kw_tools/SEO/clickbot_100_one.py

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

driver = None
def restart_browser():
    global driver
    user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
    s = Service('C:\/Users\/s1301\/Downloads\/chromedriver_107\/chromedriver')
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    # options.add_argument('--remote-debugging-port=9222')
    # options.add_experimental_option("debuggerAddress", "192.168.192.45:9922")
    options.add_argument("--user-agent=" + user_agent)
    options.add_argument("--incognito")
    # options.add_argument('--proxy-server=socks5://172.104.93.163:41800')
    driver = webdriver.Chrome(options=options, service=s)

    str1 = driver.capabilities['browserVersion']
    driver.delete_all_cookies()
    driver.set_window_size(1400, 20000)
    return driver

def process_one():
    lst=['護佳國際']
    date='1209'
    for term in lst:
        driver=restart_browser()
        escaped_search_term=urllib.parse.quote(term)
        googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(escaped_search_term, 100,'zh-TW')
        driver.get(googleurl)
        time.sleep(6)
        print(driver.current_url)

        driver.save_screenshot('C:\/Users\/s1301\/Pictures\/Saved Pictures\/'+date+term+'.png')
        df=pd.DataFrame()
        elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']/a")
        cnt=1
        datadict={'搜尋詞':[],'結果標題':[],'結果網址':[],'結果名次':[]}

        for elmt in elmts:
            try:
                href=elmt.get_attribute('href')
                datadict['搜尋詞'].append(term)
                datadict['結果標題'].append(elmt.text)
                datadict['結果網址'].append(href)
                datadict['結果名次'].append(str(cnt))

                cnt+=1
            except:
                print('href2 exception')
                traceback.print_exc()

        if len(datadict['結果標題'])<=0:
            print('None')
            driver.quit()
            sys.exit()
        df['搜尋詞']=datadict['搜尋詞']
        df['結果標題']=datadict['結果標題']
        df['結果網址']=datadict['結果網址']
        df['結果名次']=datadict['結果名次']

        df.to_excel('C:\/Users\/s1301\/Pictures\/Saved Pictures\/'+date+term+".xls")

        driver.quit()
        print('等待')
        time.sleep(random.randint(100,120))
process_one()


os.system('docker container stop tiny8')
time.sleep(3)
os.system('docker container rm tiny8')
time.sleep(3)
os.system('docker run -d -p 9924:9222 --rm --shm-size="900m" --name tiny1 chromedp/headless-shell')
time.sleep(3)