kw_tools/SEO/general_gsrack.py

import time
import json
from selenium import webdriver
from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
import time
import os
import urllib.parse
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.support import expected_conditions as EC
import codecs
import random
import requests
import datetime
import dataset
import time
import traceback
import sys
import fire
import random
import pymysql

pymysql.install_as_MySQLdb()

db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
table = db['general_log']

driver = None


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 empty_query(q):
    global driver
    googleurl = 'https://www.google.com/search?q=' + urllib.parse.quote(q)
    driver.get(googleurl)
    time.sleep(3)


def process_query(qs):
    q = qs[0]
    domain = qs[1]
    global driver
    googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(urllib.parse.quote(q), 100, 'zh-TW')
    print(googleurl)
    driver.get(googleurl)
    time.sleep(6)
    
    while True:
        try:
            elmts = driver.find_elements(By.XPATH, "//div[@class='yuRUbf']/a")
            print('尋找')
            break
        except:
            pass
    
    idx = 1
    ranking = -1
    print('搜尋結果數量', len(elmts))
    #    driver.save_screenshot('c:/tmp/test.png')
    
    for elmt in elmts:
        
        href = elmt.get_attribute('href')
        txt = elmt.text
        if len(txt) > 10:
            if domain in href:
                print('clicked....')
                print(href)
                print(txt)
                print("ranking", idx)
                table.insert({'kw': q, 'domain': domain, 'ranking': idx, 'title': txt, 'url': href,
                              'dt': datetime.datetime.now(), 'num': 1})
                webdriver.ActionChains(driver).move_to_element(elmt).perform()
                webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
                break
        idx += 1


def run_once(q):
    global driver
    result = []
    s = Service('/root/driver/chromedriver')
    # s = Service('/Users/zooeytsai/Downloads/chromedriver 2')
    user_agent = rua()
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
    options.add_argument('--remote-debugging-port=9222')
    options.add_experimental_option("debuggerAddress", "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)
    
    print('到此')
    process_query(q)
    time.sleep(3)
    driver.quit()


# for c in lst:
# while True:
#    try:
#        c=random.choice(lst)
#    except:
#        traceback.print_exc()
#    sleepint=random.randint(320,520)
#    time.sleep(sleepint)

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


if __name__ == '__main__':
    fire.Fire(JParams)
    
    
    def get(self, kw, domain, port):
        print('kw')
        print(domain)
        run_once((kw, domain, port))