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('/Users/mac/Downloads/127/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=['信義房屋','信義 房屋','信義房仲','信義 房仲']
    # lst=["驊揚室內裝修設計","驊揚室內裝修設計 評論"]
    # lst=['真理大學','真理大學停招','真理大學倒閉','真理大學評價','真理大學倒閉dcard']
    # lst = ['百威旅行社','百威旅遊','百威旅行']
    # lst = ['信義 房屋']
    # lst = ['加百裕工業股份有限公司','加百裕','黃靖容']
    # lst = ['富玉珠寶','富玉珠寶有限公司']
    # lst = ['台北牙周病醫生推薦 ','微創水雷射','水雷射牙周病']
    # lst = ['真理大學 site:ptt.cc','真理大學 site:dcard.tw']
    # lst = ['高雄 全 戶 軟水','高雄 淨水器推薦','淨水系統 高雄']
    # lst = ['啟翔輕金屬','啟翔','陳百欽']
    date='0731'

    for term in lst:
        driver=restart_browser()
        escaped_search_term=urllib.parse.quote(term)
        # googleurl = 'https://www.google.com/search?q={}&num={}&hl={}&gl=tw'.format(escaped_search_term, 100,'zh-TW')
        googleurl = 'https://www.google.com/search?q={}&num={}&hl={}&gl=tw&tbm=vid&tbs=vd:m'.format(urllib.parse.quote(term), 100, 'zh-TW')

        driver.get(googleurl)
        time.sleep(6)
        print(driver.current_url)

        # driver.save_screenshot('/Users/mac/Downloads/'+date+term+'.png')
        driver.save_screenshot('/Users/mac/Downloads/'+date+term+"_vi"+'.png')
        df=pd.DataFrame()
        # elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']//a")
        elmts=driver.find_elements(By.XPATH,"//div[@class='xe8e1b']//a")
        print(len(elmts))
        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_csv('/Users/mac/Downloads/'+date+term+".csv", encoding='utf-8')
        df.to_csv('/Users/mac/Downloads/'+date+term+"_vi"+".csv")

        driver.quit()
        print('等待')
        time.sleep(random.randint(80,90))

process_one()