import json
import re
from bs4 import BeautifulSoup
from selenium import webdriver
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC

browser = webdriver.Chrome()
# 瀏覽器需要多次使用，所以單獨(dú)拿出來(lái)。設(shè)置一個(gè)最長(zhǎng)的等待時(shí)間,等待目標(biāo)加載完成
wait = WebDriverWait(browser, 10)


def search(keyword):
 # wait容易出現(xiàn)加載時(shí)間長(zhǎng)的問(wèn)題，因此用try來(lái)捕捉異常
 try:
 browser.get('https://www.taobao.com')
 # 加載需要一定時(shí)間的，設(shè)置了等待時(shí)間，等待加載
 # 輸入按鈕的加載等待
 input = wait.until(
  # 設(shè)置加載目標(biāo)，它是一個(gè)選擇器，參數(shù)是需要選擇方式和等待加載的內(nèi)容
  EC.presence_of_element_located((By.CSS_SELECTOR, "#q")) # 選擇CSS選擇器和選擇內(nèi)容
 )
 # 提交按鈕
 submit = wait.until(
  # EC后面是選擇條件，按鈕的加載條件最好的是element_to_be_clickable，意思為元素可以點(diǎn)擊的
  EC.element_to_be_clickable((By.CSS_SELECTOR, "#J_TSearchForm > div.search-button > button"))
 )
 input.send_keys(keyword) # send_keys對(duì)輸入框輸入內(nèi)容
 submit.click() # 提交搜索內(nèi)容，進(jìn)入下一個(gè)頁(yè)面
 # 等待頁(yè)碼元素加載完成，并返回最大頁(yè)碼數(shù)
 total = wait.until(
  EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.total"))
 )
 # 等待加載完成后獲取信息
 get_products()
 return total.text
 except TimeoutException:
 # 超時(shí)后重新請(qǐng)求，因此遞歸調(diào)用
 return search()


def next_page(page_number):
 try:
 # 頁(yè)碼輸入框和翻頁(yè)按鈕
 input = wait.until(
  EC.presence_of_element_located((By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > input"))
 )
 # 提交按鈕
 submit = wait.until(
  EC.element_to_be_clickable(
  (By.CSS_SELECTOR, "#mainsrp-pager > div > div > div > div.form > span.btn.J_Submit"))
 )
 input.clear()
 input.send_keys(page_number)
 submit.click()
 # 判斷翻頁(yè)成功
 wait.until(
  EC.text_to_be_present_in_element((By.CSS_SELECTOR,
      '#mainsrp-pager > div > div > div > ul > li.item.active > span'),
      str(page_number)))
 get_products()
 except TimeoutException:
 return next_page(page_number)


def get_products():
 # 判斷單個(gè)頁(yè)面是否被加載出來(lái)
 wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#mainsrp-itemlist .items .item')))
 html = browser.page_source # 獲取頁(yè)面源代碼，所有的
 # 使用BS進(jìn)行分析
 soup = BeautifulSoup(html, 'lxml')
 items = soup.select('#mainsrp-itemlist .items .item')
 for item in items:
 image = item.select('.pic .img')[0]['data-src']
 price = item.select('.price strong')[0].text
 deal = item.select('.deal-cnt')[0].text[:-3]
 title = item.select('.title')[0].text.strip()
 shop = item.select('.shop')[0].text.strip()
 location = item.select('.location')[0].text
 product = {
  'image': image,
  'price': price,
  'deal': deal,
  'title': title,
  'shop': shop,
  'location': location
 }
 save_text(product) # 下載內(nèi)容


def save_text(product):
 # 保存為txt文件，a追加寫(xiě)模式，編碼模式utf-8
 with open('text.txt', 'a', encoding='utf-8') as f:
 # 使用JSON把字典轉(zhuǎn)換為str格式，加換行符
 f.write(json.dumps(product, ensure_ascii=False) + '\n')
 f.close()


def main():
 # 通過(guò)關(guān)鍵字在淘寶進(jìn)行搜索
 total = search('美食')
 # 用正則提取頁(yè)碼數(shù)字
 total = int(re.compile('(\d+)').search(total).group(1))
 # 翻頁(yè)
 for i in range(2, total+1): # 循環(huán)包含前，不包含尾
 next_page(i)
 browser.close()


if __name__ == '__main__':
 main()