# coding=utf-8
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

import itertools
import csv
import codecs
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
unicode('gbk', errors='ignore')

def crawl(url):
    chromedriverPath = "C:\Python27\Scripts\chromedriver.exe"

    # twitter includes 13 tweets every refresh
    eachCount = 13

    #scroll times
    #scrollTimes = 1

    #driver = webdriver.Chrome()
    driver = webdriver.Chrome(chromedriverPath)
    driver.get(url)

    try:
        for i in itertools.count():##range(scrollTimes):
            driver.execute_script("window.scrollTo(0, document.body.scrollHeight);")

            lastTweetCss = "#stream-items-id >li:nth-of-type(" + str(eachCount*(i+2)+1) + ") .tweet-text"
            print lastTweetCss
            elem = WebDriverWait(driver,20).until(EC.visibility_of_element_located((By.CSS_SELECTOR,lastTweetCss)))
            printTweet(driver)
    finally:
        driver.close()


def printTweet(driver):
    tweetCss = "[data-item-type=tweet]"
    nameCss = ".fullname"
    timeCss = "._timestamp"
    contentCss = ".tweet-text"

    items = driver.find_elements_by_css_selector(tweetCss)
    resultArr = []
    for i,item in enumerate(items):
        try:
            nameElem = item.find_element_by_css_selector(nameCss)
            timeElem = item.find_element_by_css_selector(timeCss)
            contentElem = item.find_element_by_css_selector(contentCss)

            name = nameElem.text
            time = timeElem.text
            content = contentElem.text

            resultArr.append([name,time,content])
            print("%d: name=%s time=%s content=%s" % (i,name,time,content))
        except Exception, e:
            pass
			#print("error index=%d" % (i))
            #print e

    printToCsv(resultArr)


def printToCsv(data):
    writer = csv.writer(codecs.open('result.csv','wb'))
    writer.writerow(['name','time','content'])

    for item in data:
        writer.writerow(item)


if __name__ == '__main__':
    url = "https://twitter.com/search?q=%23%24aapl%20lang%3Aen%20since%3A2015-12-30%20until%3A2016-01-01&src=typd"
    crawl(url)