#!/usr/bin/python
# -*-coding:utf-8-*-
"""微信公众号历史文章获取"""
import asyncio
from pyppeteer import launch
import logging
from pyppeteer.errors import TimeoutError
import re
import common
# 插入数据库
import sys
import requests
import json
from pyppeteer_stealth import stealth
import qrcode
import zxing
import pandas as pd
import numpy as np
import time
import pymongo
import os
from bs4 import BeautifulSoup

try:
    mongo_collection = pymongo.MongoClient(os.getenv('MONGOD_HOST'), os.getenv(
        'MONGOD_PORT'))  # 如 mongodb://admin:123456@192.168.221.128:27017
    mongo_collection.server_info()
except Exception as e:
    print("数据库配置异常,请检查...")
    sys.exit()


# 下载图片
def downImg(url, path_name="IMG"):
    """
    下载图片到本地
    :param url: 图片数组
    :param path_name: 保存文件名
    :return:
    """
    import requests
    # 图片链接
    a = 0
    url_path = []
    for i in url:
        image_url = i
        print(image_url)
        a += 1
        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/96.0.4664.45 Safari/537.36'
        }
        r = requests.get(image_url, headers=headers)
        if not os.path.exists(str(path_name)):
            os.mkdir(str(path_name))
        # 下载图片
        with open(str(path_name) + "/" + str(a) + ".jpg", mode="wb") as f:
            f.write(r.content)  # 图片内容写入文件
        # /Users/wankaifa/穿搭图集
        url_path.append("/Users/wankaifa/穿搭图集/" + str(a) + ".jpg")
    # 返回图片路径
    return url_path


class Tencent:
    # 查询网站
    def __init__(self):
        # 登录成功后获取
        self.token = 0
        self.cookies = ''
        # 是否已登录
        self.is_login = 0
        self.keyword_url = "https://mp.weixin.qq.com/"
        self.user = "674514904@qq.com"
        self.pwd = "wkf674514904"
        mongo_db = mongo_collection['article']
        mongo_collection_model = mongo_db['man']
        # url_list = mongo_collection_model.find({"$or": [{"title": {'$regex': "发型"}},{"title": {'$regex': "穿搭"}},{"title": {'$regex': "搭配"}},{"title": {'$regex': "发型"}}]})
        url_list = mongo_collection_model.find({"$and": [{"title": {'$regex': "秋"}},{'new_img': None}]})
        # url_list_one = mongo_collection_model.find_one({"$and": [{"title": {'$regex': "早秋"}},{'new_img': None}]})
        # print(url_list_one)
        # 获取所有url
        url_arr = []
        self.title_arr = {}
        print(url_list)
        for url in url_list:
            print(url)
            url_arr.append(url['link'])
            self.title_arr[url['link']] = url['title']
        if len(url_arr)==0:
            print("数据为空...")
            sys.exit()
        # 将数组 list1 每 3 个切分一次
        list2 = common.list_split(url_arr, 2)
        for i in range(len(list2)):
            print(list2[i])
            # 开启
            self.sem = asyncio.Semaphore(2)  # 有界信号量（等待其中两个协程结束）
            # 遍历所需的网站
            tasks = [asyncio.ensure_future(self.main(new_total_url)) for new_total_url in list2[i]]
            asyncio.get_event_loop().run_until_complete(asyncio.wait(tasks))

    async def main(self, num):
        print(num)
        async with self.sem:
            browser = await launch(headless=True, userDataDir='./userdata', args=['--disable-infobars', '--no-sandbox'],
                                   dumpio=True)
            page = await browser.newPage()
            await stealth(page)  # <-- Here
            await page.goto(num)
            # print(await page.content())
            soup = BeautifulSoup(await page.content(), "html.parser")
            await browser.close()
            print(soup.select("#activity-name")[0].get_text())
            wxw_img = soup.select("#js_content")
            # 获取图片
            new_img = wxw_img[0].find_all("img")
            # 获取文章源码
            js_content = str(wxw_img[0])
            print(new_img)
            detail_url = []
            for img in new_img:
                detail_url.append(img.get('data-src'))
            print(detail_url)
            print(len(detail_url))
            url_path = downImg(detail_url, "../../../穿搭图集/" + self.title_arr[num])
            # 将内容保存到对应的数据
            mongo_db = mongo_collection['article']
            mongo_collection_model = mongo_db['man']
            ret2find = mongo_collection_model.find_one({"link": num})
            print(ret2find)
            mongo_collection_model.update_one({
                '_id': ret2find['_id']
            }, {
                '$set': {
                    'content': js_content,
                    'old_img': json.dumps(detail_url),
                    'new_img': json.dumps(url_path),
                }
            }, upsert=False)


# 测试打开
Tencent()