def testExtractorFromUrl(self):
'''
test the extractor
'''
url = 'https://en.wikipedia.org/wiki/Louvre'
e = Extractor(url=url)
e.find_geoEntities()
self.check(e.places, ['Paris', 'France'])
def testStackOverflow54721435(self):
'''
see https://stackoverflow.com/questions/54721435/unable-to-extract-city-names-from-a-text-using-geograpypython
'''
text = 'I live in Kadawatha a suburb of Colombo Sri Lanka'
e = Extractor(text=text)
e.find_entities()
print(e.places)
def testStackoverflow54077973(self):
'''
see https://stackoverflow.com/questions/54077973/geograpy3-library-for-extracting-the-locations-in-the-text-gives-unicodedecodee
'''
address = 'Jersey City New Jersey 07306'
e = Extractor(text=address)
e.find_entities()
self.check(e.places, ['Jersey', 'City'])
def testExtractorFromUrl(self):
'''
test the extractor
'''
url = 'http://www.bbc.com/news/world-europe-26919928'
e = Extractor(url=url)
e.find_geoEntities()
self.check(e.places, ['Russia', 'Kiev', 'Ukraine'])
def testStackoverflow43322567(self):
'''
see https://stackoverflow.com/questions/43322567
'''
url = 'https://en.wikipedia.org/wiki/U.S._state'
e = Extractor(url=url)
places = e.find_geoEntities()
self.check(places, ['Alabama', 'Virginia', 'New York'])
print(places)
def testStackoverflow54712198(self):
'''
see https://stackoverflow.com/questions/54712198/not-only-extracting-places-from-a-text-but-also-other-names-in-geograpypython
'''
text = '''Opposition Leader Mahinda Rajapaksa says that the whole public administration has collapsed due to the constitution council’s arbitrary actions. The Opposition Leader said so in response to a query a journalised raised after a meeting held...'''
e = Extractor(text)
places = e.find_geoEntities()
if self.debug:
print(places)
self.assertEqual([], places)
def get_place_context(url=None, text=None):
e = Extractor(url=url, text=text)
e.find_entities()
pc = PlaceContext(e.places)
pc.set_countries()
pc.set_regions()
pc.set_cities()
pc.set_other()
return pc
def locateCity(location, correctMisspelling=False, debug=False):
'''
locate the given location string
Args:
location(string): the description of the location
Returns:
Locator: the location
'''
e = Extractor(text=location, debug=debug)
e.split()
loc = Locator.getInstance(correctMisspelling=correctMisspelling,
debug=debug)
city = loc.locateCity(e.places)
return city
def testStackoverflow55548116(self):
'''
see https://stackoverflow.com/questions/55548116/geograpy3-library-is-not-working-properly-and-give-traceback-error
'''
feedContent = ['Las Vegas is a city in Nevada']
placesInFeed = []
for content in feedContent:
if content != "":
e = Extractor(text=content)
e.find_entities()
places = e.places
if self.debug:
print(places)
placesInFeed.append(places)
def get_place_context(url=None, text=None):
e = Extractor(url=url, text=text)
e.find_entities()
pc = PlaceContext(e.places, e.people, e.organs)
pc.set_countries()
pc.set_regions()
pc.set_cities()
pc.set_other()
return pc
# url = 'http://www.bbc.com/news/world-us-canada-39821789'
# places = get_place_context(url=url)
# len(places)
def get_place_context(url=None, text=None, labels=Labels.default, debug=False):
'''
Get a place context for a given text with information
about country, region, city and other
based on NLTK Named Entities in the label set Geographic(GPE),
Person(PERSON) and Organization(ORGANIZATION).
Args:
url(String): the url to read text from (if any)
text(String): the text to analyze
debug(boolean): if True show debug information
Returns:
pc:
PlaceContext: the place context
'''
e = Extractor(url=url, text=text, debug=debug)
e.find_entities(labels=labels)
pc = PlaceContext(e.places)
pc.setAll()
return pc
def test():
e = Extractor(url='http://www.bbc.com/news/world-europe-26919928')
e.find_entities()
assert len(e.places) > 0
assert 'Russia' in e.places
assert 'Kiev' in e.places
text = """ Perfect just Perfect! It's a perfect storm for Nairobi on a
Friday evening! horrible traffic here is your cue to become worse @Ma3Route """
e2 = Extractor(text=text)
e2.find_entities()
assert len(e2.places) > 0
assert 'Nairobi' in e2.places
text3 = """ Risks of Cycling in Nairobi:http://www.globalsiteplans.com/environmental-design/engineering-environmental-design/the-risky-affair-of-cycling-in-nairobi-kenya/ ... via @ConstantCap @KideroEvans @county_nairobi @NrbCity_Traffic """
e3 = Extractor(text=text3)
e3.find_entities()
assert len(e3.places) > 0
assert 'Nairobi' in e3.places
text4 = """ @DurbanSharks [Africa Renewal]It is early morning in Nairobi, the Kenyan capital. The traffic jam along Ngong """
e4 = Extractor(text=text4)
e4.find_entities()
assert len(e4.places) > 0
assert 'Nairobi' in e4.places
assert 'Ngong' in e4.places
def test():
e = Extractor(url='http://www.bbc.com/news/world-europe-26919928')
e.find_entities()
assert len(e.places) > 0
assert 'Russia' in e.places
assert 'Kiev' in e.places
text = """ Perfect just Perfect! It's a perfect storm for Nairobi on a
Friday evening! horrible traffic here is your cue to become worse @Ma3Route """
e2 = Extractor(text=text)
e2.find_entities()
assert len(e2.places) > 0
assert 'Nairobi' in e2.places
text3 = """ Risks of Cycling in Nairobi:http://www.globalsiteplans.com/environmental-design/engineering-environmental-design/the-risky-affair-of-cycling-in-nairobi-kenya/ ... via @ConstantCap @KideroEvans @county_nairobi @NrbCity_Traffic """
e3 = Extractor(text=text3)
e3.find_entities()
assert len(e3.places) > 0
assert 'Nairobi' in e3.places
text4 = """ @DurbanSharks [Africa Renewal]It is early morning in Nairobi, the Kenyan capital. The traffic jam along Ngong """
e4 = Extractor(text=text4)
e4.find_entities()
assert len(e4.places) > 0
assert 'Nairobi' in e4.places
assert 'Ngong' in e4.places
# unicode
text5 = u""" There is a city called New York in the United States."""
e5 = Extractor(text=text5)
e5.find_entities()
print e5.places
assert len(e5.places) == 2
assert u'New York' in e5.places
assert u'United States' in e5.places
# unicode and two words
text6 = u""" There is a city called São Paulo in Brazil."""
e6 = Extractor(text=text6)
e6.find_entities()
print e6.places
assert len(e6.places) > 1
assert u'São Paulo' in e6.places
def collect_news():
print('Running collecting news')
retrive_news_from_firebase()
# check_news_dataset()
set_entityCount()
url = [
"http://www.adaderana.lk/rss.php",
"http://www.hirunews.lk/rss/english.xml",
"https://www.news.lk/news?format=feed",
"https://srilankamirror.com/news?format=feed&type=rss",
"http://www.thesundayleader.lk/feed/", "https://www.newsfirst.lk/feed/"
]
for url in url:
# print(url)
# read the rss feeds from urls
feedParsed = feedparser.parse(url)
# print(feedParsed)
# check whether the rss reading success or not
if feedParsed.feed != {}:
global news_in_db
global entityCount
for post in feedParsed.entries:
if is_news_already_exist_in_db(post.title) != True:
category = classify_news(post.title)
newsObj = News(post.title, post.description, post.summary,
post.link, category, post.published,
entityCount)
newsObjects.append(newsObj)
locations = Extractor(
text=post.description) # Extract location
locations.find_entities()
# print(locations.places) # locations is an array
newsObj.add_locations(locations.places)
# data = {
# "title": newsObj.title,
# "id":entityCount,
# "description": newsObj.description,
# "summary": newsObj.summery,
# "link": newsObj.link,
# "category": newsObj.category,
# "locations": newsObj.locations,
# "date_time": newsObj.date_time
# }
# firebase.database().set(data)
global db
doc_ref = db.collection(u'news').document()
doc_ref.set({
u'title': newsObj.title,
u'news_id': newsObj.news_id,
u'description': newsObj.description,
u'summary': newsObj.summary,
u'link': newsObj.link,
u'category': newsObj.category,
u'locations': newsObj.locations,
u'date_time': newsObj.date_time
})
update_news_dataset(newsObj)
# db.collection(u'newsAppData').document(u'news').set(newsObj)
print("feed " + str(newsObj.news_id) + " : " +
str(newsObj.title))
print('category: ', category, '. time ', newsObj.date_time,
' . locations:', newsObj.locations)
entityCount = entityCount + 1
else:
print('Connection failed with url :', url)
WAIT_SECONDS = 100 # timer for thread
print(time.ctime())
news_in_db.clear()
threading.Timer(WAIT_SECONDS, collect_news).start()
def testExtractorFromText(self):
'''
test different texts for getting geo context information
'''
text = """ Perfect just Perfect! It's a perfect storm for Nairobi on a
Friday evening! horrible traffic here is your cue to become worse @Ma3Route """
e2 = Extractor(text=text)
e2.find_entities()
self.check(e2.places, ['Nairobi'])
text3 = """ Risks of Cycling in Nairobi:http://www.globalsiteplans.com/environmental-design/engineering-environmental-design/the-risky-affair-of-cycling-in-nairobi-kenya/ ... via @ConstantCap @KideroEvans @county_nairobi @NrbCity_Traffic """
e3 = Extractor(text=text3)
e3.find_entities()
self.check(e3.places, ['Nairobi'])
text4 = """ @DurbanSharks [Africa Renewal]It is early morning in Nairobi, the Kenyan capital. The traffic jam along Ngong """
e4 = Extractor(text=text4)
e4.find_entities()
self.check(e4.places, ['Nairobi', 'Ngong'])
# unicode
text5 = u""" There is a city called New York in the United States."""
e5 = Extractor(text=text5)
e5.find_entities()
self.check(e5.places, ['New York', 'United States'])
# unicode and two words
text6 = u""" There is a city called São Paulo in Brazil."""
e6 = Extractor(text=text6)
e6.find_entities()
self.check(e6.places, ['São Paulo'])
def test():
e = Extractor(url='http://www.bbc.com/news/world-europe-26919928')
e.find_entities()
assert len(e.places) > 0
assert 'Russia' in e.places
assert 'Kiev' in e.places
text = """ Perfect just Perfect! It's a perfect storm for Nairobi on a
Friday evening! horrible traffic here is your cue to become worse @Ma3Route """
e2 = Extractor(text=text)
e2.find_entities()
assert len(e2.places) > 0
assert 'Nairobi' in e2.places
text3 = """ Risks of Cycling in Nairobi:http://www.globalsiteplans.com/environmental-design/engineering-environmental-design/the-risky-affair-of-cycling-in-nairobi-kenya/ ... via @ConstantCap @KideroEvans @county_nairobi @NrbCity_Traffic """
e3 = Extractor(text=text3)
e3.find_entities()
assert len(e3.places) > 0
assert 'Nairobi' in e3.places
text4 = """ @DurbanSharks [Africa Renewal]It is early morning in Nairobi, the Kenyan capital. The traffic jam along Ngong """
e4 = Extractor(text=text4)
e4.find_entities()
assert len(e4.places) > 0
assert 'Nairobi' in e4.places
assert 'Ngong' in e4.places
