kw_tools/website_clickjobs/n2nart/_clickjob.py

import time
from datetime import datetime as dt
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.support import expected_conditions as EC
import codecs
import random
import requests
import dataset
import traceback
import sys
from selenium.webdriver.common.keys import Keys
import timeit
import socket

db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
driver=None
headers = {
        "Authorization": "Bearer " + "t35vhZtWNgvDNWHc3DJh0OKll3mcB9GvC8K2EAkBug2",
        "Content-Type": "application/x-www-form-urlencoded"
}

sleepoffset = 0

def send_msg(kw):
    params = {"message": "處理關鍵字: "+kw}  
    r = requests.post("https://notify-api.line.me/api/notify",headers=headers, params=params)

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(urllist, query, client):
    sleepoffset = 0
    global driver
    driver.get('https://www.google.com?num=100')
    time.sleep(3)
    print(driver.current_url)

    # elmts=driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")a4bIc
    # ABOVE METHOD IS DEPRECATED STARTING SELENIUM 4.3.0, USE THIS
    #
    #elmt = driver.find_element(By.XPATH, "//input[@name='q']")
    elmt = driver.find_element(By.XPATH, "//textarea[@name='q']")
    time.sleep(1)

    elmt.send_keys(query)
    elmt.send_keys(Keys.ENTER)

    idx=1
    ranking=-1
    domain_in_link = 0

    googleurl = driver.current_url
    print(driver.current_url)

    if "sorry" in googleurl:
        return 444

    try: #in case there are duplicates...
        clickmore=driver.find_element("xpath","//p[@id='ofr']").find_element(By.TAG_NAME, "a")
        webdriver.ActionChains(driver).move_to_element(clickmore).perform()
        webdriver.ActionChains(driver).move_to_element(clickmore).click().perform()
    except:
        pass
    elmts=driver.find_elements("xpath","//div[@class='yuRUbf']/a")

    print (len(elmts))
    # driver.save_screenshot('c:/tmp/test.png')
    n=0
    clickcand=[]

    for el in elmts:
        n+=1
        #txt=el.text
        txt='aaaaaaaaaaa'
        href=el.get_attribute('href')
        if len(txt)>10:
            for url in urllist:
                if url in href:
                    clickcand.append([el,n])
                
    if len(clickcand)!=0:
        '''for e in clickcand:
            href = e[0].get_attribute('href')
            print(href)
            print(e[0].text)
            print("Rank: " + str(e[1]))
            db['sns_log'].insert({"kw": query, "ranking": e[1], "url": href, "dt": dt.now(), "client": client, "title": e[0].text, "results": n})'''

        e = random.choice(clickcand)  
        el = e[0]
        domain_in_link += 1
        print('clicked....')
        href = el.get_attribute('href')
        print(href)
        print(el.text)
        
        webdriver.ActionChains(driver).move_to_element(el).perform()
        webdriver.ActionChains(driver).move_to_element(el).click().perform()
        db['sns_log'].insert({"kw": query, "ranking": e[1], "url": href, "dt": dt.now(), "client": client, "title": el.text, "results": n})
        duration = random.randint(40,60)
        time.sleep(duration)

        print(domain_in_link)
        return 200

    return 0 # if no articles found
    
    

def run_once(url, query, client):
    global driver
    result=[]
    options = webdriver.ChromeOptions()
    options.add_argument('--headless')
#    options.add_argument("--user-agent=" +user_agent)
    options.add_argument("--incognito")
    options.add_argument('--no-sandbox')
    options.add_argument('--disable-dev-shm-usage')

    driver = webdriver.Chrome(
    options=options)

    driver.delete_all_cookies()
    driver.set_window_size(1400,1000)

    statuscode = process_query(url, query, client)
    driver.quit()

    return statuscode

#execution starts here

def execute(url, query, client):
    print("Ctrl+C or Ctrl+Z to stop.")
    statuscode = 0
    st = timeit.default_timer()
    try:
        statuscode = run_once(url, query, client)
    except:
        traceback.print_exc()
    timetaken = timeit.default_timer()-st
    print("Time taken: " + str(timetaken))
    
    print("Process returned with " + str(statuscode))
    if statuscode == 444:
        print("You have been caught!!!")
        
        #notify("Clickbot " + brands[domain] + " has been caught by Google and will terminate. IP: ")

    extrasleep = 0
    if(timetaken < 50):
        extrasleep = 50 - timetaken
    print("Ctrl+C or Ctrl+Z to stop now.")
    print("You have " + str(10 + extrasleep) + " seconds.")
    time.sleep(10 + extrasleep)
    return statuscode