-
Notifications
You must be signed in to change notification settings - Fork 0
/
datapull.py
183 lines (146 loc) · 6.94 KB
/
datapull.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
import os
import pandas as pd
import tweepy
import re
import string
from textblob import TextBlob
from nltk.corpus import stopwords
from nltk.tokenize import word_tokenize
import preprocessor as p
# from preprocessor.api import clean, tokenize, parse
consumer_key = 'zwljbXvpxzPOVptOUwgL79MkR'
consumer_secret = '9AaolFVV4LJ34Qz49OW2dlYiD3iRSjkydB4G433A0W4wPgHd6o'
access_key= '2420697092-1oDbLVZ0syvpOYvMyPiBQXSgmC8A5yPZVKITKAi'
access_secret = 'gRRSTcuJzqW4IvI3nLIkKSKMUXOQuGdLcsuN4NUETeupJ'
auth = tweepy.OAuthHandler(consumer_key, consumer_secret)
auth.set_access_token(access_key, access_secret)
api = tweepy.API(auth)
result_tweets=r"C:\Users\harsh\Documents\MDMProject\get_result.csv"
#columns of the csv file
COLS = ['id', 'created_at', 'source', 'original_text','clean_text', 'sentiment','polarity','subjectivity', 'lang',
'favorite_count', 'retweet_count', 'original_author', 'possibly_sensitive', 'hashtags',
'user_mentions', 'place', 'place_coord_boundaries']
#set two date variables for date range
start_date = '2020-04-14'
end_date = '2020-04-15'
# Happy Emoticons
emoticons_happy = set([
':-)', ':)', ';)', ':o)', ':]', ':3', ':c)', ':>', '=]', '8)', '=)', ':}',
':^)', ':-D', ':D', '8-D', '8D', 'x-D', 'xD', 'X-D', 'XD', '=-D', '=D',
'=-3', '=3', ':-))', ":'-)", ":')", ':*', ':^*', '>:P', ':-P', ':P', 'X-P',
'x-p', 'xp', 'XP', ':-p', ':p', '=p', ':-b', ':b', '>:)', '>;)', '>:-)',
'<3'
])
# Sad Emoticons
emoticons_sad = set([
':L', ':-/', '>:/', ':S', '>:[', ':@', ':-(', ':[', ':-||', '=L', ':<',
':-[', ':-<', '=\\', '=/', '>:(', ':(', '>.<', ":'-(", ":'(", ':\\', ':-c',
':c', ':{', '>:\\', ';('
])
#Emoji patterns
emoji_pattern = re.compile("["
u"\U0001F600-\U0001F64F" # emoticons
u"\U0001F300-\U0001F5FF" # symbols & pictographs
u"\U0001F680-\U0001F6FF" # transport & map symbols
u"\U0001F1E0-\U0001F1FF" # flags (iOS)
u"\U00002702-\U000027B0"
u"\U000024C2-\U0001F251"
"]+", flags=re.UNICODE)
#combine sad and happy emoticons
emoticons = emoticons_happy.union(emoticons_sad)
#mrhod clean_tweets()
def clean_tweets(tweet):
stop_words = set(stopwords.words('english'))
word_tokens = word_tokenize(tweet)
#after tweepy preprocessing the colon left remain after removing mentions
#or RT sign in the beginning of the tweet
tweet = re.sub(r':', '', tweet)
tweet = re.sub(r'…', '', tweet)
#replace consecutive non-ASCII characters with a space
tweet = re.sub(r'[^\x00-\x7F]+',' ', tweet)
#remove emojis from tweet
tweet = emoji_pattern.sub(r'', tweet)
#filter using NLTK library append it to a string
filtered_tweet = [w for w in word_tokens if not w in stop_words]
filtered_tweet = []
#looping through conditions
for w in word_tokens:
#check tokens against stop words , emoticons and punctuations
if w not in stop_words and w not in emoticons and w not in string.punctuation:
filtered_tweet.append(w)
return ' '.join(filtered_tweet)
#print(word_tokens)
#print(filtered_sentence)
#method write_tweets()
def write_tweets(keyword, file):
# If the file exists, then read the existing data from the CSV file.
if os.path.exists(file):
df = pd.read_csv(file, header=0)
else:
df = pd.DataFrame(columns=COLS)
#page attribute in tweepy.cursor and iteration
for page in tweepy.Cursor(api.search, q=keyword,
count=200, include_rts=False, since=start_date).pages(50):
for status in page:
new_entry = []
status = status._json
## check whether the tweet is in english or skip to the next tweet
if status['lang'] != 'en':
continue
#when run the code, below code replaces the retweet amount and
#no of favorires that are changed since last download.
if status['created_at'] in df['created_at'].values:
i = df.loc[df['created_at'] == status['created_at']].index[0]
if status['favorite_count'] != df.at[i, 'favorite_count'] or \
status['retweet_count'] != df.at[i, 'retweet_count']:
df.at[i, 'favorite_count'] = status['favorite_count']
df.at[i, 'retweet_count'] = status['retweet_count']
continue
#tweepy preprocessing called for basic preprocessing
#clean_text = p.clean(status['text'])
#call clean_tweet method for extra preprocessing
filtered_tweet=clean_tweets(status['text'])
#pass textBlob method for sentiment calculations
blob = TextBlob(filtered_tweet)
Sentiment = blob.sentiment
#seperate polarity and subjectivity in to two variables
polarity = Sentiment.polarity
subjectivity = Sentiment.subjectivity
#new entry append
new_entry += [status['id'], status['created_at'],
status['source'], status['text'],filtered_tweet, Sentiment,polarity,subjectivity, status['lang'],
status['favorite_count'], status['retweet_count']]
#to append original author of the tweet
new_entry.append(status['user']['screen_name'])
try:
is_sensitive = status['possibly_sensitive']
except KeyError:
is_sensitive = None
new_entry.append(is_sensitive)
# hashtagas and mentiones are saved using comma separted
hashtags = ", ".join([hashtag_item['text'] for hashtag_item in status['entities']['hashtags']])
new_entry.append(hashtags)
mentions = ", ".join([mention['screen_name'] for mention in status['entities']['user_mentions']])
new_entry.append(mentions)
#get location of the tweet if possible
try:
location = status['user']['location']
except TypeError:
location = ''
new_entry.append(location)
try:
coordinates = [coord for loc in status['place']['bounding_box']['coordinates'] for coord in loc]
except TypeError:
coordinates = None
new_entry.append(coordinates)
single_tweet_df = pd.DataFrame([new_entry], columns=COLS)
df = df.append(single_tweet_df, ignore_index=True)
csvFile = open(file, 'a' ,encoding='utf-8')
df.to_csv(csvFile, mode='a', columns=COLS, index=False, encoding="utf-8")
#declare keywords as a query for three categories
movie_keywords="#Endgame"
# with open(r"C:\Users\harsh\Documents\MDMProject\hamhongekamiyab.txt","r",encoding='utf=8') as f:
# line=f.readline()
# movie_keywords=line
#call main method passing keywords and file path
write_tweets(movie_keywords, result_tweets)