从 Twitter 抓取用户位置

This says only 100 user's information can be grabbed what is the better way to lift that limitation ?

代码:

import sys
import string
import simplejson
from twython import Twython
import csv
import pandas as pd

#WE WILL USE THE VARIABLES DAY, MONTH, AND YEAR FOR OUR OUTPUT FILE NAME
import datetime
now = datetime.datetime.now()
day=int(now.day)
month=int(now.month)
year=int(now.year)


#FOR OAUTH AUTHENTICATION -- NEEDED TO ACCESS THE TWITTER API
t = Twython(app_key='ABC', 
    app_secret='ABC',
    oauth_token='ABC',
    oauth_token_secret='ABC')

#INPUT HAS NO HEADER NO INDEX
ids = pd.read_csv('user_keyword.csv', header=['userName', 'userID', 'Date', 'Keyword'], usecols=['userName'])

#ACCESS THE LOOKUP_USER METHOD OF THE TWITTER API -- GRAB INFO ON UP TO 100 IDS WITH EACH API CALL

users = t.lookup_user(user_id = ids)

#NAME OUR OUTPUT FILE - %i WILL BE REPLACED BY CURRENT MONTH, DAY, AND YEAR
outfn = "twitter_user_data_%i.%i.%i.csv" % (now.month, now.day, now.year)

#NAMES FOR HEADER ROW IN OUTPUT FILE
fields = "id, screen_name, name, created_at, url, followers_count, friends_count, statuses_count, 
    favourites_count, listed_count, 
    contributors_enabled, description, protected, location, lang, expanded_url".split()

#INITIALIZE OUTPUT FILE AND WRITE HEADER ROW   
outfp = open(outfn, "w")
outfp.write(string.join(fields, "	") + "
")  # header

#THE VARIABLE 'USERS' CONTAINS INFORMATION OF THE 32 TWITTER USER IDS LISTED ABOVE
#THIS BLOCK WILL LOOP OVER EACH OF THESE IDS, CREATE VARIABLES, AND OUTPUT TO FILE
for entry in users:
    #CREATE EMPTY DICTIONARY
    r = {}
    for f in fields:
        r[f] = ""
    #ASSIGN VALUE OF 'ID' FIELD IN JSON TO 'ID' FIELD IN OUR DICTIONARY
    r['id'] = entry['id']
    #SAME WITH 'SCREEN_NAME' HERE, AND FOR REST OF THE VARIABLES
    r['screen_name'] = entry['screen_name']
    r['name'] = entry['name']
    r['created_at'] = entry['created_at']
    r['url'] = entry['url']
    r['followers_count'] = entry['followers_count']
    r['friends_count'] = entry['friends_count']
    r['statuses_count'] = entry['statuses_count']
    r['favourites_count'] = entry['favourites_count']
    r['listed_count'] = entry['listed_count']
    r['contributors_enabled'] = entry['contributors_enabled']
    r['description'] = entry['description']
    r['protected'] = entry['protected']
    r['location'] = entry['location']
    r['lang'] = entry['lang']
    #NOT EVERY ID WILL HAVE A 'URL' KEY, SO CHECK FOR ITS EXISTENCE WITH IF CLAUSE
    if 'url' in entry['entities']:
        r['expanded_url'] = entry['entities']['url']['urls'][0]['expanded_url']
    else:
        r['expanded_url'] = ''
    print r
    #CREATE EMPTY LIST
    lst = []
    #ADD DATA FOR EACH VARIABLE
    for f in fields:
        lst.append(unicode(r[f]).replace("/", "/"))
    #WRITE ROW WITH DATA IN LIST
    outfp.write(string.join(lst, "	").encode("utf-8") + "
")

outfp.close()    

错误:

File "user_profile_location.py", line 35, in <module>
    ids = pd.read_csv('user_keyword.csv', header=['userName', 'userID', 'Date', 'Keyword'], usecols=['userName'])
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 562, in parser_f
    return _read(filepath_or_buffer, kwds)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 315, in _read
    parser = TextFileReader(filepath_or_buffer, **kwds)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 645, in __init__
    self._make_engine(self.engine)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 799, in _make_engine
    self._engine = CParserWrapper(self.f, **self.options)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 1202, in __init__
    ParserBase.__init__(self, kwds)
  File "/usr/local/lib/python2.7/dist-packages/pandas/io/parsers.py", line 918, in __init__
    raise ValueError("cannot specify usecols when "
ValueError: cannot specify usecols when specifying a multi-index header

解决方案

假设您只想获取用户在他/她的个人资料页面中的位置，您可以使用 API.get_user 来自 Tweepy.下面是工作代码.

#!/usr/bin/env python
from __future__ import print_function

#Import the necessary methods from tweepy library
import tweepy
from tweepy import OAuthHandler


#user credentials to access Twitter API 
access_token = "your access token here"
access_token_secret = "your access token secret key here"
consumer_key = "your consumer key here"
consumer_secret = "your consumer secret key here"


def get_user_details(username):
        userobj = api.get_user(username)
        return userobj


if __name__ == '__main__':
    #authenticating the app (https://apps.twitter.com/)
    auth = tweepy.auth.OAuthHandler(consumer_key, consumer_secret)
    auth.set_access_token(access_token, access_token_secret)
    api = tweepy.API(auth)

    #for list of usernames, put them in iterable and call the function
    username = 'thinkgeek'
    userOBJ = get_user_details(username)
    print(userOBJ.location)