kw_tools/SEO/new_100.py

import random
import sys
import dataset
from selenium import webdriver
import traceback
import datetime
import codecs
import time
import urllib
import argparse
import schedule

import logging
import sys
from logging.handlers import SysLogHandler
import socket
import pandas as pd
import socket
import os
_LOG_SERVER = ('hhh.ptt.cx', 514)
logger = logging.getLogger('clickbot_100')
handler1 = SysLogHandler(address=_LOG_SERVER,socktype=socket.SOCK_DGRAM)
logger.addHandler(handler1)
#logger.debug('[clickbot_100][清原]begin')

hname=socket.gethostname()
pid=str(os.getpid())
logger.fatal('[clickbot_100]['+hname+']['+pid+']begin')


def restart_browser():
    options = webdriver.ChromeOptions()
    options.add_argument('--headless') 
    driver=webdriver.Chrome(options=options)
    driver.set_window_size(950,6000)
    return driver


def process_one():
    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
    lst=[]
    table=db['google_rank']
    cursor = db.query('select term from seo.selected_kw')
    # cursor=db.query('select term from selected_kw and term not in (SELECT distinct(keyword) FROM ig_tags.save_result where url like "%beastparadise.net%" and datediff(now(),dt)=0)')
    for c in cursor:
        lst.append(c['term'])

    term=random.choice(lst)
    print(term)
    logger.debug('[clickbot_100]['+term+']')
    driver=restart_browser()
    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()
    # driver.get_screenshot_as_file("/Users/zooeytsai/排名100.png")
    elmts=driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")

    clickelmt=None
    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')
            if 'taroboba-yuan.com' in href:
                clickelmt=elmt
                logger.debug('[clickbot_100]['+term+']['+str(cnt)+']')

            print(href)
            print(elmt.text)
            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))

            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 clickelmt:
        webdriver.ActionChains(driver).move_to_element(clickelmt).perform()
        webdriver.ActionChains(driver).move_to_element(clickelmt).click().perform()
    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")
    df.to_excel('c:/tmp/'+fname+".xls")

    driver.quit()

process_one()

parser = argparse.ArgumentParser()
parser.add_argument('--loop')
args = parser.parse_args()

if args.loop:

#    schedule.every(6).minutes.do(process_one)
    schedule.every(0.4).minutes.do(process_one)

    while True:
        schedule.run_pending()
        time.sleep(1)