import csv
import time
import urllib.parse as parse
from selenium import webdriver
from pyquery import PyQuery as pq
from selenium.webdriver.common.by import By
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

driver = webdriver.Chrome()
driver.set_window_size(1920, 1200)
wait = WebDriverWait(driver, 10)


def login_zhihu(username, password):
    """登錄知乎
    :param username: 用戶(hù)名
    :param password: 密碼
    """
    try:
        login_url = 'https://www.zhihu.com/signin'
        driver.get(login_url)

        username_input = wait.until(EC.presence_of_element_located((By.XPATH,
                                                                    '//*[@id="root"]/div/main/div/div/div/div[2]/div[1]/form/div[1]/div[2]/div[1]/input')))
        username_input.send_keys(username)
        password_input = wait.until(EC.presence_of_element_located((By.XPATH,
                                                                    '//*[@id="root"]/div/main/div/div/div/div[2]/div[1]/form/div[2]/div/div[1]/input')))
        password_input.send_keys(password)

        # 等待20秒很泊，用于手動(dòng)輸入驗(yàn)證碼
        time.sleep(20)
        button = wait.until(EC.element_to_be_clickable((By.XPATH,
                                                        '//*[@id="root"]/div/main/div/div/div/div[2]/div[1]/form/button')))
        button.submit()

        # 等待Cookies加載# 等待Cookies加載
        time.sleep(10)
        cookies = driver.get_cookies()
        print(cookies)
    except Exception as e:
        print(e)
    finally:
        driver.close()


def topic_title_spider(keyword='王寶強(qiáng)', filename='wangbaoqiang', scroll_times=10):
    """ 獲取關(guān)鍵詞搜素下標(biāo)題和評(píng)論的數(shù)目
    :param keyword: 關(guān)鍵詞
    :param filename: 保存的文件名
    :param scroll_times: 頁(yè)面向下滾動(dòng)次數(shù)
    """
    start = time.time()

    # 建立一個(gè)收集數(shù)據(jù)的csv文件
    csvFile = open('./%s.csv' % filename, 'a+', newline='')
    writer = csv.writer(csvFile)
    writer.writerow(('title', 'review_num'))

    # 將關(guān)鍵詞轉(zhuǎn)換為十六進(jìn)制格式颇象，填入到鏈接中
    kw = parse.quote(keyword)
    url = 'https://www.zhihu.com/search?type=content&q=%s' % kw
    driver.get(url)

    # 加載盡可能多的頁(yè)面數(shù)據(jù)
    for i in range(1, scroll_times, 1):
        driver.execute_script('window.scrollTo(0, document.body.scrollHeight)')
        duration = time.time() - start
        print('%s -- 小爬蟲(chóng) 已經(jīng)向下滾動(dòng) 第%d次 了，運(yùn)行時(shí)間%.2f秒鸟废，好累啊!' % (keyword, i, duration))
        time.sleep(5)

    html = driver.page_source

    # 解析獲取所需內(nèi)容
    doc = pq(html)
    items = doc('.Card .List-item').items()
    count = 0
    for i, item in enumerate(items):
        button = item.find('.ContentItem-action')
        if button:
            try:
                review_num = button.text().split(' ')[-2]
                title = item.find('.ContentItem-title').text().replace('\r', '').replace('\n', '')
                writer.writerow((title, review_num))
                count += 1
                print('成功' + str(count) + '條佩微！')
                print(title, review_num)
                print()
            except Exception as e:
                print(e)
                continue

    csvFile.close()
    driver.quit()


if __name__ == '__main__':
    # login_zhihu('XXX', 'XXX')
    topic_title_spider(keyword='Python', filename='python', scroll_times=20)