twitter data #programming

gistfile1.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

'''ハッシュタグ#programmngからStatusListを受け取りファイルへテキストを保存する

1,「#programming」を条件にデータを取得
2,「, . ( ) 」をスペースに置換
3,小文字に変換
#4,スペースで文字を分割
#5,文字が#で始まっていたら#を削除
'''

import twitter
import re

def convert(text):
    text = text.encode('utf-8')
    text = re.sub(r'[,\.\(\)]',' ', text)
    text = text.lower()
    return text

def writeFile(searchList, fo):
    for i in xrange(1, len(searchList)):
	text = convert(searchList[i].text)
	fo.write(text + '\n')
    fo.close()

def getTimeLine(LANG = "en", SEARCH_WORD = "#programming",
		per_page = 100,start_page = 1, end_page = 51):
    api = twitter.Api()
    for i in xrange(start_page,end_page):
	searchList = api.GetSearch(
	    SEARCH_WORD, per_page=per_page, page=i, lang=LANG)
	fileName = './tmp/'+ LANG + str(i)
	f = open(fileName, 'w')
	writeFile(searchList, f)
	
if __name__ == "__main__":
    getTimeLine()