def analyze_users_in_search_results(t, q, max_batches=5, count=100):
# Search for something
statuses = search(t, q=q, max_batches=max_batches, count=count)
# Extract the screen names from the results
# and optionally map them to a useful field like the tweet id
screen_name_to_tweet_ids = {}
screen_name_to_info = {}
screen_name_to_location = {}
for status in statuses:
screen_name = status['user']['screen_name']
if not screen_name_to_tweet_ids.has_key(screen_name):
screen_name_to_tweet_ids[screen_name] = []
screen_name_to_tweet_ids[screen_name] += [ status['id'] ]
screen_name_to_info[screen_name] = status['user']
screen_name_to_location[screen_name] = status['user']['location']
# Note that the "location" field can
# be anything a user has typed in, and may be something like "Everywhere",
# "United States" or something else that won't geocode to a specific coordinate
# on a map.
# Use the various screen_name_to{tweet_ids, info, location} maps to determine
# interesting things about the people who appear in the search results.
return screen_name_to_info, screen_name_to_location, screen_name_to_tweet_ids
def analyze_users_in_search_results(t, q, max_batches=5, count=100):
# Search for something
statuses = search(t, q=q, max_batches=max_batches, count=count)
# Extract the screen names from the results
# and optionally map them to a useful field like the tweet id
screen_name_to_tweet_ids = {}
screen_name_to_info = {}
screen_name_to_location = {}
for status in statuses:
screen_name = status['user']['screen_name']
if not screen_name_to_tweet_ids.has_key(screen_name):
screen_name_to_tweet_ids[screen_name] = []
screen_name_to_tweet_ids[screen_name] += [status['id']]
screen_name_to_info[screen_name] = status['user']
screen_name_to_location[screen_name] = status['user']['location']
# Note that the "location" field can
# be anything a user has typed in, and may be something like "Everywhere",
# "United States" or something else that won't geocode to a specific coordinate
# on a map.
# Use the various screen_name_to{tweet_ids, info, location} maps to determine
# interesting things about the people who appear in the search results.
return screen_name_to_info, screen_name_to_location, screen_name_to_tweet_ids
)
return g
if __name__ == '__main__':
# Your query
Q = ' '.join(sys.argv[1])
# How many batches of data to grab for the search results
MAX_BATCHES = 2
# How many search results per page
COUNT = 100
# Get some search results for a query
t = oauth_login()
search_results = search(t, q=Q, max_batches=MAX_BATCHES, count=COUNT)
g = create_rt_graph(search_results)
# Print out some stats
print >> sys.stderr, "Number nodes:", g.number_of_nodes()
print >> sys.stderr, "Num edges:", g.number_of_edges()
print >> sys.stderr, "Num connected components:", \
len(nx.connected_components(g.to_undirected()))
print >> sys.stderr, "Node degrees:", sorted(nx.degree(g))
)
return g
if __name__ == "__main__":
# Your query
Q = " ".join(sys.argv[1])
# How many batches of data to grab for the search results
MAX_BATCHES = 2
# How many search results per page
COUNT = 100
# Get some search results for a query
t = oauth_login()
search_results = search(t, q=Q, max_batches=MAX_BATCHES, count=COUNT)
g = create_rt_graph(search_results)
# Print out some stats
print >>sys.stderr, "Number nodes:", g.number_of_nodes()
print >>sys.stderr, "Num edges:", g.number_of_edges()
print >>sys.stderr, "Num connected components:", len(nx.connected_components(g.to_undirected()))
print >>sys.stderr, "Node degrees:", sorted(nx.degree(g))
# Inspect the tweet to see if was produced with /statuses/retweet/:id
# See http://dev.twitter.com/doc/post/statuses/retweet/:id
if tweet.has_key('retweeted_status'):
rt_origins += [ tweet['retweeted_status']['user']['screen_name'].lower() ]
# Also, inspect the tweet for the presence of "legacy" retweet
# patterns such as "RT" and "via"
try:
rt_origins += [
mention.strip()
for mention in rt_patterns.findall(tweet['text'])[0][1].split()
]
except IndexError, e:
pass
# Filter out any duplicates
return list(set([rto.strip("@").lower() for rto in rt_origins]))
if __name__ == '__main__':
t = oauth_login()
tweets = search(t, q='Python', max_batches=1, count=100)
for tweet in tweets:
print tweet['text'], get_rt_origins(tweet)
# -*- coding: utf-8 -*-
import json
from recipe__oauth_login import oauth_login
from recipe__search import search
def get_entities(tweet):
return tweet['entities']
if __name__ == '__main__':
t = oauth_login()
tweets = search(t, "Python", max_batches=1, count=10) # Use "Python" as a sample query to get some tweets to process
entities = [ get_entities(tweet) for tweet in tweets ]
print json.dumps(entities, indent=1)
# See http://dev.twitter.com/doc/post/statuses/retweet/:id
if tweet.has_key('retweeted_status'):
rt_origins += [
tweet['retweeted_status']['user']['screen_name'].lower()
]
# Also, inspect the tweet for the presence of "legacy" retweet
# patterns such as "RT" and "via"
try:
rt_origins += [
mention.strip()
for mention in rt_patterns.findall(tweet['text'])[0][1].split()
]
except IndexError, e:
pass
# Filter out any duplicates
return list(set([rto.strip("@").lower() for rto in rt_origins]))
if __name__ == '__main__':
t = oauth_login()
tweets = search(t, q='RKP1107', max_batches=1, count=100)
for tweet in tweets:
print tweet['text'], get_rt_origins(tweet)
# Extract geo coordinates from search results import sys import twitter from recipe__oauth_login import oauth_login from recipe__search import search Q = ' '.join(sys.argv[1:]) t = oauth_login() statuses = search(t, q=Q, max_batches=10, count=100) # Extract geocoordinates from tweets in search results coords = [ status['geo'] for status in statuses if status['geo'] is not None ] print coords
# Extract geo coordinates from search results import sys import twitter from recipe__oauth_login import oauth_login from recipe__search import search Q = ' '.join(sys.argv[1:]) t = oauth_login() statuses = search(t, q=Q, max_batches=10, count=100) # Extract geocoordinates from tweets in search results coords = [status['geo'] for status in statuses if status['geo'] is not None] print coords
# See http://dev.twitter.com/doc/post/statuses/retweet/:id
if tweet.has_key('retweeted_status'):
rt_origins += [
tweet['retweeted_status']['user']['screen_name'].lower()
]
# Also, inspect the tweet for the presence of "legacy" retweet
# patterns such as "RT" and "via"
try:
rt_origins += [
mention.strip()
for mention in rt_patterns.findall(tweet['text'])[0][1].split()
]
except IndexError, e:
pass
# Filter out any duplicates
return list(set([rto.strip("@").lower() for rto in rt_origins]))
if __name__ == '__main__':
t = oauth_login()
tweets = search(t, q='Python', max_batches=1, count=100)
for tweet in tweets:
print tweet['text'], get_rt_origins(tweet)
