spider_douyin/detail.py

from selenium import webdriver
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.common.by import By
from time import sleep
import time
import json
import auth
import requests
import main


# webdriver 下载地址:http://chromedriver.storage.googleapis.com/index.html
# 放置于：把文件存放在python根目录下，例如：C:\xxx\Python\Python38下

def get_detail(url_login, url_detail):
    options = webdriver.ChromeOptions()
    options.add_experimental_option('excludeSwitches', ['enable-automation'])
    # options.add_argument(r'--headless')
    #     # options.add_argument(r'user-data-dir=C:\Users\Administrator\AppData\Local\Google\Chrome')
    #     # options.add_argument('--disable-gpu')

    browser = webdriver.Chrome(options=options)

    try:
        wait = WebDriverWait(browser, 15)
        browser.maximize_window()
        browser.implicitly_wait(3)  # 设置等待3秒后打开目标网页
        browser.implicitly_wait(3)

        # 登录页面
        browser.get(url=url_login)
        auth.add_cookie(browser)

        # 进入数据详情页
        browser.get(url_detail)
        sleep(10)
        if not auth.check_login(browser):
            print('登录失败')
            send_wechat_info("抖音线索登录失败")
            return

        # 进入数据详情页
        # browser.get(url_detail)

        sleep(5)
        while True:
            if time.localtime().tm_hour == 0:  # 这个时间点停止
                break
            # 切换线索推荐tab 为了刷新
            click_sales_clue_push(browser)
            sleep(5 * 60)  # 停止5分钟
            # click_sales_clue_list(browser)
            browser.get(url_detail)

            # 抓取数据
            # get_table(browser)
            click_page(browser)
            # 退出前更新一次cookie
            auth.record_cookie(browser)

            sleep(60 * 60*2)  # 停止5分钟

        browser.quit()
    except Exception as e:
        print('err_detail')
        print(e)
        browser.quit()
    return


# 1:姓名,2:电话,3:线索创建时间,4:互动类型,5:线索类型,6:最新互动记录,7:线索渠道,8:来源抖音号,9:分配状态
# 10:自动定位城市,11:手动填写地域,12:通话状态,13:最近互动时间,14:来源抖音号类型
key_dic = {1: "name", 2: "phone", 3: "create_time", 4: "status_interact", 5: "status_clue",
           6: "new_interact", 7: "clue_channel", 8: "from_douyin", 9: "status_distribution",
           10: "city", 11: "city_hand", 12: "status_call", 13: "last_time", 14: "from"}


# 点击线索推送
def click_sales_clue_push(browser):
   print("点击线索推荐")
   try:
       browser.find_element(By.ID, "PSalesCluePush").click()
   except:
       print("没有找到线索管理tab")

   sleep(5)


# 点击线索管理
def click_sales_clue_list(browser):
    browser.find_element(By.ID, "PSalesClueList").click()
    print("点击线索管理")
    sleep(5)


# 判断是否需要分页
def click_page(browser):
    page_items = browser.find_elements(By.CLASS_NAME, "leads-pager-item")
    num = len(page_items)
    if num <= 3:
        print("只有1页")
        get_table(browser)
        return

    for page in range(1, num - 3):
        page_items[num - 1].click()
        sleep(10)
        get_table(browser)


# 读取数据
def get_table(browser):
    # tr html的结构如下示例：
    # <tr>
    #   <td>name</td> <td>phone</td>...
    # </tr>'

    tr_list = browser.find_elements(By.CLASS_NAME, "listTableRow")
    for tr in tr_list:
        tds = tr.find_elements(By.TAG_NAME, "td")
        data = {}
        for i in range(1, len(key_dic)):
            data[key_dic[i]] = tds[i].text

        # 给服务器传数据
        send_data(data)


# 发送数据
def send_data(data):
    print(data)
    headers = {'Content-Type': 'application/json'}
    response = requests.post(url=main.URL_SEND_DATA, headers=headers, data=json.dumps(data))
    print(response)
    return ''


# 发送企业微信消息
def send_wechat_info(message):
    print(message)
    data = {
        "msgtype": "text",
        "text": {
            "content": message
        }
    }
    headers = {'Content-Type': 'application/json'}
    response = requests.post(url=main.URL_SEND_WECHAT_INFO, headers=headers, data=json.dumps(data))
    print(response)
    return ''

#

if __name__ == "__main__":
    print(time.localtime().tm_hour)
    # send_wechat_info("测试消息")