#!/usr/bin/env python                                                                                                                                             
# -*- coding:utf-8 -*-  
import json
from requests_oauthlib import OAuth1Session
from twitter import Twitter, OAuth
from janome.tokenizer import Tokenizer
import collections
import re
from collections import Counter, defaultdict
import sys, json, time, calendar
from datetime import datetime
from dateutil.relativedelta import relativedelta

#APIキーの設置
CONSUMER_KEY =  'YOURS'
CONSUMER_SECRET = 'YOURS'
ACCESS_TOKEN = 'YOURS'
ACCESS_SECRET = 'YOURS'

t = Twitter(auth=OAuth(
    ACCESS_TOKEN,
    ACCESS_SECRET,
    CONSUMER_KEY,
    CONSUMER_SECRET
))
    
twitter = OAuth1Session(CONSUMER_KEY, CONSUMER_SECRET, ACCESS_TOKEN, ACCESS_SECRET)
url = "https://api.twitter.com/1.1/search/tweets.json"
userTweets = []


def get_userstweets_again(screen_name, max_id):
    
    max_id = max_id
    count = 200 #一度のアクセスで何件取ってくるか
    aTimeLine = t.statuses.user_timeline(screen_name = screen_name, count=count, max_id=max_id)
    for tweet in aTimeLine:
        userTweets.append(tweet['text'])
            


def get_userstweets(screen_name):
    number_of_tweets = 0
    count = 200 #一度のアクセスで何件取ってくるか
    aTimeLine = t.statuses.user_timeline(screen_name = screen_name, count=count, include_rts='false',)
    for tweet in aTimeLine:
        number_of_tweets += 1
        userTweets.append(tweet['text'])
        if number_of_tweets >= 200:
            max_id = tweet["id"]
            print(max_id)
            get_userstweets_again(screen_name, max_id)

#検索したい相手を指定 
print("相性を調べたい相手のuser_idを入力してください")
target_user_id = input('>> ')
print('----------------------------------------------------')

get_userstweets(target_user_id)

print(userTweets)
print(len(userTweets))

# #複合語をつくる
from janome.tokenizer import Tokenizer
import collections
import re
import sys
import MeCab
import collections
import termextract.japanese_plaintext
import termextract.core

for text in userTweets:
    if "RT" in text:
        userTweets.remove(text)
        
texts = ','.join(userTweets)

texts=re.sub(r'https?://[\w/:%#\$&\?\(\)~\.=\+\-…]+', "", texts)
texts=re.sub('RT', "", texts)
texts=re.sub('お気に入り', "", texts)
texts=re.sub('まとめ', "", texts)
texts=re.sub(r'[!-~]', "", texts)#半角記号,数字,英字
texts=re.sub(r'[︰-＠]', "", texts)#全角記号
texts=re.sub('\n', "", texts)#改行文字

# 複合語を抽出し、重要度を算出
frequency = termextract.japanese_plaintext.cmp_noun_dict(texts)
LR = termextract.core.score_lr(frequency,
         ignore_words=termextract.japanese_plaintext.IGNORE_WORDS,
         lr_mode=1, average_rate=1
     )
term_imp = termextract.core.term_importance(frequency, LR)

# 重要度が高い順に並べ替えて出力
data_collection = collections.Counter(term_imp)
for cmp_noun, value in data_collection.most_common():
    print(termextract.core.modify_agglutinative_lang(cmp_noun), value, sep="\t")