# encoding:utf-8

import hashlib
import re
import time
import random
import urllib
import urllib.request
import datetime
from ftplib import FTP
import pymysql
from pymysql.converters import escape_string
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from selenium.webdriver.common.by import By
from bs4 import BeautifulSoup

# 设置浏览器
options = Options()
options.add_experimental_option('debuggerAddress', '127.0.0.1:9222')
bro = webdriver.Chrome(options=options)

def shanlaji(content):
   content = re.sub('<span ></span>', "", content)
   content = re.sub('class="note-content"', "", content)
   content = re.sub('class=""', "", content)
   content = re.sub('target=""', "", content)
   content = re.sub('id="hash-tag"', "", content)
   content = re.sub('href=""', "", content)
   content = re.sub('class="title"', "", content)
   content = re.sub('class="desc"', "", content)
   content = re.sub('id="detail-desc"', "", content)
   content = re.sub('id="detail-title"', "", content)
   content = re.sub('data-v-.*?=""', "", content)
   # content = re.sub('data-.*?=".*?"', "", content)
   #data-v-104cd31e=""
   content = re.sub('label=".*?"', "", content)
   # content = re.sub('class=".*?"', "", content)
   # content = re.sub('powered-by=".*?"', "", content)
   # content = re.sub('id=".*?"', "", content)
   # id="showcomment"
   # class="weapp_text_link wx_tap_link js_wx_tap_highlight"
   # label="Powered by 135editor.com"
   # data-miniprogram-appid="wx1cf959f941c33f64"
   return (content)
# ftp上传达到紫田服务器
def ftp_img(wangzhan, bendi_file, md5_name):
   # print('上传img开始')
   today = datetime.date.today()
   today = str(today)
   f_img = FTP('111111', timeout=1100)
   f_img.login('ssd4', 'rAPDC6WzDf38YCjP')
   try:
       f_img.mkd(f'{wangzhan}')
   except Exception as err:
       pass
       # print(err)
   f_img.cwd(f'{wangzhan}')  # 上传路径
   try:
       f_img.mkd(f'{today}')
   except Exception as err:
       pass
       # print(err)
   f_img.cwd(f'{today}')  # 上传路径
   try:
       with open(bendi_file, 'rb') as file:
           f_img.storbinary('STOR %s' % md5_name, file)
   except:
       time.sleep(5)
       with open(bendi_file, 'rb') as file:
           f_img.storbinary('STOR %s' % md5_name, file)
   file.close()
   # print('上传img结束')
   f_img.quit()
   print('上传img成功')

def page():
   content=''

   # 连接数据库
   conn_weixin = pymysql.connect(
       host='42.333333333',
       user='2323322323',
       password='sWEms5TKewFtnfiC',
       database='232323',
       charset='utf8mb4', )
   cursor_weixin = conn_weixin.cursor(cursor=pymysql.cursors.DictCursor)

   # 随机找一个关键词
   sql = f'''select * from xiaohongshu_url where status=0  order by id desc limit 1 '''
   cursor_weixin.execute(sql)
   res = cursor_weixin.fetchone()
   while  not res :
       print('没有数据了，等待5秒钟后再次尝试')
       sql = f'''select * from xiaohongshu_url where status=0  order by id desc limit 1 '''
       cursor_weixin.execute(sql)
       res = cursor_weixin.fetchone()

   #print(res)
   url='https://www.xiaohongshu.com'+res['url'].replace('search_result','explore')
   #print(url)

   bro.get(url)
   #print(22222)
   #处理图片
   imgs=bro.find_elements(By.CLASS_NAME,'swiper-slide')
   img_urls=[]
   for img in imgs:
       style=img.get_attribute('style')
       #print(style)
       for i in style.split(";"):
           #print(i)
           if 'background-image' in i :
               img_url=i.split('"')[-2]
               #print('img_url:',img_url)
               img_urls.append(img_url)
   #print(img_urls)
   img_urls = list(set(img_urls))
   #print(img_urls)
   for img_url in img_urls:
       # print('img地址',src)
       opener = urllib.request.build_opener()
       opener.addheaders = [('User-Agent','Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/36.0.1941.0 Safari/537.36')]
       urllib.request.install_opener(opener)
       new_img_name = str(res['wangzhan_id']) + "_" + str(time.time() + random.randint(1, 100)).replace('.','') + '.webp'

       urllib.request.urlretrieve(img_url, new_img_name)
       with open(new_img_name, 'rb') as f:
           md5_name = str(res['wangzhan_id']) + "_" + hashlib.md5(f.read()).hexdigest() + '.webp'
       # 上传到机房
       ftp_img(res['wangzhan_id'], new_img_name, md5_name)
       today = datetime.date.today()
       today = str(today)
       content=content+f'''<p style="text-align: center;" ><img src='https://img.taotu.cn/ssd/ssd4/{res['wangzhan_id']}/{today}/{md5_name}' ></p> '''
       print('图片地址替换成功')
   #print('content1:',content)
   div1=bro.find_element(By.CLASS_NAME,'note-content')
   div1_bs= BeautifulSoup(div1.get_attribute('outerHTML'), "html.parser")
   for i in div1_bs.find_all(name='a',id='hash-tag'):
       i['href'] =''
       i['class']=''
       i['target']=''
   div1_bs.find(name='div',class_='bottom-container').extract()
   inner_imgs=div1_bs.find_all(name='img')
   for i in inner_imgs:
       i.extract()

   content=content+str(div1_bs)
   #print('content2:', content)
   content=shanlaji(content)
   #print('content3:', content)
   # rcgz
   if int(res['wangzhan_id'])==58:
       conn_wangzhan = pymysql.connect(
           # host='192.168.102.1',
           host='32222222',
           user='232332',
           password='3223',
           database='232332',
           charset='utf8mb4')
       cursor_wangzhan = conn_wangzhan.cursor(cursor=pymysql.cursors.DictCursor)
       sql = f'''insert into article (title,content,time,fid,zuozhe) values("{escape_string(res['title'])}","{escape_string(shanlaji(str(content)))}","{int(time.time())}","{res['fid']}","{'小红书_'+res['gzh']}")'''
       cursor_wangzhan.execute(sql)
       conn_wangzhan.commit()
       print('■■■■■■■■■■■■■■■■■■■■■■■■■■ rcgz 插入数据库成功')
       sql = f'''update xiaohongshu_url set status= 1 where id ={res['id']}'''
       cursor_weixin.execute(sql)
       conn_weixin.commit()
       print('更新状态成功')
       conn_wangzhan.close()
       cursor_wangzhan.close()
   cursor_weixin.close()
   conn_weixin.close()
   #print('over')
while 1 > 0:
   page()
   time.sleep(8)