-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathget_2016_tweets.py
308 lines (260 loc) · 14.1 KB
/
get_2016_tweets.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
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
# -*- coding: utf-8 -*-
"""
Created on Fri Sep 25 08:32:25 2020
@author: rapha
"""
import tweepy
import pandas as pd
import numpy as np
import os.path
import time
## Auth tweepy
auth = tweepy.OAuthHandler("Jk4mzY6QmtV8cpPlKGANAMlQn",
"dn0Hj2nB3iitrlqIwXC8I3tUsQgMF7Pa3KCdHdbEwzCIfYKl8T")
auth.set_access_token("309118593-4rwYHPmOey8BFsuUHwHhLUhzXxvyXIwjsEX3tBXZ",
"Cs0nHXO2Z1sFoe9ukM0D997GWGRiFxZmXuWyGxCzQoFIh")
api = tweepy.API(auth)
try:
api.verify_credentials()
print("Authentication OK")
except:
print("Error during authentication")
api.update_status("Hello")
## 2. Retrieving / hydrating tweets
## 90 000 at a time, in 15 minutes, saving it in different files
election_filter_dateok=pd.read_csv('C:/Users/rapha/Desktop/StagePython/Projet/election_filter_dateok.csv',sep=";")
filenames=[]
for i in range(0,449):
filenames.append("tweets_"+str(i)+".csv")
def getNextFile():
for i,name in enumerate(filenames):
if os.path.isfile('C:/Users/rapha/Desktop/StagePython/Projet/tweets/'+name):
print(name+ " exists")
else:
print(name+ " does not exists")
return(i)
break
##il faut fonctionner par ajouter vertical et pas par remplacement ?
def createNextFile2():
next_file_num=getNextFile()
local_df_tweets=pd.DataFrame()
all_ids_list=election_filter_dateok.iloc[next_file_num*90000:next_file_num*90000+90000,0].tolist()
local_df_tweets['id']=None
local_df_tweets['text']=None
local_df_tweets['author_name']=None
local_df_tweets['author_realname']=None
local_df_tweets['author_verified']=None
local_df_tweets['author_id']=None
local_df_tweets['author_followers']=None
local_df_tweets['author_favcount']=None
local_df_tweets['author_friendscount']=None
local_df_tweets['author_location']=None
local_df_tweets['author_statuscount']=None
local_df_tweets['created_at']=None
local_df_tweets['favorite_count']=None
local_df_tweets['in_reply_to_status_id']=None
local_df_tweets['in_reply_to_user_id']=None
local_df_tweets['in_reply_to_screen_name']=None
local_df_tweets['is_quote_status']=None
local_df_tweets['lang']=None
local_df_tweets['place']=None
local_df_tweets['retweet_count']=None
local_df_tweets['retweeted_status_text']=None
local_df_tweets['retweeted_status_author_name']=None
local_df_tweets['source']=None
for k in range(0,int(len(all_ids_list)/100)):
start = time.time()
print("Tweet pack number : "+str(k))
listlim=0
if (len(all_ids_list)-k*100+100>=0):
listlim=k*100+100
else:
listlim=len(all_ids_list)
list_id_pre=all_ids_list[k*100:listlim]
list_id=[format(x,'.0f') for x in list_id_pre]
#print(list_id)
lookup=api.statuses_lookup(list_id,tweet_mode="extended")
local_pack_df_tweets=pd.DataFrame()
for count,status in enumerate(lookup):
local_pack_df_tweets.loc[count,"id"]="'"+status.id_str
local_pack_df_tweets.loc[count,"text"]=status.full_text
local_pack_df_tweets.loc[count,"author_realname"]=status.author.name
local_pack_df_tweets.loc[count,"author_name"]=status.author.screen_name
local_pack_df_tweets.loc[count,"author_id"]=status.author.id_str
local_pack_df_tweets.loc[count,"author_favcount"]=status.author.favourites_count
local_pack_df_tweets.loc[count,"author_friendscount"]=status.author.friends_count
local_pack_df_tweets.loc[count,"author_location"]=status.author.location
local_pack_df_tweets.loc[count,"author_statuscount"]=status.author.statuses_count
local_pack_df_tweets.loc[count,"author_verified"]=status.author.verified
local_pack_df_tweets.loc[count,"author_followers"]=status.author.followers_count
local_pack_df_tweets.loc[count,"author_verified"]=status.author.verified
local_pack_df_tweets.loc[count,"created_at"]=status.created_at
local_pack_df_tweets.loc[count,"favorite_count"]=status.favorite_count
if (status.in_reply_to_status_id_str != None):
local_pack_df_tweets.loc[count,"in_reply_to_status_id"]="'"+status.in_reply_to_status_id_str
local_pack_df_tweets.loc[count,"in_reply_to_user_id"]=status.in_reply_to_user_id_str
local_pack_df_tweets.loc[count,"in_reply_to_screen_name"]=status.in_reply_to_screen_name
local_pack_df_tweets.loc[count,"is_quote_status"]=status.is_quote_status
local_pack_df_tweets.loc[count,"lang"]=status.lang
local_pack_df_tweets.loc[count,"place"]=status.place
local_pack_df_tweets.loc[count,"retweet_count"]=status.retweet_count
local_pack_df_tweets.loc[count,"source"]=status.source
try:
local_pack_df_tweets.loc[count,"retweeted_status_text"]=status.retweeted_status.full_text
local_pack_df_tweets.loc[count,"retweeted_status_author_name"]=status.retweeted_status.author.screen_name
except:
local_pack_df_tweets.loc[count,"retweeted_status_text"]=None
local_pack_df_tweets.loc[count,"retweeted_status_author_name"]=None
print("tweet number : "+str(count)+" of tweet_pack : "+str(k))
local_df_tweets=local_df_tweets.append(local_pack_df_tweets)
end = time.time()
print(str(end - start)+ " seconds for pack number : "+str(k))
local_df_tweets.to_csv('C:/Users/rapha/Desktop/StagePython/Projet/tweets/tweets_'+str(next_file_num)+'.csv',sep=";",index=False)
return("Work done, tweets saved to tweets_"+str(next_file_num)+".csv")
#Lançons la création de fichiers
for i in range(10):
createNextFile2()
time.sleep(5*60) #toutes les 5 minutes #suffisant car la création prend minimum 10min elle même
## Problèmes de temps!
##plus le df est grand plus les opérations sur chaque paquet sont longues
def createNextFile():
next_file_num=getNextFile()
local_df_tweets=pd.DataFrame()
#local_df_tweets['id']=election_filter_dateok.iloc[next_file_num*90000:next_file_num*90000+90000,0]
local_df_tweets['id']=election_filter_dateok.iloc[98000:99000,0]
local_df_tweets['text']=None
local_df_tweets['author_name']=None
local_df_tweets['author_realname']=None
local_df_tweets['author_verified']=None
local_df_tweets['author_id']=None
local_df_tweets['author_followers']=None
local_df_tweets['author_favcount']=None
local_df_tweets['author_friendscount']=None
local_df_tweets['author_location']=None
local_df_tweets['author_statuscount']=None
local_df_tweets['created_at']=None
local_df_tweets['favorite_count']=None
local_df_tweets['in_reply_to_status_id']=None
local_df_tweets['in_reply_to_user_id']=None
local_df_tweets['in_reply_to_screen_name']=None
local_df_tweets['is_quote_status']=None
local_df_tweets['lang']=None
local_df_tweets['place']=None
local_df_tweets['retweet_count']=None
local_df_tweets['retweeted_status_text']=None
local_df_tweets['retweeted_status_author_name']=None
local_df_tweets['source']=None
for k in range(0,int(len(local_df_tweets)/100)):
print("Tweet pack number : "+str(k))
listlim=0
if (len(local_df_tweets)-k*100+100>=0):
listlim=k*100+100
else:
listlim=len(local_df_tweets)
list_id=local_df_tweets.iloc[k*100:listlim,0].tolist()
lookup=api.statuses_lookup(list_id,tweet_mode="extended")
print(lookup)
for count,status in enumerate(lookup):
local_df_tweets.loc[k*100+count,"id"]="'"+status.id_str
local_df_tweets.loc[k*100+count,"text"]=status.full_text
local_df_tweets.loc[k*100+count,"author_realname"]=status.author.name
local_df_tweets.loc[k*100+count,"author_name"]=status.author.screen_name
local_df_tweets.loc[k*100+count,"author_id"]=status.author.id_str
local_df_tweets.loc[k*100+count,"author_favcount"]=status.author.favourites_count
local_df_tweets.loc[k*100+count,"author_friendscount"]=status.author.friends_count
local_df_tweets.loc[k*100+count,"author_location"]=status.author.location
local_df_tweets.loc[k*100+count,"author_statuscount"]=status.author.statuses_count
local_df_tweets.loc[k*100+count,"author_verified"]=status.author.verified
local_df_tweets.loc[k*100+count,"author_followers"]=status.author.followers_count
local_df_tweets.loc[k*100+count,"author_verified"]=status.author.verified
local_df_tweets.loc[k*100+count,"created_at"]=status.created_at
local_df_tweets.loc[k*100+count,"favorite_count"]=status.favorite_count
if (status.in_reply_to_status_id_str != None):
local_df_tweets.loc[k*100+count,"in_reply_to_status_id"]="'"+status.in_reply_to_status_id_str
local_df_tweets.loc[k*100+count,"in_reply_to_user_id"]=status.in_reply_to_user_id_str
local_df_tweets.loc[k*100+count,"in_reply_to_screen_name"]=status.in_reply_to_screen_name
local_df_tweets.loc[k*100+count,"is_quote_status"]=status.is_quote_status
local_df_tweets.loc[k*100+count,"lang"]=status.lang
local_df_tweets.loc[k*100+count,"place"]=status.place
local_df_tweets.loc[k*100+count,"retweet_count"]=status.retweet_count
local_df_tweets.loc[k*100+count,"source"]=status.source
try:
local_df_tweets.loc[k*100+count,"retweeted_status_text"]=status.retweeted_status.full_text
local_df_tweets.loc[k*100+count,"retweeted_status_author_name"]=status.retweeted_status.author.screen_name
except:
local_df_tweets.loc[k*100+count,"retweeted_status_text"]=None
local_df_tweets.loc[k*100+count,"retweeted_status_author_name"]=None
print("tweet number : "+str(count)+" of tweet_pack : "+str(k))
print(status.full_text)
local_df_tweets.to_csv('C:/Users/rapha/Desktop/StagePython/Projet/tweets/tweets_'+str(next_file_num)+'.csv',sep=";",index=False)
return("Work done, tweets saved to tweets_"+str(next_file_num)+".csv")
local_df_tweets=pd.DataFrame()
local_df_tweets['id']=election_filter_dateok.iloc[190000:199000,0].tolist()
local_df_tweets['text']=None
local_df_tweets['author_name']=None
local_df_tweets['author_realname']=None
local_df_tweets['author_verified']=None
local_df_tweets['author_id']=None
local_df_tweets['author_followers']=None
local_df_tweets['author_favcount']=None
local_df_tweets['author_friendscount']=None
local_df_tweets['author_location']=None
local_df_tweets['author_statuscount']=None
local_df_tweets['created_at']=None
local_df_tweets['favorite_count']=None
local_df_tweets['in_reply_to_status_id']=None
local_df_tweets['in_reply_to_user_id']=None
local_df_tweets['in_reply_to_screen_name']=None
local_df_tweets['is_quote_status']=None
local_df_tweets['lang']=None
local_df_tweets['place']=None
local_df_tweets['retweet_count']=None
local_df_tweets['retweeted_status_text']=None
local_df_tweets['retweeted_status_author_name']=None
local_df_tweets['source']=None
for k in range(0,int(len(local_df_tweets)/100)):
start = time.time()
print("Tweet pack number : "+str(k))
listlim=0
if (len(local_df_tweets)-k*100+100>=0):
listlim=k*100+100
else:
listlim=len(local_df_tweets)
list_id_pre=local_df_tweets.iloc[k*100:listlim,0].tolist()
list_id=[format(x,'.0f') for x in list_id_pre]
#print(list_id)
lookup=api.statuses_lookup(list_id,tweet_mode="extended")
for count,status in enumerate(lookup):
local_df_tweets.loc[k*100+count,"id"]="'"+status.id_str
local_df_tweets.loc[k*100+count,"text"]=status.full_text
local_df_tweets.loc[k*100+count,"author_realname"]=status.author.name
local_df_tweets.loc[k*100+count,"author_name"]=status.author.screen_name
local_df_tweets.loc[k*100+count,"author_id"]=status.author.id_str
local_df_tweets.loc[k*100+count,"author_favcount"]=status.author.favourites_count
local_df_tweets.loc[k*100+count,"author_friendscount"]=status.author.friends_count
local_df_tweets.loc[k*100+count,"author_location"]=status.author.location
local_df_tweets.loc[k*100+count,"author_statuscount"]=status.author.statuses_count
local_df_tweets.loc[k*100+count,"author_verified"]=status.author.verified
local_df_tweets.loc[k*100+count,"author_followers"]=status.author.followers_count
local_df_tweets.loc[k*100+count,"author_verified"]=status.author.verified
local_df_tweets.loc[k*100+count,"created_at"]=status.created_at
local_df_tweets.loc[k*100+count,"favorite_count"]=status.favorite_count
if (status.in_reply_to_status_id_str != None):
local_df_tweets.loc[k*100+count,"in_reply_to_status_id"]="'"+status.in_reply_to_status_id_str
local_df_tweets.loc[k*100+count,"in_reply_to_user_id"]=status.in_reply_to_user_id_str
local_df_tweets.loc[k*100+count,"in_reply_to_screen_name"]=status.in_reply_to_screen_name
local_df_tweets.loc[k*100+count,"is_quote_status"]=status.is_quote_status
local_df_tweets.loc[k*100+count,"lang"]=status.lang
local_df_tweets.loc[k*100+count,"place"]=status.place
local_df_tweets.loc[k*100+count,"retweet_count"]=status.retweet_count
local_df_tweets.loc[k*100+count,"source"]=status.source
try:
local_df_tweets.loc[k*100+count,"retweeted_status_text"]=status.retweeted_status.full_text
local_df_tweets.loc[k*100+count,"retweeted_status_author_name"]=status.retweeted_status.author.screen_name
except:
local_df_tweets.loc[k*100+count,"retweeted_status_text"]=None
local_df_tweets.loc[k*100+count,"retweeted_status_author_name"]=None
#print("tweet number : "+str(count)+" of tweet_pack : "+str(k))
#print(status.full_text)
end = time.time()
print(str(end - start)+ " seconds for pack number : "+str(k))