def test_request_once(self):
with patch("google_play_scraper.features.reviews.reviews",
wraps=reviews) as mock_reviews:
result = reviews_all("co.kr.uaram.userdeliver_")
self.assertEqual(1, mock_reviews.call_count)
result_of_reviews, _ = reviews("co.kr.uaram.userdeliver_", count=10000)
self.assertTrue(0 < len(result) < 10)
self.assertEqual(len(result), len(result_of_reviews))
def test_request_multiple_times(self):
with patch(
"google_play_scraper.features.reviews.reviews", wraps=reviews
) as mock_reviews:
result = reviews_all("co.kr.uaram.userdeliver_", lang="ko", country="kr")
self.assertEqual(2, mock_reviews.call_count)
result_of_reviews, _ = reviews(
"co.kr.uaram.userdeliver_", lang="ko", country="kr", count=10000
)
self.assertTrue(300 < len(result) < 500)
self.assertEqual(len(result), len(result_of_reviews))
def test_no_reviews(self):
result = reviews_all("product.dp.io.ab180blog",
lang="sw",
country="it")
self.assertListEqual([], result)
def test_no_reviews(self):
result = reviews_all("com.spotify.music", lang="sw", country="it")
self.assertListEqual([], result)
#-----------------------------------------------------------------------------------------------
get_ipython().system('pip install google_play_scraper')
get_ipython().system('pip install sklearn')
import pandas as pd
from google_play_scraper.features.reviews import Sort, reviews_all, reviews
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.decomposition import LatentDirichletAllocation
#-----------------------------------------------------------------------------------------------
# Reviews data extraction
#-----------------------------------------------------------------------------------------------
result = reviews_all('com.bt.bms',
sleep_milliseconds=0,
lang='en',
country='us')
#-----------------------------------------------------------------------------------------------
# Create dataframe of the reviews
#-----------------------------------------------------------------------------------------------
df = pd.DataFrame(result)
print(f'Total textual reviews: {len(result)} \n')
unique_users = len(df['userName'].unique())
unknown_users = len(df[df['userName'] == 'A Google user'])
total_reviews = len(df)
print(f'Total unique users : {unique_users}')