response["number_of_results"]
pages = response["number_of_pages"]
if hatebase.debug == True:
print(response)
self.assertEqual(response["token"], hatebase.token)
self.assertTrue(int(pages) > 500)
self.assertTrue(int(results) > 54239)
def test_vocabulary_details(self):
if python_version == 3:
key = input("Testing Vocabulary Details: What's your API Key?\n")
elif python_version == 2:
key = raw_input(
"Testing Vocabulary Details: What's your API Key?\n")
hatebase = HatebaseAPI({"key": key, "debug": False})
format = "json"
vocab_filter = {"language": "eng"}
# get vocabulary and its first result
response = hatebase.getVocabulary(filters=vocab_filter, format=format)
vocab = response["result"]
# get vocabulary_id of first vocab entry
vocab_id = vocab[0]["vocabulary_id"]
details_filters = {'vocabulary_id': vocab_id}
# get vocab details
response = hatebase.getVocabularyDetails(filters=details_filters,
format=format)
resp_vocab_id = response["result"]["vocabulary_id"]
if hatebase.debug == True:
print(response)
self.assertEqual(response["token"], hatebase.token)
self.assertEqual(vocab_id, resp_vocab_id)
def main():
hatebase = HatebaseAPI({"key": '4UyMTCENrNkmsYgPZiRneBVbVJYHDY7F'})
filters = {"language": "eng"}
format = "json"
# initialize list for all vocabulary entry dictionaries
eng_vocab = []
response = hatebase.getVocabulary(filters=filters, format=format)
pages = response["number_of_pages"]
# fill the vocabulary list with all entries of all pages
# this might take some time...
for page in range(1, pages+1):
filters["page"] = str(page)
response = hatebase.getVocabulary(filters=filters, format=format)
eng_vocab.append(response["result"])
# create empty pandas df for all vocabulary entries
df_eng_vocab = pd.DataFrame()
# fill df
for elem in eng_vocab:
df_eng_vocab = df_eng_vocab.append(elem)
# reset the df index
df_eng_vocab.reset_index(drop=True, inplace=True)
df_eng_vocab.to_csv('hatebase_eng.csv')
def test_vocabulary(self):
if python_version == 3:
key = input("Testing Vocabulary: What's your API Key?\n")
elif python_version == 2:
key = raw_input("Testing Vocabulary: What's your API Key?\n")
hatebase = HatebaseAPI({"key": key, "debug": False})
filters = {"language": "deu"}
format = "json"
# get vocabulary
response = hatebase.getVocabulary(filters=filters, format=format)
# get some details from response
vocablist = response["result"]
results = response["number_of_results"]
pages = response["number_of_pages"]
lang = response["language"]
if hatebase.debug == True:
print("len(vocab): {}, # of pages: {}, # of results: {}, lang: {}".
format(len(vocablist), pages, results, lang))
self.assertEqual(response["token"], hatebase.token)
self.assertTrue(int(results) >= 18)
self.assertEqual(int(response['number_of_results']), int(results))
#Check hate word frequency in a list of messages.
#Uses NTLK and Hatebase libraries
#Graphs top ten occurences of hate words!
#ONLY DO ONCE
#DO NOT WASTE API CALLS
key = "ENTER_YOU_KEY_HERE"
from json import loads
from hatebase import HatebaseAPI
hatebase = HatebaseAPI({"key": key})
#"language": "eng"
pagenumber = 1
responses = []
#Loads top 1000 results
while pagenumber <= 11:
filters = {"country": "US", "page": str(pagenumber)}
output = "json"
query_type = "vocabulary"
response = hatebase.performRequest(filters, output, query_type)
# convert to Python object
responses.append(loads(response))
pagenumber += 1
print "Done getting API results"
#Process Hate Words
data = []
import json
import requests
from hatebase import HatebaseAPI
key = "TuwmngrrxcytZkgqyfvtpdUb4yjsKsru"
hatebase = HatebaseAPI({"key": key})
filters = {
'is_about_nationality': "false",
'is_about_ethnicity': "false",
'is_about_religion': "false",
'is_about_gender': "false",
'is_about_sexual_orientation': "false",
'is_about_disability': "false",
'is_about_class': "true",
'language': 'ENG',
'country': 'US',
'year': "2015"
}
format = "json"
json_response = hatebase.getSightings(filters=filters, format=format)
with open('classOnly2015.txt', 'w+') as outfile:
outfile.write(json.dumps(json_response, indent=4))
from json import loads
import json
from hatebase import HatebaseAPI
hatebase = HatebaseAPI({"key": '1cfe0ef015998aea71f2ad32bf9f601f'})
filters = {'language': 'eng', 'type': 't'}
output = "json"
query_type = "vocabulary"
response = hatebase.performRequest(filters, output, query_type)
# convert to Python object
response = loads(response)
with open('hatefile', 'w') as w:
w.write(json.dumps(response["data"]))
import json
from hatebase import HatebaseAPI
key = input('Please enter your api key for https://hatebase.org/: ')
hatebase = HatebaseAPI({"key": key})
filters = {"language": "eng"}
format = "json"
# initialize list for all vocabulary entry dictionaries
en_vocab = {}
response = hatebase.getVocabulary(filters=filters, format=format)
pages = response["number_of_pages"]
# fill the vocabulary list with all entries of all pages
# this might take some time...
for page in range(1, pages + 1):
filters["page"] = str(page)
response = hatebase.getVocabulary(filters=filters, format=format)
result = response["result"]
en_vocab[result['term']] = result
with open('en_vocab.json', 'w', encoding='utf-8') as json_file:
json.dump(en_vocab, json_file)
''' This is the code for using the Hatebase API
It uses this Python wrapper: https://github.com/DanielJDufour/hatebase
which can be installed with: pip install hatebase
'''
from json import loads
from hatebase import HatebaseAPI
key = # get a key here: https://www.hatebase.org/request_api
# Define parameters
hatebase = HatebaseAPI({"key": key})
filters = {'language': 'eng'}
output = 'json'
query_type = 'sightings'
# Query the database
response = hatebase.performRequest(filters, output, query_type)
# Convert to Python object
resp = loads(response)