I'm trying to take every open tweets in a hashtag but my code does not go further than 299 tweets.
I also trying to take tweets from a specific time line like tweets only in May 2015 and July 2016. Are there any way to do it in the main process or should I write a little code for it?
Here is my code:
# if this is the first time, creates a new array which
# will store max id of the tweets for each keyword
if not os.path.isfile("max_ids.npy"):
max_ids = np.empty(len(keywords))
# every value is initialized as -1 in order to start from the beginning the first time program run
max_ids.fill(-1)
else:
max_ids = np.load("max_ids.npy") # loads the previous max ids
# if there is any new keywords added, extends the max_ids array in order to correspond every keyword
if len(keywords) > len(max_ids):
new_indexes = np.empty(len(keywords) - len(max_ids))
new_indexes.fill(-1)
max_ids = np.append(arr=max_ids, values=new_indexes)
count = 0
for i in range(len(keywords)):
since_date="2015-01-01"
sinceId = None
tweetCount = 0
maxTweets = 5000000000000000000000 # maximum tweets to find per keyword
tweetsPerQry = 100
searchQuery = "#{0}".format(keywords[i])
while tweetCount < maxTweets:
if max_ids[i] < 0:
if (not sinceId):
new_tweets = api.search(q=searchQuery, count=tweetsPerQry)
else:
new_tweets = api.search(q=searchQuery, count=tweetsPerQry,
since_id=sinceId)
else:
if (not sinceId):
new_tweets = api.search(q=searchQuery, count=tweetsPerQry,
max_id=str(max_ids - 1))
else:
new_tweets = api.search(q=searchQuery, count=tweetsPerQry,
max_id=str(max_ids - 1),
since_id=sinceId)
if not new_tweets:
print("Keyword: {0} No more tweets found".format(searchQuery))
break
for tweet in new_tweets:
count += 1
print(count)
file_write.write(
.
.
.
)
item = {
.
.
.
.
.
}
# instead of using mongo's id for _id, using tweet's id
raw_data = tweet._json
raw_data["_id"] = tweet.id
raw_data.pop("id", None)
try:
db["Tweets"].insert_one(item)
except pymongo.errors.DuplicateKeyError as e:
print("Already exists in 'Tweets' collection.")
try:
db["RawTweets"].insert_one(raw_data)
except pymongo.errors.DuplicateKeyError as e:
print("Already exists in 'RawTweets' collection.")
tweetCount += len(new_tweets)
print("Downloaded {0} tweets".format(tweetCount))
max_ids[i] = new_tweets[-1].id
np.save(arr=max_ids, file="max_ids.npy") # saving in order to continue mining from where left next time program run
Sorry, I can't answer in comment, too long. :)
Sure :) Check this example: Advanced searched for #data keyword 2015 may - 2016 july Got this url: https://twitter.com/search?l=&q=%23data%20since%3A2015-05-01%20until%3A2016-07-31&src=typd
session = requests.session()
keyword = 'data'
date1 = '2015-05-01'
date2 = '2016-07-31'
session.get('https://twitter.com/search?l=&q=%23+keyword+%20since%3A+date1+%20until%3A+date2&src=typd', streaming = True)
Now we have all the requested tweets, Probably you could have problems with 'pagination' Pagination url ->
Probably you could put a random tweet id, or you can parse first, or requests some data from twitter. It can be done.
Use Chrome's networking tab to find all the requested information :)