kw_tools/SEO/ranking_day2.py

from random import randint
import sys
import dataset
from selenium import webdriver
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 pymysql

pymysql.install_as_MySQLdb()
import random
from selenium.webdriver.chrome.service import Service
import os
import fire

path = 'C:\portable\chromedriver'
path_z = '/Users/zooeytsai/Downloads/chromedriver 2'
driver = None
db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
lst = []
table = db['google_rank']


def rua():
    pool = [
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",
        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36 OPR/68.0.3618.125",
    ]
    return random.choice(pool)


def process_one(item):
    global driver
    term = item[0]
    domain = item[1]
    print(term, domain)
    
    escaped_search_term = urllib.parse.quote(term)
    googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(escaped_search_term, 100, 'zh-TW')
    print(googleurl)
    driver.get(googleurl)
    time.sleep(6)
    # fname=term.replace(' ','_')
    # driver.save_screenshot('c:/tmp/seo/'+fname+'.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))
            if domain in href:
                print(href)
                print(elmt.text)
                table.insert(
                    {'title': elmt.text, 'url': href, 'keyword': term, 'dt': datetime.datetime.now(), 'num': 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('/Users/zooeytsai/'+fname+".xls")
    
    driver.quit()
    print('中場休息')
    time.sleep(randint(90, 120))


def run_once(q):
    global driver
    result = []
    s = Service('/root/driver/chromedriver')
    user_agent = rua()
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    options.add_argument('--remote-debugging-port=9222')
    options.add_experimental_option("debuggerAddress", f"127.0.0.1:{q[2]}")
    options.add_argument("--user-agent=" + user_agent)
    options.add_argument("--incognito")
    
    driver = webdriver.Chrome(options=options, service=s)
    
    driver.delete_all_cookies()
    driver.set_window_size(1400, 1000)
    
    process_one(q)
    time.sleep(3)
    driver.quit()


class JParams(object):
    
    def get(self, kw, domain, port):
        print(kw)
        print(domain)
        run_once((kw, domain, port))


if __name__ == '__main__':
    fire.Fire(JParams)