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

"""
1.爬取淘寶美食的流程
- 搜索關(guān)鍵字: 用selenium打開瀏覽器,模擬輸入關(guān)鍵字,并搜索對應(yīng)的商品列表.
- 分析頁碼并翻頁,模擬翻頁,查看到所有頁面的商品列表.
- 分析并提取商品,利用Pyquery分析源碼,解析得到商品列表.
- 存儲到MONGODB數(shù)據(jù)庫,將商品列表信息存儲到mongoDB數(shù)據(jù)庫.
"""
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
from pyquery import PyQuery as pq
import re
from anli.mongoconfig import *
import pymongo

client = pymongo.MongoClient(MONGO_URL)
db = client[MONGO_DB]

#設(shè)置×××面訪問
opt = webdriver.FirefoxOptions()
opt.set_headless()
browser = webdriver.Firefox(options=opt)

#等待瀏覽器加載頁面成功.
wait = WebDriverWait(browser,10)

def search():
  try:
    # 后臺打開瀏覽器
    browser.get('https://www.taobao.com')

    # 用CSS選擇器復(fù)制搜索框
    input = wait.until(
      EC.presence_of_element_located((By.CSS_SELECTOR, '#q'))
    )

    # 找到搜索按鈕.
    submit = wait.until(
      # EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm .search-button')))
      EC.element_to_be_clickable((By.CSS_SELECTOR,'#J_TSearchForm > div.search-button > button')))

    # 輸入關(guān)鍵字
    input.send_keys('美食')

    # 點(diǎn)擊搜索按鈕.
    submit.click()

    # 輸出總共的頁數(shù).
    total=wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'.total')))

    # 調(diào)取商品列表的函數(shù).
    get_products()
    return total.text
  except TimeoutException: #超時錯誤.
    return search()

# 翻頁
def next_page(page_number):
  try:
    #注意在firefox和chrome瀏覽器復(fù)制出來的元素不太一樣.
    #要傳入的頁碼: 到第幾頁
    input = wait.until(
      EC.presence_of_element_located((By.CSS_SELECTOR,'input.input:nth-child(2)'))
    )
    #復(fù)制確定按鈕的元素:
    submit = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'span.btn:nth-child(4)')))

    #清除頁碼
    input.clear()
    #輸入當(dāng)前頁碼
    input.send_keys(page_number)

    #點(diǎn)擊確定按鈕.
    submit.click()

    #判斷當(dāng)前頁碼是否是當(dāng)前數(shù)字: 復(fù)制高亮頁碼數(shù).
    wait.until(EC.text_to_be_present_in_element((By.CSS_SELECTOR,'span.num'),str(page_number)))
    get_products()
  except TimeoutException:
    next_page(page_number)

#解析jquery源碼
def get_products():
  #商品列表:
  wait.until(EC.presence_of_element_located((By.CSS_SELECTOR,'#mainsrp-itemlist .items .item')))

  # 獲取網(wǎng)頁源碼
  html = browser.page_source
  doc = pq(html)
  items = doc('#mainsrp-itemlist .items .item').items()
  for item in items:
    #定義商品列表詳細(xì)信息的字典
    product = {
      'title': item.find('.title').text(),
      'price': item.find('.price').text(),
      'image': item.find('.pic .img').attr('src'),
      'shop': item.find('.shop').text(),
      'deal': item.find('.deal-cnt').text()[:-3],
      'location': item.find('.location').text()
    }
    print(product)
    #將商品列表信息保存到mongoDB數(shù)據(jù)庫.
    save_to_mongo(product)

def save_to_mongo(result):
  try:
    if db[MONGO_TABLE].insert(result):
      print('存儲到mongodb成功',result)
  except Exception:
    print('存儲到mongodb失敗',result)

def main():
  total = search()

  # 用正則表達(dá)式只匹配出數(shù)字,并打印數(shù)字.
  total = int(re.compile('(\d+)').search(total).group(1))
  print(total)
  for i in range(2,total + 1):
    next_page(i)

if __name__=='__main__':
  main()
  #關(guān)閉×××面瀏覽器.
  browser.quit()
#mongoconfig.py
#!/usr/bin/env python
# -*- coding:utf-8 -*-

MONGO_URL = 'localhost'
MONGO_DB = 'taobao'
MONGO_TABLE = 'meishi'