forked from minimaxir/facebook-page-post-scraper
-
Notifications
You must be signed in to change notification settings - Fork 1
/
get_fb_posts_fb_group.py
executable file
·207 lines (158 loc) · 7.69 KB
/
get_fb_posts_fb_group.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
import urllib2
import json
import datetime
import csv
import time
from MySQL_Actions import MySQL_Codes
import settings
app_id = settings.app_id
app_secret = settings.app_secret # DO NOT SHARE WITH ANYONE!
#group_id = settings.group_id_for_posts
access_token = app_id + "|" + app_secret
db_action = MySQL_Codes()
def work_as_scheduled(sgroup_id):
scrapeFacebookPageFeedStatus(sgroup_id, access_token)
def reset_deleted_tag():
db_action.ID_checker_already_deleted = {}
def request_until_succeed(url):
req = urllib2.Request(url)
success = False
while success is False:
try:
response = urllib2.urlopen(req)
if response.getcode() == 200:
success = True
except Exception, e:
print e
time.sleep(5)
print "Error for URL %s: %s" % (url, datetime.datetime.now())
print "Retrying."
return response.read()
# Needed to write tricky unicode correctly to csv
def unicode_normalize(text):
return text.translate({ 0x2018:0x27, 0x2019:0x27, 0x201C:0x22, 0x201D:0x22,
0xa0:0x20 }).encode('utf-8')
def getFacebookPageFeedData(group_id, access_token, num_statuses):
# Construct the URL string; see
# http://stackoverflow.com/a/37239851 for Reactions parameters
base = "https://graph.facebook.com/v2.6"
node = "/%s/feed" % group_id
fields = "/?fields=message,link,created_time,type,name,id," + \
"comments.limit(0).summary(true),shares,reactions." + \
"limit(0).summary(true),from"
parameters = "&limit=%s&access_token=%s" % (num_statuses, access_token)
url = base + node + fields + parameters
# retrieve data
data = json.loads(request_until_succeed(url))
return data
def getReactionsForStatus(status_id, access_token):
# See http://stackoverflow.com/a/37239851 for Reactions parameters
# Reactions are only accessable at a single-post endpoint
base = "https://graph.facebook.com/v2.6"
node = "/%s" % status_id
reactions = "/?fields=" \
"reactions.type(LIKE).limit(0).summary(total_count).as(like)" \
",reactions.type(LOVE).limit(0).summary(total_count).as(love)" \
",reactions.type(WOW).limit(0).summary(total_count).as(wow)" \
",reactions.type(HAHA).limit(0).summary(total_count).as(haha)" \
",reactions.type(SAD).limit(0).summary(total_count).as(sad)" \
",reactions.type(ANGRY).limit(0).summary(total_count).as(angry)"
parameters = "&access_token=%s" % access_token
url = base + node + reactions + parameters
# retrieve data
data = json.loads(request_until_succeed(url))
return data
def processFacebookPageFeedStatus(status, access_token):
# The status is now a Python dictionary, so for top-level items,
# we can simply call the key.
# Additionally, some items may not always exist,
# so must check for existence first
status_id = status['id']
status_message = '' if 'message' not in status.keys() else \
unicode_normalize(status['message'])
link_name = '' if 'name' not in status.keys() else \
unicode_normalize(status['name'])
status_type = status['type']
status_link = '' if 'link' not in status.keys() else \
unicode_normalize(status['link'])
status_author = unicode_normalize(status['from']['name'])
# Time needs special care since a) it's in UTC and
# b) it's not easy to use in statistical programs.
status_published = datetime.datetime.strptime(\
status['created_time'],'%Y-%m-%dT%H:%M:%S+0000')
status_published = status_published + datetime.timedelta(hours=-5) # EST
# best time format for spreadsheet programs:
status_published = status_published.strftime('%Y-%m-%d %H:%M:%S')
# Nested items require chaining dictionary keys.
num_reactions = 0 if 'reactions' not in status else \
status['reactions']['summary']['total_count']
num_comments = 0 if 'comments' not in status else \
status['comments']['summary']['total_count']
num_shares = 0 if 'shares' not in status else \
status['shares']['count']
# Counts of each reaction separately; good for sentiment
# Only check for reactions if past date of implementation:
# http://newsroom.fb.com/news/2016/02/reactions-now-available-globally/
reactions = getReactionsForStatus(status_id, access_token) \
if status_published > '2016-02-24 00:00:00' else {}
num_likes = 0 if 'like' not in reactions else \
reactions['like']['summary']['total_count']
# Special case: Set number of Likes to Number of reactions for pre-reaction
# statuses
num_likes = num_reactions if status_published < '2016-02-24 00:00:00' else \
num_likes
def get_num_total_reactions(reaction_type, reactions):
if reaction_type not in reactions:
return 0
else:
return reactions[reaction_type]['summary']['total_count']
num_loves = get_num_total_reactions('love', reactions)
num_wows = get_num_total_reactions('wow', reactions)
num_hahas = get_num_total_reactions('haha', reactions)
num_sads = get_num_total_reactions('sad', reactions)
num_angrys = get_num_total_reactions('angry', reactions)
# return a tuple of all processed data
return (status_id, status_message, status_author, link_name, status_type,
status_link, status_published, num_reactions, num_comments,
num_shares, num_likes, num_loves, num_wows, num_hahas, num_sads,
num_angrys)
def scrapeFacebookPageFeedStatus(group_id, access_token):
#with open('%s_facebook_statuses.csv' % group_id, 'wb') as file:
# w = csv.writer(file)
# w.writerow(["status_id", "status_message", "status_author",
# "link_name", "status_type", "status_link",
# "status_published", "num_reactions", "num_comments",
# "num_shares", "num_likes", "num_loves", "num_wows",
# "num_hahas", "num_sads", "num_angrys"])
has_next_page = True
num_processed = 0 # keep a count on how many we've processed
scrape_starttime = datetime.datetime.now()
print "Scraping %s Facebook Group: %s\n" % \
(group_id, scrape_starttime)
statuses = getFacebookPageFeedData(group_id, access_token, 100)
while has_next_page:
for status in statuses['data']:
# Ensure it is a status with the expected metadata
if 'reactions' in status:
db_action.save_to_db(processFacebookPageFeedStatus(status,access_token),'status',group_id)
#w.writerow(processFacebookPageFeedStatus(status, \
# access_token))
# output progress occasionally to make sure code is not
# stalling
num_processed += 1
if num_processed % 100 == 0:
print "%s Statuses Processed: %s" % (num_processed,
datetime.datetime.now())
# if there is no next page, we're done.
if 'paging' in statuses.keys():
statuses = json.loads(request_until_succeed(\
statuses['paging']['next']))
else:
has_next_page = False
#db_action.close_db_connection()
print "\nDone!\n%s Statuses Processed in %s" % \
(num_processed, datetime.datetime.now() - scrape_starttime)
if __name__ == '__main__':
print ('Invalid action! Please run "crawler_job.py" instead.')
# scrapeFacebookPageFeedStatus(group_id, access_token)
# The CSV can be opened in all major statistical programs. Have fun! :)