new set

website_clickjobs/type-1/_clickjob0113.py

@@ -0,0 +1,162 @@
+import time
+from datetime import datetime
+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
+
+add_tabs = [7,9,11,13,15,7,9,11,13,15,7,9,11,13,15,7,9,11,13,15]
+
+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(domain, target_id, brands, query):
+    print(target_id)
+    sleepoffset = 0
+    global driver
+    if query == "艾立思" and "index" in target_id:
+        driver.get('https://www.google.com/search?num=1000&q=艾立思&rlz=1C1ONGR_zh-TWTW997TW997&ei=zjdUY_DBG9Lm-Abpgq84&start=0&sa=N&filter=0&ved=2ahUKEwjw4KeEvfT6AhVSM94KHWnBCwcQ8tMDegQIARAQ&cshid=1666463754367857&biw=1368&bih=761&dpr=2')
+        time.sleep(4)
+    else:
+        driver.get('https://www.google.com/search?q='+query+'&num=100&filter=0')
+        time.sleep(3)
+        print(driver.current_url)
+
+        # elmts=driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")
+        # ABOVE METHOD IS DEPRECATED STARTING SELENIUM 4.3.0, USE THIS
+        #
+        '''elmt = driver.find_element(By.XPATH, "//input[@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
+
+    elmts=driver.find_elements("xpath","//div[@class='yuRUbf']/a")
+
+    targets=[]
+    targets.append("https://hhh.com.tw/HHH_NEW/designers/index_designerList.php?cid=" + target_id)
+    targets.append("https://m.hhh.com.tw/HHH_NEW/designers/index_designerList.php?cid=" + target_id)
+    targets.append("https://www.hhh.com.tw/HHH_NEW/designers/index_designerList.php?cid=" + target_id)
+    targets.append("https://hhh.com.tw/HHH_NEW/designers_static/" + target_id + ".html")
+    targets.append("https://m.hhh.com.tw/HHH_NEW/designers_static/" + target_id + ".html")
+    targets.append("https://www.hhh.com.tw/HHH_NEW/designers_static/" + target_id + ".html")
+    
+    print (len(elmts))
+    # driver.save_screenshot('c:/tmp/test.png')
+    n=0
+    for el in elmts:
+        n+=1
+        href=el.get_attribute('href')
+        txt=el.text
+        if len(txt)>10:
+            for t in targets:
+                if t in href:
+                    domain_in_link += 1
+                    print('clicked....')
+                    print(href)
+                    print(txt)
+
+                    if query == "艾立思" and "index" in target_id and href != "https://hhh.com.tw/brand-index.php?brand_id=211":
+                        print("wrong site")
+                        continue
+                    
+                    webdriver.ActionChains(driver).move_to_element(el).perform()
+                    webdriver.ActionChains(driver).move_to_element(el).click().perform()
+                    print("Rank: " + str(n))
+                    time.sleep(15)
+
+                    print(domain_in_link)
+                    return 200
+    
+    with open("missing.txt", "a") as file:
+        file.write(target_id + " " + query + "\n")
+    
+    
+
+def run_once(domain, target_id, brands, query):
+    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(domain, target_id, brands, query)
+    driver.quit()
+
+    return statuscode
+
+#execution starts here
+
+def execute(domain, target_id, brands, target_name):
+    print("Ctrl+C or Ctrl+Z to stop.")
+    statuscode = 0
+    st = timeit.default_timer()
+    try:
+        statuscode = run_once(domain, target_id, brands, target_name)
+    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(30 + extrasleep) + " seconds.")
+    time.sleep(30 + extrasleep)
+    return statuscode

website_clickjobs/type-1/hhh_r3.py

@@ -0,0 +1,33 @@
+from _clickjob0113 import *
+
+hhhdb = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+ds=hhhdb.query('select * from hhh.hhh_designer_for_crawl')
+data=[]
+for i in ds:
+    for j in range(i['weight']):
+        data.append([i['hdesigner_id'],i['title'].replace('\xa0','')])
+random.shuffle(data)
+
+domain = 'hhh.com.tw'
+#target_domain = get_xml_data(sourceurls)
+brands={domain:'hhh'}
+#query_list = ['幸福空間']
+
+#data = getdata()
+
+runcount=0
+while True:
+        print("Run " + str(runcount+1))
+        target = random.choice(data) # START HERE
+        target_id = str(target[0])
+        target_name = target[1]
+        print(target_id)
+        print(target_name)
+        statuscode = execute(domain, target_id, brands, target_name)
+        if statuscode == 444:
+            print("Completed ", runcount, " times before being caught")
+            time.sleep(300)
+        else:
+            runcount+=1
+            time.sleep(40)
+time.sleep(60)