def findLocation(self, params):
'''
Find location name from extracted text using Geograpy.
'''
file_name = params['file_name']
text_content = QueryText(file_name)
if text_content:
e = extraction.Extractor(text=text_content)
e.find_entities()
status = IndexLocationName(file_name, e.places)
if status[0]:
return {
'job': 'find_location',
'status': 'successful',
'comment': 'Location/s found and indexed to Solr.'
}
else:
return {
'job': 'find_location',
'status': 'unsuccessful',
'comment': status[1]
}
else:
return {
'job': 'find_location',
'status': 'unsuccessful',
'comment': 'Cannot extract text.'
}
def find_places(message):
extractor, flag = extraction.Extractor(text=message), True
extractor.find_entities()
available_places, place_from, place_to = extractor.places, None, None
for place in available_places:
if flag:
flag, place_from = False, place
else:
flag, place_to = True, place
return place_from, place_to
def find_geograpy_locations(self, statement):
"""
I actually extended geograpy to include more potential locations.
I think we get a few more false postivies, so we need to do some filtering.
TODO: Change the extraction script to include allow for supplying tags.
Person and Organisation tags should be flagged as possible locations.`x
:param statement:
:return:
"""
e = extraction.Extractor(text=statement)
e.find_entities()
return e.places
def process_item(self, item, spider):
try:
adapter = ItemAdapter(item)
extractor = extraction.Extractor(url=adapter['url'])
extractor.find_geoEntities()
places = list(set(extractor.places))
adapter['places_mentioned'] = places
except Exception:
raise DropItem('Failed to extract '
'places mentioned in: '
+ item['url'])
return item
def weather(self, source, location_params):
"""
Jarvis will give you current weather in given city.
If params are empty Jarvis will ask for name of city.
:param source: speech_recognition.Microphone
object of speech_recognition.Microphone, which represents a physical microphone on the computer
:param location_params: part of commend after "hot" word
:return: None
"""
base_url = "http://api.openweathermap.org/data/2.5/weather?"
def get_weather(city):
complete_url = f"{base_url}appid={self.api_key_weather}&q={city}"
response = requests.get(complete_url).json()
if response["cod"] != "404":
weather = response["main"]
current_temperature = round(pytemperature.k2c(weather["temp"]),
2)
current_temperature = f'{"minus" if current_temperature < 0 else ""}' + str(
current_temperature)
current_pressure = weather["pressure"]
current_humidity = weather["humidity"]
weather_description = response["weather"][0]["description"]
self.convert_text_to_speech(
f'Temperature (in celsius unit) = {current_temperature} '
f'atmospheric pressure (in hPa unit) = {current_pressure} '
f' humidity (in percentage) = {current_humidity} '
f'description = {weather_description}')
else:
self.convert_text_to_speech(JarvisPhrases.NO_CITY)
city_extractor = extraction.Extractor(text=" ".join(location_params))
while True:
city_extractor.find_entities()
if len(city_extractor.places) > 0:
city = city_extractor.places[0]
get_weather(city)
break
else:
self.convert_text_to_speech(JarvisPhrases.WEATHER)
audio = self.recognizer.listen(source)
location = self.recognizer.recognize_google(audio)
city_extractor.text = location
def test1():
# peacefiles_w = [join(peace_dir_w,f) for f in listdir(peace_dir_w) if isfile(join(peace_dir_w, f)) and ".docx" in f]
# for f in range(len(peacefiles_w)):
#
# logging.info("Splitting: %s"%(peacefiles_w[f]))
#
# doc = docx.Document(peacefiles_w[f])
# section = doc.sections[0]
# header = section.header
# #pdb.set_trace()
# for paragraph in header.paragraphs:
# print(paragraph.text) # or whatever you have in mind
import geograpy
import nltk
from geograpy import extraction
text = "Thyroid-associated orbitopathy (TO) is an autoimmune-\
mediated orbital inflammation that can lead to disfigurement and blindness. \
Multiple genetic loci have been associated with Graves' disease, but the genetic \
basis for TO is largely unknown. British This japanese study aimed to identify loci associated with \
TO in individuals with Graves' Mexican austrian japan Chinese disease, using a genome-wide association scan \
(GWAS) for the first time to our knowledge in TO.Genome-wide association scan was \
performed on pooled USA united states DNA from French britain an Australian Caucasian discovery cohort of 265 \
participants with Graves' disease and TO (cases) and 147 patients with Graves' \
mapisease without TO (controls)."
from geotext import GeoText
places = GeoText(text)
print(places)
e = extraction.Extractor(text=text)
nes = nltk.ne_chunk(nltk.pos_tag(text))
#print(nes)
e.find_geoEntities()
#print(e.find_geoEntities())
country = e.places
for s in range(len(country)):
country[s] = stemmer.stem(country[s])
# You can now access all of the places found by the Extractor
print(country)
#pdb.set_trace()
print(stemmer.stem("Chinese"))
def find_location(request, file_name):
'''
Find location name from extracted text using Geograpy.
'''
if "none" in IndexStatus("locations", file_name):
text_content = QueryText(file_name)
if text_content:
e = extraction.Extractor(text=text_content)
e.find_entities()
status = IndexLocationName(file_name, e.places)
if status[0]:
return HttpResponse(
status=200, content="Location/s found and index to Solr.")
else:
return HttpResponse(status=400, content=status[1])
else:
return HttpResponse(status=400, content="Cannot find location.")
else:
return HttpResponse(status=200, content="Loading...")
def extract_loc_name(t):
e = extraction.Extractor(text=t)
e.find_entities()
return e.places