本文整理汇总了Python中dataset.DataSet.output_tweet方法的典型用法代码示例。如果您正苦于以下问题：Python DataSet.output_tweet方法的具体用法？Python DataSet.output_tweet怎么用？Python DataSet.output_tweet使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类dataset.DataSet的用法示例。
在下文中一共展示了DataSet.output_tweet方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: TweetDB
# 需要导入模块: from dataset import DataSet [as 别名]
# 或者: from dataset.DataSet import output_tweet [as 别名]
class TweetDB():
def __init__(self):
conf = Configuration()
self.ptext = TextProcess(conf)
self.ds = DataSet(conf)
self.mongo = MongoDB(self.ds.db,self.ds.collection)
self.tweet=""
self.tokens = ""
self.i = 0
self.enable_translation = self.ptext.translation
self.translation_store = self.ptext.translation_store
def get_tweet_from_db(self):
where = {
"text":{"$exists":"true"},
"geo.coordinates":{"$exists":"true"}
}
select = {"text":1,"source":1,"geo":1, "user":1,"retweet_count":1,"created_at":1}
results = self.mongo.find(where,select)
return results
def process_tweets(self):
tweets = self.get_tweet_from_db()
for rawTweet in tweets:
if "text" in rawTweet:
tokens = {}
self.ptext.set_tweet_text(rawTweet['text'])
self.ptext.set_tweet_source(rawTweet['source'])
self.ptext.process_text()
rawTweet['source'] = self.ptext.get_tweet_source()
rawTweet['text'] = self.ptext.get_tweet_text()
self.tokens = self.ptext.get_tweet_tokens()
tokens['tokens'] = self.tokens
rawTweet.update(tokens)
self.tweet = self.cleaner.unset_tweet_keys(rawTweet)
if not self.ptext.get_translate_status():
self.ds.output_tweet(self.tweet)
self.i += 1
else:
if self.translation_store:
if self.enable_translation:
if not self.ptext.get_translate_failed():
self.ds.output_tweet(self.tweet)
self.i += 1
else:
self.ds.output_tweet(self.tweet)
self.i += 1
def get_tweet_count(self):
return self.i示例2: ProcessTweets
# 需要导入模块: from dataset import DataSet [as 别名]
# 或者: from dataset.DataSet import output_tweet [as 别名]
class ProcessTweets(Thread):
def __init__(self,conf,q):
self.ptext = TextProcess(conf)
self.ds = DataSet(conf)
self.cleaner = KeyCleaner()
self.enable_translation = self.ptext.translation
self.translation_store = self.ptext.translation_store
self.tweets = q # Tweets queue
self.tweet = ""
self.tokens = ""
self.i = 0
Thread.__init__(self)
def run(self):
while True:
rawTweet = self.tweets.get()
if "text" in rawTweet:
tokens = {}
self.ptext.set_tweet_text(rawTweet['text'])
self.ptext.set_tweet_source(rawTweet['source'])
self.ptext.process_text()
rawTweet['source'] = self.ptext.get_tweet_source()
rawTweet['text'] = self.ptext.get_tweet_text()
self.tokens = self.ptext.get_tweet_tokens()
tokens['tokens'] = self.tokens
rawTweet.update(tokens)
self.tweet = self.cleaner.unset_tweet_keys(rawTweet)
if not self.ptext.get_translate_status():
self.ds.output_tweet(self.tweet)
self.i += 1
else:
if self.translation_store:
if self.enable_translation:
if not self.ptext.get_translate_failed():
self.ds.output_tweet(self.tweet)
self.i += 1
else:
self.ds.output_tweet(self.tweet)
self.i += 1
self.tweets.task_done()
def get_tweet_count(self):
return self.i