from datetime import datetime
import random
import csv
from concurrent.futures import ThreadPoolExecutor, as_completed

from lxml import etree
import pymysql
import requests

from models import create_session, Comments

#隨機(jī)UA
USERAGENT = [
  'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/14.0.835.163 Safari/535.1',
  'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36',
  'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0) Gecko/20100101 Firefox/6.0',
  'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50',
  'Opera/9.80 (Windows NT 6.1; U; zh-cn) Presto/2.9.168 Version/11.50',
  'Mozilla/5.0 (Windows; U; Windows NT 6.1; ) AppleWebKit/534.12 (KHTML, like Gecko) Maxthon/3.0 Safari/534.12'
]


class CommentFetcher:
  headers = {'User-Agent': ''}
  cookie = ''
  cookies = {'cookie': cookie}
  # cookie為登錄后的cookie，需要自行復(fù)制
  base_node = '//div[@class="comment-item"]'


  def __init__(self, movie_id, start, type=''):
    '''
    :type: 全部評(píng)論：''， 好評(píng)：h 中評(píng)：m 差評(píng)：l
    :movie_id: 影片的ID號(hào)
    :start: 開(kāi)始的記錄數(shù)，0-480
    '''
    self.movie_id = movie_id
    self.start = start
    self.type = type
    self.url = 'https://movie.douban.com/subject/{id}/comments?start={start}&limit=20&sort=new_score\&status=P&percent_type={type}&comments_only=1'.format(
      id=str(self.movie_id),
      start=str(self.start),
      type=self.type
    )
    #創(chuàng)建數(shù)據(jù)庫(kù)連接
    self.session = create_session()

  #隨機(jī)useragent
  def _random_UA(self):
    self.headers['User-Agent'] = random.choice(USERAGENT)


  #獲取api接口，使用get方法，返回的數(shù)據(jù)為json數(shù)據(jù)，需要提取里面的HTML
  def _get(self):
    self._random_UA()
    res = ''
    try:
      res = requests.get(self.url, cookies=self.cookies, headers=self.headers)
      res = res.json()['html']
    except Exception as e:
      print('IP被封，請(qǐng)使用代理IP')
    print('正在獲取{} 開(kāi)始的記錄'.format(self.start))
    return res

  def _parse(self):
    res = self._get()
    dom = etree.HTML(res)

    #id號(hào)
    self.id = dom.xpath(self.base_node + '/@data-cid')
    #用戶(hù)名
    self.username = dom.xpath(self.base_node + '/div[@class="avatar"]/a/@title')
    #用戶(hù)連接
    self.user_center = dom.xpath(self.base_node + '/div[@class="avatar"]/a/@href')
    #點(diǎn)贊數(shù)
    self.vote = dom.xpath(self.base_node + '//span[@class="votes"]/text()')
    #星級(jí)
    self.star = dom.xpath(self.base_node + '//span[contains(@class,"rating")]/@title')
    #發(fā)表時(shí)間
    self.time = dom.xpath(self.base_node + '//span[@class="comment-time "]/@title')
    #評(píng)論內(nèi)容 所有span標(biāo)簽class名為short的節(jié)點(diǎn)文本
    self.content = dom.xpath(self.base_node + '//span[@class="short"]/text()')

  #保存到數(shù)據(jù)庫(kù)
  def save_to_database(self):
    self._parse()
    for i in range(len(self.id)):
      try:
        comment = Comments(
          id=int(self.id[i]),
          username=self.username[i],
          user_center=self.user_center[i],
          vote=int(self.vote[i]),
          star=self.star[i],
          time=datetime.strptime(self.time[i], '%Y-%m-%d %H:%M:%S'),
          content=self.content[i]
        )

        self.session.add(comment)
        self.session.commit()
        return 'finish'


      except pymysql.err.IntegrityError as e:
        print('數(shù)據(jù)重復(fù)，不做任何處理')

      except Exception as e:
        #數(shù)據(jù)添加錯(cuò)誤，回滾
        self.session.rollback()

      finally:
        #關(guān)閉數(shù)據(jù)庫(kù)連接
        self.session.close()

  #保存到csv
  def save_to_csv(self):
    self._parse()
    f = open('comment.csv', 'w', encoding='utf-8')
    csv_in = csv.writer(f, dialect='excel')
    for i in range(len(self.id)):
      csv_in.writerow([
        int(self.id[i]),
        self.username[i],
        self.user_center[i],
        int(self.vote[i]),
        self.time[i],
        self.content[i]
      ])
    f.close()


if __name__ == '__main__':
  with ThreadPoolExecutor(max_workers=4) as executor:
    futures = []
    for i in ['', 'h', 'm', 'l']:
      for j in range(25):
        fetcher = CommentFetcher(movie_id=26266893, start=j * 20, type=i)
        futures.append(executor.submit(fetcher.save_to_csv))

    for f in as_completed(futures):
      try:
        res = f.done()
        if res:
          ret_data = f.result()
          if ret_data == 'finish':
            print('{} 成功保存數(shù)據(jù)'.format(str(f)))
      except Exception as e:
        f.cancel()