def cal_propage_work(item):
uid = item['uid']
timestamp = item['timestamp']
text = item['text']
sw_list = searchWord(text.encode('utf-8'))
sensitive = len(sw_list)
#ip = item['geo']
ip = item['send_ip']
# attribute location
if ip:
save_city(uid, ip, timestamp, sensitive)
# attribute activity
date = ts2datetime(timestamp)
ts = datetime2ts(date)
date = date.replace('-','')
time_segment = (timestamp - ts) / Fifteenminutes
save_activity(uid, date, time_segment, sensitive)
# attribute mention
at_uname_list = extract_uname(text)
try:
at_uname = at_uname_list[0]
save_at(uid, at_uname, timestamp, sensitive)
except:
pass
def get_one_click_evaluation(task_detail):
results = []
text = task_detail['text'].encode('utf-8')
node = createWordTree()
#print 'text...',text
sensitive_words_dict = searchWord(text, node)
#print 'sensitive_words_dict..',sensitive_words_dict
if sensitive_words_dict:
score = 0
sensitive_words_list = []
for k, v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
#print 'tmp_stage..',tmp_stage
if tmp_stage:
score += v * sensitive_score_dict[str(tmp_stage)]
sensitive_words_list.append(k.decode('utf-8'))
results.append(score)
results.append(sensitive_words_list)
else:
results = [0, []]
return results
def sensitive_process(text,timestamp):
## 人物敏感度
iter_results = {} # iter_results = {uid:{}}
now_ts = time.time()
#run_type
today_sensitive_results = {}
if S_TYPE != 'test':
now_date_ts = datetime2ts(ts2datetime(now_ts))
else:
now_date_ts = datetime2ts(S_DATE)
for i in range(WEEK,0,-1):
ts = now_date_ts - DAY*i
sensitive_results = r_cluster_3.hmget('sensitive_'+str(ts), uid_list)
count = 0
for uid in uid_list:
if uid not in today_sensitive_results:
today_sensitive_results[uid] = {}
#compute sensitive
sensitive_item = sensitive_results[count]
if sensitive_item:
uid_sensitive_dict = json.loads(sensitive_item)
else:
uid_sensitive_dict = {}
for sensitive_word in uid_sensitive_dict:
try:
iter_results[uid]['sensitive'][sensitive_word] += uid_sensitive_dict[sensitive_word]
except:
iter_results[uid]['sensitive'][sensitive_word] = uid_sensitive_dict[sensitive_word]
if ts == now_date_ts - DAY:
try:
today_sensitive_results[uid][sensitive_word] += uid_sensitive_dict[sensitive_word]
except:
today_sensitive_results[uid][sensitive_word] = uid_sensitive_dict[sensitive_word]
for uid in uid_list:
results[uid] = {}
## 信息敏感度
sensitive_words_dict = searchWord(text.encode('utf-8', 'ignore'), DFA)
if sensitive_words_dict:
item['sensitive_words_string'] = "&".join(sensitive_words_dict.keys())
item['sensitive_words_dict'] = json.dumps(sensitive_words_dict)
else:
item['sensitive_words_string'] = ""
item['sensitive_words_dict'] = json.dumps({})
sensitive_words_dict = json.loads(item['sensitive_words_dict'])
if sensitive_words_dict:
score = 0
for k,v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
score += v*sensitive_score_dict[str(tmp_stage)]
index_body['sensitive'] = score
def compute_sensitive(text):
score = 0
node = createWordTree()
sensitive_words_dict = searchWord(text.encode('utf-8'), node)
if sensitive_words_dict:
for k, v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
score += v * sensitive_score_dict[str(tmp_stage)]
return score
def sensitive_check(text):
DFA = createWordTree()
item = {}
count = 0
sensitive_words_dict = searchWord(text, DFA)
if sensitive_words_dict:
item['sensitive_words_string'] = "&".join(sensitive_words_dict.keys())
item['sensitive_words_dict'] = json.dumps(sensitive_words_dict)
else:
item['sensitive_words_string'] = ""
item['sensitive_words_dict'] = json.dumps({})
for i in sensitive_words_dict:
count += sensitive_words_dict[i]
return count, item
def comment_uname2uid(item):
direct_uid = None
uid = item['uid']
root_uid = item['root_uid']
timestamp = item['timestamp']
text = item['text']
sensitive_words_dict = searchWord(text.encode('utf-8', 'ignore'), DFA)
sensitive = len(sensitive_words_dict)
direct_uid = ''
if isinstance(text, str):
text = text.decode('utf-8', 'ignore')
RE = re.compile(u'回复@([a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+):', re.UNICODE)
comment_chains = RE.findall(text)
if comment_chains != []:
direct_uname = comment_chains[0]
direct_uid = uname2uid(direct_uname)
if direct_uid == '':
direct_uid = root_uid
save_comment(uid, direct_uid, timestamp, sensitive)
def get_sensitive_user(timestamp, uid):
score = 0
query_body = {
'query':{
'term':{'uid':uid}
},
'size':50
}
index_name = flow_text_index_name_pre + ts2datetime(timestamp)
search_results = es_flow_text.search(index=index_name,doc_type=flow_text_index_type,body=query_body)['hits']['hits']
for result in search_results:
text = result['_source']['text'].encode('utf-8')
node = createWordTree();
sensitive_words_dict = searchWord(text, node)
if sensitive_words_dict:
sensitive_words_list = []
for k,v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
score += v*sensitive_score_dict[str(tmp_stage)]
print '\n'
print '\n'
print '\n'
print '\n'
print '\n'
print 'score=============',score
print '\n'
print '\n'
print '\n'
print '\n'
return score
def comment_uname2uid(item):
direct_uid = None
uid = item['uid']
root_uid = item['root_uid']
timestamp = item['timestamp']
text = item['text']
sensitive_words_dict = searchWord(text.encode('utf-8', 'ignore'), DFA)
sensitive = len(sensitive_words_dict)
direct_uid = ''
if isinstance(text, str):
text = text.decode('utf-8', 'ignore')
RE = re.compile(u'回复@([a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+):',
re.UNICODE)
comment_chains = RE.findall(text)
if comment_chains != []:
direct_uname = comment_chains[0]
direct_uid = uname2uid(direct_uname)
if direct_uid == '':
direct_uid = root_uid
save_comment(uid, direct_uid, timestamp, sensitive)
def cal_propage_work(item):
uid = item['uid']
timestamp = item['timestamp']
text = item['text']
sensitive_words_dict = searchWord(text.encode('utf-8', 'ignore'), DFA)
sensitive = len(sensitive_words_dict)
#if sensitive:
# r.sadd('sensitive_user', uid) # 敏感微博用户集合
#ip = item['geo']
ip = item['send_ip']
# attribute location
if ip:
save_city(uid, ip, timestamp, sensitive)
# attribute activity
date = ts2datetime(timestamp)
ts = datetime2ts(date)
time_segment = (timestamp - ts) / Fifteenminutes
save_activity(uid, timestamp, time_segment, sensitive)
# attribute mention
at_uname_list = extract_uname(text)
try:
if at_uname_list:
at_uname = at_uname_list[0]
if at_uname != '':
save_at(uid, at_uname, timestamp, sensitive)
except:
pass
# hashtag
hashtag_list = extract_hashtag(text)
if hashtag_list:
cal_hashtag_work(uid, hashtag_list, timestamp, sensitive)
def cal_propage_work(item):
uid = item['uid']
timestamp = item['timestamp']
text = item['text']
sensitive_words_dict = searchWord(text.encode('utf-8', 'ignore'), DFA)
sensitive = len(sensitive_words_dict)
#if sensitive:
# r.sadd('sensitive_user', uid) # 敏感微博用户集合
#ip = item['geo']
ip = item['send_ip']
# attribute location
if ip:
save_city(uid, ip, timestamp, sensitive)
"""
# attribute activity
date = ts2datetime(timestamp)
ts = datetime2ts(date)
time_segment = (timestamp - ts) / Fifteenminutes
save_activity(uid, timestamp, time_segment, sensitive)
# attribute mention
at_uname_list = extract_uname(text)
try:
at_uname = at_uname_list[0]
save_at(uid, at_uname, timestamp, sensitive)
except:
pass
"""
# hashtag
hashtag_list = extract_hashtag(text)
if hashtag_list:
cal_hashtag_work(uid, hashtag_list, timestamp, sensitive)
def test(ft_type):
print ft_type
if ft_type == 'facebook':
index_name_pre = facebook_flow_text_index_name_pre
index_type = facebook_flow_text_index_type
user_index_name = facebook_user_index_name
user_index_type = facebook_user_index_type
else:
index_name_pre = twitter_flow_text_index_name_pre
index_type = twitter_flow_text_index_type
user_index_name = twitter_user_index_name
user_index_type = twitter_user_index_type
# date_list = load_date_list(True)
date_list = load_date_list()
DFA = createWordTree()
query_body = {
'post_filter': {
'missing': {
'field': 'keywords_string'
}
},
'query': {
'filtered': {
'filter': {
'bool': {
'must': [{
'range': {
'flag_ch': {
'gte': -1
}
}
}]
}
}
}
}
}
for date in date_list:
count = 0
bulk_action = []
index_name = index_name_pre + date
try:
es_scan_results = scan(es,
query=query_body,
size=1000,
index=index_name,
doc_type=index_type)
while True:
try:
scan_data = es_scan_results.next()
item = scan_data['_source']
text = item['text_ch']
uid = item['uid']
if ft_type == 'facebook':
_id = item['fid']
else:
_id = item['tid']
ts = datetime2ts(date)
#add sentiment field to weibo
sentiment, keywords_list = triple_classifier(item)
#add key words to weibo
keywords_dict, keywords_string = get_weibo_keywords(
keywords_list)
#sensitive_words_dict
sensitive_words_dict = searchWord(
text.encode('utf-8', 'ignore'), DFA)
if sensitive_words_dict:
sensitive_words_string_data = "&".join(
sensitive_words_dict.keys())
sensitive_words_dict_data = json.dumps(
sensitive_words_dict)
else:
sensitive_words_string_data = ""
sensitive_words_dict_data = json.dumps({})
#redis
if sensitive_words_dict:
sensitive_count_string = r_cluster.hget(
'sensitive_' + str(ts), str(uid))
if sensitive_count_string: #redis取空
sensitive_count_dict = json.loads(
sensitive_count_string)
for word in sensitive_words_dict.keys():
if sensitive_count_dict.has_key(word):
sensitive_count_dict[
word] += sensitive_words_dict[word]
else:
sensitive_count_dict[
word] = sensitive_words_dict[word]
r_cluster.hset('sensitive_' + str(ts), str(uid),
json.dumps(sensitive_count_dict))
else:
r_cluster.hset('sensitive_' + str(ts), str(uid),
json.dumps(sensitive_words_dict))
#sensitive
sensitive_score = 0
if sensitive_words_dict:
for k, v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
sensitive_score += v * sensitive_score_dict[
str(tmp_stage)]
#directed_uid
directed_uid_data = 0
directed_uid, directed_uname = get_root_retweet(
text, uid, ft_type)
if directed_uid:
directed_uid_data = long(directed_uid)
# hashtag
hashtag = ''
RE = re.compile(
u'#([0-9a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+)[ ," =.。： :、]'
)
hashtag_list = re.findall(RE, text)
if hashtag_list:
hashtag = '&'.join(hashtag_list)
#action
action = {'update': {'_id': _id}}
# action_data
action_data = {
'sentiment': str(sentiment),
'keywords_dict': json.dumps(keywords_dict),
'keywords_string': keywords_string,
'sensitive_words_string': sensitive_words_string_data,
'sensitive_words_dict': sensitive_words_dict_data,
'sensitive': sensitive_score,
'directed_uid': directed_uid_data,
'directed_uname': directed_uname,
'hashtag': hashtag,
}
bulk_action.extend([action, {'doc': action_data}])
count += 1
if count % 1000 == 0 and count != 0:
if bulk_action:
es.bulk(bulk_action,
index=index_name,
doc_type=facebook_flow_text_index_type,
timeout=600)
bulk_action = []
count = 0
except StopIteration:
break
if bulk_action:
es.bulk(bulk_action,
index=index_name,
doc_type=facebook_flow_text_index_type,
timeout=600)
except Exception, e: #es文档不存在
print e
continue
if int(item['sp_type']) == 1:
read_count += 1
text = item['text']
uid = item['uid']
#add sentiment field to weibo
sentiment, keywords_list = triple_classifier(item)
item['sentiment'] = str(sentiment)
#add key words to weibo
keywords_dict, keywords_string = get_weibo_keywords(keywords_list)
item['keywords_dict'] = json.dumps(keywords_dict) # use to compute
item['keywords_string'] = keywords_string # use to search
sensitive_words_dict = searchWord(text.encode('utf-8', 'ignore'), DFA)
if sensitive_words_dict:
item['sensitive_words_string'] = "&".join(sensitive_words_dict.keys())
item['sensitive_words_dict'] = json.dumps(sensitive_words_dict)
else:
item['sensitive_words_string'] = ""
item['sensitive_words_dict'] = json.dumps({})
timestamp = item['timestamp']
date = ts2datetime(timestamp)
ts = datetime2ts(date)
if sensitive_words_dict:
print sensitive_words_dict.keys()[0]
sensitive_count_string = r_cluster.hget('sensitive_'+str(ts), str(uid))
if sensitive_count_string: #redis取空
sensitive_count_dict = json.loads(sensitive_count_string)
def get_sensitive_user(timestamp, uid):
score = 0
query_body = {'query': {'term': {'uid': uid}}, 'size': 50}
index_name = flow_text_index_name_pre + ts2datetime(timestamp)
try:
search_results = es_xnr.search(index=index_name,
doc_type=flow_text_index_type,
body=query_body)['hits']['hits']
except Exception, e:
pass
search_results = []
for result in search_results:
text = result['_source']['text'].encode('utf-8')
node = createWordTree()
sensitive_words_dict = searchWord(text, node)
if sensitive_words_dict:
sensitive_words_list = []
for k, v in sensitive_words_dict.iteritems():
tmp_stage = r_sensitive.hget("sensitive_words", k)
if tmp_stage:
score += v * sensitive_score_dict[str(tmp_stage)]
return score
if __name__ == '__main__':
# '2017-10-15'
# print get_sensitive_user(timestamp=1507996800, uid='100003271864059')
print get_sensitive_info(timestamp=1507996800,
mid='123124323',
text=u"64和达赖太阳花")
text = text_ch[0]
item['text'] = text_ch[0]
except:
pass
#add sentiment field to weibo
sentiment, keywords_list = triple_classifier(item)
item['sentiment'] = str(sentiment)
#add key words to weibo
keywords_dict, keywords_string = get_weibo_keywords(
keywords_list)
item['keywords_dict'] = json.dumps(
keywords_dict) # use to compute
item['keywords_string'] = keywords_string # use to search
sensitive_words_dict = searchWord(
text.encode('utf-8', 'ignore'), DFA)
if sensitive_words_dict:
item['sensitive_words_string'] = "&".join(
sensitive_words_dict.keys())
item['sensitive_words_dict'] = json.dumps(
sensitive_words_dict)
else:
item['sensitive_words_string'] = ""
item['sensitive_words_dict'] = json.dumps({})
timestamp = item['timestamp']
date = ts2datetime(timestamp)
ts = datetime2ts(date)
if sensitive_words_dict:
#print 'sensitive_words_dict...keys[0]...',sensitive_words_dict.keys()[0]
sensitive_count_string = r_cluster.hget(
def cal_propage_work(item, sensitive_words):
cluster_redis = R_CLUSTER_FLOW1
user = str(item['uid'])
followers_count = item['user_fansnum']
friends_count = item.get("user_friendsnum", 0)
cluster_redis.hset(user, 'user_fansnum', followers_count)
cluster_redis.hset(user, 'user_friendsnum', friends_count)
retweeted_uid = str(item['root_uid'])
retweeted_mid = str(item['root_mid'])
message_type = int(item['message_type'])
mid = str(item['mid'])
timestamp = item['timestamp']
text = item['text']
sw_list = searchWord(text.encode('utf-8'))
sensitive_result = len(sw_list)
if sensitive_result:
date = ts2datetime(timestamp)
ts = datetime2ts(date)
map = {}
for w in sw_list:
word = "".join([chr(x) for x in w])
word = word.decode('utf-8')
print word
if not map.__contains__(word):
map[word] = 1
else:
map[word] += 1
try:
sensitive_count_string = r_cluster.hget('sensitive_'+str(ts), str(uid))
sensitive_count_dict = json.loads(sensitive_count_string)
for word in map:
count = map[word]
if sensitive_count_dict.__contains__(word):
sensitive_count_dict[word] += count
else:
sensitive_count_dict[word] = count
r_cluster.hset('sensitive_'+str(ts), str(uid), json.dumps(sensitive_count_dict))
except:
r_cluster.hset('sensitive_'+str(ts), str(uid), json.dumps(sensitive_dict))
if message_type == 1:
cluster_redis.sadd('user_set', user)
if sensitive_result:
cluster_redis.hset('s_'+user, mid + '_origin_weibo_timestamp', timestamp)
else:
cluster_redis.hset(user, mid + '_origin_weibo_timestamp', timestamp)
elif message_type == 2: # comment weibo
cluster_redis.sadd('user_set', user)
if cluster_redis.sismember(user + '_comment_weibo', retweeted_mid) or cluster_redis.sismember('s_' + user + '_comment_weibo', retweeted_mid):
return
#RE = re.compile(u'//@([a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+):', re.UNICODE)
#nicknames = RE.findall(text)
if not sensitive_result:
cluster_redis.sadd(user + '_comment_weibo', retweeted_mid)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby(user, 'comment_weibo', 1)
if 1:
#if len(nicknames) == 0:
cluster_redis.hincrby(retweeted_uid, retweeted_mid + '_origin_weibo_comment', 1)
cluster_redis.hincrby(retweeted_uid, 'origin_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset(retweeted_uid, retweeted_mid + '_origin_weibo_comment_timestamp', timestamp)
"""
else:
nick_id_ = nicknames[0]
_id = single_redis.hget(NICK_UID_NAMESPACE, nick_id_)
print _id
single_redis.hset(ACTIVE_NICK_UID_NAMESPACE, nick_id_, _id)
if _id:
cluster_redis.hincrby(str(_id), retweeted_mid + '_retweeted_weibo_comment', 1)
cluster_redis.hincrby(str(_id), 'retweeted_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset(str(_id), retweeted_mid + '_retweeted_weibo_comment_timestamp', timestamp)
"""
else:
cluster_redis.sadd('s_' + user + '_comment_weibo', retweeted_mid)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby('s_'+user, 'comment_weibo', 1)
if 1:
#if len(nicknames) == 0:
cluster_redis.hincrby('s_' + retweeted_uid, retweeted_mid + '_origin_weibo_comment', 1)
cluster_redis.hincrby('s_' + retweeted_uid, 'origin_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset('s_' + retweeted_uid, retweeted_mid + '_origin_weibo_comment_timestamp', timestamp)
"""
else:
nick_id_ = nicknames[0]
_id = single_redis.hget(NICK_UID_NAMESPACE, nick_id_)
print _id
single_redis.hset(ACTIVE_NICK_UID_NAMESPACE, nick_id_, _id)
if _id:
cluster_redis.hincrby('s_' + str(_id), retweeted_mid + '_retweeted_weibo_comment', 1)
cluster_redis.hincrby('s_' + str(_id), 'retweeted_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset('s_' + str(_id), retweeted_mid + '_retweeted_weibo_comment_timestamp', timestamp)
"""
elif message_type == 3:
cluster_redis.sadd('user_set', user)
if cluster_redis.sismember(user + '_retweeted_weibo', retweeted_mid) or cluster_redis.sismember('s_' + user + '_retweeted_weibo', retweeted_mid):
return
"""
RE = re.compile(u'//@([a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+):', re.UNICODE)
nicknames = RE.findall(text)
"""
if not sensitive_result:
cluster_redis.sadd(user + '_retweeted_weibo', retweeted_mid)
cluster_redis.hset(user, retweeted_mid + '_retweeted_weibo_timestamp', timestamp)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby(retweeted_uid, 'origin_weibo_retweeted_timestamp_%s' % queue_index, 1)
cluster_redis.hincrby(retweeted_uid, retweeted_mid + '_origin_weibo_retweeted', 1)
"""
if len(nicknames) != 0:
for nick_id in nicknames:
_id = single_redis.hget(NICK_UID_NAMESPACE, nick_id)
print _id
single_redis.hset(ACTIVE_NICK_UID_NAMESPACE, nick_id, _id)
if _id:
cluster_redis.hincrby(str(_id), retweeted_mid+'_retweeted_weibo_retweeted', 1)
cluster_redis.hset(str(_id), 'retweeted_weibo_retweeted_timestamp', timestamp)
cluster_redis.hincrby(str(_id), 'retweeted_weibo_retweeted_timestamp_%s' % queue_index, 1)
"""
else:
cluster_redis.sadd('s_' + user + '_retweeted_weibo', retweeted_mid)
cluster_redis.hset('s_' + user, retweeted_mid + '_retweeted_weibo_timestamp', timestamp)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby('s_' +retweeted_uid, 'origin_weibo_retweeted_timestamp_%s' %queue_index, 1)
cluster_redis.hincrby('s_' +retweeted_uid, retweeted_mid + '_origin_weibo_retweeted', 1)
"""
if (update_user_te - update_user_ts) % 900 == 0:
print 'update track user list'
monitor_user_list = get_track_task_user()
item = receiver.recv_json()
#test
if not item:
continue
if item['sp_type'] == '1':
read_count += 1
#print 'item:', item
if str(item['uid']) in monitor_user_list:
text = item['text']
# add sensitive field and sensitive_word field to weibo
sw_list = searchWord(text.encode('utf-8'))
sensitive = len(sw_list)
if sensitive:
item['sensitive'] = 1
word_set = set()
for w in sw_list:
word = ''.join([chr(x) for x in w])
word = word.decode('utf-8')
word_set.add(word)
sensitive_word_string = '&'.join(list(word_set))
item['sensitive_word'] = sensitive_word_string
else:
item['sensitive'] = 0
# add sentiment field to weibo
sentiment = get_sentiment_attribute(text)
item['sentiment'] = sentiment
print 'update track user list'
monitor_user_list = get_track_task_user()
item = receiver.recv_json()
#test
if not item:
continue
if item['sp_type'] == '1':
read_count += 1
#print 'item:', item
if str(item['uid']) in monitor_user_list:
text = item['text']
# add sensitive field and sensitive_word field to weibo
sw_list = searchWord(text.encode('utf-8'))
sensitive = len(sw_list)
if sensitive:
item['sensitive'] = 1
word_set = set()
for w in sw_list:
word = ''.join([chr(x) for x in w])
word = word.decode('utf-8')
word_set.add(word)
sensitive_word_string = '&'.join(list(word_set))
item['sensitive_word'] = sensitive_word_string
else:
item['sensitive'] = 0
# add sentiment field to weibo
sentiment = get_sentiment_attribute(text)
item['sentiment'] = sentiment
def cal_propage_work(item, sensitive_words):
cluster_redis = R_CLUSTER_FLOW1
user = str(item['uid'])
uid = str(item['uid'])
followers_count = item['user_fansnum']
friends_count = item.get("user_friendsnum", 0)
cluster_redis.hset(user, 'user_fansnum', followers_count)
cluster_redis.hset(user, 'user_friendsnum', friends_count)
retweeted_uid = str(item['root_uid'])
retweeted_mid = str(item['root_mid'])
message_type = int(item['message_type'])
mid = str(item['mid'])
timestamp = item['timestamp']
text = item['text']
sw_list = searchWord(text.encode('utf-8'))
sensitive_result = len(sw_list)
if sensitive_result:
ts = ts2datetime(timestamp).replace('-','')
map = {}
for w in sw_list:
word = "".join([chr(x) for x in w])
word = word.decode('utf-8')
if not map.__contains__(word):
map[word] = 1
else:
map[word] += 1
try:
sensitive_count_string = r_cluster.hget('sensitive_'+str(ts), str(uid))
sensitive_count_dict = json.loads(sensitive_count_string)
for word in map:
count = map[word]
if sensitive_count_dict.__contains__(word):
sensitive_count_dict[word] += count
else:
sensitive_count_dict[word] = count
r_cluster.hset('sensitive_'+str(ts), str(uid), json.dumps(sensitive_count_dict))
except:
r_cluster.hset('sensitive_'+str(ts), str(uid), json.dumps(map))
if message_type == 1:
cluster_redis.sadd('user_set', user)
if sensitive_result:
cluster_redis.hset('s_'+user, mid + '_origin_weibo_timestamp', timestamp)
else:
cluster_redis.hset(user, mid + '_origin_weibo_timestamp', timestamp)
elif message_type == 2: # comment weibo
cluster_redis.sadd('user_set', user)
if cluster_redis.sismember(user + '_comment_weibo', retweeted_mid) or cluster_redis.sismember('s_' + user + '_comment_weibo', retweeted_mid):
return
#RE = re.compile(u'//@([a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+):', re.UNICODE)
#nicknames = RE.findall(text)
if not sensitive_result:
cluster_redis.sadd(user + '_comment_weibo', retweeted_mid)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby(user, 'comment_weibo', 1)
if 1:
#if len(nicknames) == 0:
cluster_redis.hincrby(retweeted_uid, retweeted_mid + '_origin_weibo_comment', 1)
cluster_redis.hincrby(retweeted_uid, 'origin_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset(retweeted_uid, retweeted_mid + '_origin_weibo_comment_timestamp', timestamp)
"""
else:
nick_id_ = nicknames[0]
_id = single_redis.hget(NICK_UID_NAMESPACE, nick_id_)
print _id
single_redis.hset(ACTIVE_NICK_UID_NAMESPACE, nick_id_, _id)
if _id:
cluster_redis.hincrby(str(_id), retweeted_mid + '_retweeted_weibo_comment', 1)
cluster_redis.hincrby(str(_id), 'retweeted_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset(str(_id), retweeted_mid + '_retweeted_weibo_comment_timestamp', timestamp)
"""
else:
cluster_redis.sadd('s_' + user + '_comment_weibo', retweeted_mid)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby('s_'+user, 'comment_weibo', 1)
if 1:
#if len(nicknames) == 0:
cluster_redis.hincrby('s_' + retweeted_uid, retweeted_mid + '_origin_weibo_comment', 1)
cluster_redis.hincrby('s_' + retweeted_uid, 'origin_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset('s_' + retweeted_uid, retweeted_mid + '_origin_weibo_comment_timestamp', timestamp)
"""
else:
nick_id_ = nicknames[0]
_id = single_redis.hget(NICK_UID_NAMESPACE, nick_id_)
print _id
single_redis.hset(ACTIVE_NICK_UID_NAMESPACE, nick_id_, _id)
if _id:
cluster_redis.hincrby('s_' + str(_id), retweeted_mid + '_retweeted_weibo_comment', 1)
cluster_redis.hincrby('s_' + str(_id), 'retweeted_weibo_comment_timestamp_%s' % queue_index, 1)
cluster_redis.hset('s_' + str(_id), retweeted_mid + '_retweeted_weibo_comment_timestamp', timestamp)
"""
elif message_type == 3:
cluster_redis.sadd('user_set', user)
if cluster_redis.sismember(user + '_retweeted_weibo', retweeted_mid) or cluster_redis.sismember('s_' + user + '_retweeted_weibo', retweeted_mid):
return
"""
RE = re.compile(u'//@([a-zA-Z-_⺀-⺙⺛-⻳⼀-⿕々〇〡-〩〸-〺〻㐀-䶵一-鿃豈-鶴侮-頻並-龎]+):', re.UNICODE)
nicknames = RE.findall(text)
"""
if not sensitive_result:
cluster_redis.sadd(user + '_retweeted_weibo', retweeted_mid)
cluster_redis.hset(user, retweeted_mid + '_retweeted_weibo_timestamp', timestamp)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby(retweeted_uid, 'origin_weibo_retweeted_timestamp_%s' % queue_index, 1)
cluster_redis.hincrby(retweeted_uid, retweeted_mid + '_origin_weibo_retweeted', 1)
"""
if len(nicknames) != 0:
for nick_id in nicknames:
_id = single_redis.hget(NICK_UID_NAMESPACE, nick_id)
print _id
single_redis.hset(ACTIVE_NICK_UID_NAMESPACE, nick_id, _id)
if _id:
cluster_redis.hincrby(str(_id), retweeted_mid+'_retweeted_weibo_retweeted', 1)
cluster_redis.hset(str(_id), 'retweeted_weibo_retweeted_timestamp', timestamp)
cluster_redis.hincrby(str(_id), 'retweeted_weibo_retweeted_timestamp_%s' % queue_index, 1)
"""
else:
cluster_redis.sadd('s_' + user + '_retweeted_weibo', retweeted_mid)
cluster_redis.hset('s_' + user, retweeted_mid + '_retweeted_weibo_timestamp', timestamp)
queue_index = get_queue_index(timestamp)
cluster_redis.hincrby('s_' +retweeted_uid, 'origin_weibo_retweeted_timestamp_%s' %queue_index, 1)
cluster_redis.hincrby('s_' +retweeted_uid, retweeted_mid + '_origin_weibo_retweeted', 1)
"""