kw_tools/SEO/news_clickbot.py

from random import randint
import sys
import os
import dataset
from selenium import webdriver
import traceback
import datetime
import codecs
import time
import urllib
import argparse
import schedule
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
import logging
import sys
from logging.handlers import SysLogHandler
import socket
import pandas as pd
import pymysql
pymysql.install_as_MySQLdb()

_LOG_SERVER = ('hhh.ptt.cx', 514)
logger = logging.getLogger('clickbot_100')
handler1 = SysLogHandler(address=_LOG_SERVER, socktype=socket.SOCK_DGRAM)
logger.addHandler(handler1)
logger.debug('[clickbot_100][火柴星人]begin')


path = 'C:\portable\chromedriver'
path_z = '/Users/zooeytsai/Downloads/chromedriver 4'


def restart_browser(pport):
    s = Service('/root/driver/chromedriver')
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    options.add_argument('--remote-debugging-port=9222')
    options.add_experimental_option("debuggerAddress", f"127.0.0.1:{pport}")
    options.add_argument("--user-agent=" + "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0")
    options.add_argument("--incognito")
    driver = webdriver.Chrome(options=options, service=s)
    driver.delete_all_cookies()
    driver.set_window_size(950, 20000)
    return driver


def process_one(pport):
    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
    lst = ['好睡王 引新聞','好睡王 Yahoo','好睡王 HiNet','好睡王 PCHOME','好睡王 蕃新聞','好睡王 新浪','好睡王 台北郵報','好睡王 LIFE','好睡王 match生活網','好睡王 POPDAILY','好睡王 LINE TODAY']
    table = db['news_log']

    for term in lst:
        print(term)
        logger.debug('[clickbot_100][' + term + ']')
        driver = restart_browser(pport)
        googleurl = 'https://www.google.com/?num=30'
        driver.get(googleurl)
        time.sleep(6)
        send_kw_elmt = driver.find_element(By.XPATH,'/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')
        send_kw_elmt.send_keys(term)
        time.sleep(3)
        send_kw_elmt.send_keys(Keys.ENTER)
        time.sleep(6)
        elmts = driver.find_elements(By.XPATH, "//div[@class='yuRUbf']/a")
        idx = 1
        print(len(elmts))
        for elmt in elmts:
            href = elmt.get_attribute('href')
            txt = elmt.text
            print(txt)
            if len(txt) > 10:
                if '炎炎夏日易輾轉難眠' in txt:
                    print("ranking", idx)
                    table.insert({'kw': term, 'ranking': idx, 'title': txt, 'url': href,
                                  'dt': datetime.datetime.now()})
                    print('clicked....')
                    webdriver.ActionChains(driver).move_to_element(elmt).perform()
                    webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
                    time.sleep(5)
                    break
            idx += 1
        
        
        driver.quit()
        print('中場休息')
        time.sleep(randint(90, 120))
    db.close()


while True:
    try:
        os.system('docker container restart tiny4')
        time.sleep(1)
        break
    except:
        os.system('docker container restart tiny4')
        time.sleep(15)

process_one('9925')

# parser = argparse.ArgumentParser()
# parser.add_argument('--loop', action="store_true")
# args = parser.parse_args()

# if args.loop:
#     schedule.every(0.4).minutes.do(process_one)
#     # print('今天開始')
#     # schedule.every().day.at('9:30').do(process_one)
#
#     while True:
#         schedule.run_pending()
#         time.sleep(1)

# >> C:\tmp\seo_line.txt 2>&1