#import redis 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.support import expected_conditions as EC import codecs import random import requests import time import sys import docker import codecs import random import os import time driver=None headers = { "Authorization": "Bearer " + "t35vhZtWNgvDNWHc3DJh0OKll3mcB9GvC8K2EAkBug2", "Content-Type": "application/x-www-form-urlencoded" } 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(qs): q=qs[0] domain=qs[2] cnt=qs[1] global driver googleurl='https://www.google.com/search?q='+urllib.parse.quote(q) driver.get(googleurl) time.sleep(3) if cnt > 0: for i in range(cnt): elmt=driver.find_element_by_xpath("//a[@id='pnnext']") webdriver.ActionChains(driver).move_to_element(elmt).perform() webdriver.ActionChains(driver).move_to_element(elmt).click().perform() time.sleep(3) elmts=driver.find_elements_by_xpath("//div[@class='g']//div[@class='yuRUbf']//a") idx=1 ranking=-1 for elmt in elmts: href=elmt.get_attribute('href') txt=elmt.text if len(txt)>10: # if 'hhh.com.tw' in href: # if 'hhh.com.tw' in href: # if 'ai.choozmo.com' in href: if domain in href: # if 'searchome.net' in href: webdriver.ActionChains(driver).move_to_element(elmt).perform() webdriver.ActionChains(driver).move_to_element(elmt).click().perform() break def re_get_webdriver(): global driver result=[] client = docker.from_env() ls=client.containers.list() print(ls) for l in ls: if 'p6666' in l.name: ls[0].restart() time.sleep(4) # options = webdriver.EdgeOptions() try: driver = webdriver.Remote( command_executor='http://127.0.0.1:6666/wd/hub') driver.set_window_size(1400,1000) return except: driver=None return None driver=None def run_once(url): global driver i=random.randint(0,20) if i<=3 or driver is None: # if True: re_get_webdriver() if driver is None: return driver.execute_script('window.open("'+url+'","_blank");') # driver.get(url) driver.execute_script("window.scrollTo(0, window.scrollY + 400)") time.sleep(1) fpath=__file__ # fpath=fpath.replace('hhh_click_selenium.py','cases.csv') fpath=fpath.replace('hhh_666_edges.py','urls.csv') print(fpath) lst=[] fr=codecs.open(fpath,'r','utf-8') lines=fr.readlines() for l in lines: elmts=l.split(',') lst.append('https://www.hhh.com.tw'+elmts[0]) fr.close() #lst=['https://www.hhh.com.tw/columns/detail/3427/index.php'] #for i in range(20): while True: l=random.choice(lst) print(l) # driver.get(l) run_once(l) # time.sleep(2)