kw_tools/SEO/google_rank.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 pymysql
pymysql.install_as_MySQLdb()

driver = None


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

    global driver
    googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(urllib.parse.quote(q), 100, 'zh-TW')
    driver.get(googleurl)
    print(driver.current_url)
    time.sleep(6)

    elmts = driver.find_elements(By.XPATH, "//div[@class='yuRUbf']/a")

    idx = 1
    ranking = -1
    print(len(elmts))
    # driver.save_screenshot('C:\/Users\/s1301\/Pictures\/Saved Pictures\/')
    
    for elmt in elmts:
        href = elmt.get_attribute('href')
        txt = elmt.text
        table.insert({'title': elmt.text, 'url': href, 'keyword': q, 'dt': datetime.datetime.now(), 'ranking': idx})

        idx += 1
    db.close()

def run_once(q):
    global driver
    result = []
    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")

    driver = webdriver.Chrome(
        options=options, service=s)
    str1 = driver.capabilities['browserVersion']
    print('版本', str1)
    driver.delete_all_cookies()
    driver.set_window_size(1400, 1000)

    print(q)
    process_query(q)
    time.sleep(3)
    driver.quit()


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

lst = ['信義房仲','信義 房屋','信義 房仲','雙響泡']
for i in lst:
    run_once(i)