我正在尝试下载带位置的推文。我可以很好地下载它们,但我也希望将#keywords
和@Mentions
过滤到一个单独的列以及其他列。
代码:
import tweepy
from tweepy import Stream
from tweepy import OAuthHandler
from tweepy.streaming import StreamListener
import pandas as pd
import json
import csv
import sys
import time
reload(sys)
sys.setdefaultencoding('utf8')
ckey = 'abc'
csecret = 'abc'
atoken = 'abc'
asecret = 'abc'
OAUTH_KEYS = {'consumer_key':ckey, 'consumer_secret':csecret, 'access_token_key':atoken, 'access_token_secret':asecret}
auth = tweepy.OAuthHandler(OAUTH_KEYS['consumer_key'], OAUTH_KEYS['consumer_secret'])
api = tweepy.API(auth, wait_on_rate_limit=True, wait_on_rate_limit_notify=True)
if (not api):
print ("Can't Authenticate")
sys.exit(-1)
else:
print " Scraping data now" # Enter lat and long and radius in Kms q='hello'
cursor = tweepy.Cursor(api.search,geocode="40.712784,-74.005941,1000km",since='2016-07-10',until='2016-07-11',lang='en',count=100)
results=[]
for item in cursor.items(10000): # Remove the limit to 1000
results.append(item)
def toDataFrame(tweets):
# COnvert to data frame
DataSet = pd.DataFrame()
DataSet['tweetID'] = [tweet.id for tweet in tweets]
DataSet['tweetText'] = [tweet.text.encode('utf-8') for tweet in tweets]
DataSet['tweetRetweetCt'] = [tweet.retweet_count for tweet in tweets]
DataSet['tweetFavoriteCt'] = [tweet.favorite_count for tweet in tweets]
DataSet['tweetSource'] = [tweet.source for tweet in tweets]
DataSet['tweetCreated'] = [tweet.created_at for tweet in tweets]
DataSet['userID'] = [tweet.user.id for tweet in tweets]
DataSet['userScreen'] = [tweet.user.screen_name for tweet in tweets]
DataSet['userName'] = [tweet.user.name for tweet in tweets]
DataSet['userCreateDt'] = [tweet.user.created_at for tweet in tweets]
DataSet['userDesc'] = [tweet.user.description for tweet in tweets]
DataSet['userFollowerCt'] = [tweet.user.followers_count for tweet in tweets]
DataSet['userFriendsCt'] = [tweet.user.friends_count for tweet in tweets]
DataSet['userLocation'] = [tweet.user.location for tweet in tweets]
DataSet['userTimezone'] = [tweet.user.time_zone for tweet in tweets]
DataSet['Coordinates'] = [tweet.coordinates for tweet in tweets]
DataSet['GeoEnabled'] = [tweet.user.geo_enabled for tweet in tweets]
DataSet['Language'] = [tweet.user.lang for tweet in tweets]
tweets_place= []
#users_retweeted = []
for tweet in tweets:
if tweet.place:
tweets_place.append(tweet.place.full_name)
else:
tweets_place.append('null')
DataSet['TweetPlace'] = [i for i in tweets_place]
#DataSet['UserWhoRetweeted'] = [i for i in users_retweeted]
return DataSet
DataSet = toDataFrame(results)
DataSet.to_csv('NewYork_10_07.csv',index=False)
print "Download Completed"
上面的代码适用于使用Lat-long创建漏洞的推文但是如何将语句包含在过滤tweetText
中的关键字和提及到两个单独的列中?