databasebased

website_clickjobs/type-GD/_clickjob.py

@@ -0,0 +1,146 @@
+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
+
+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(url, query):
+    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")
+    # 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
+
+    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
+    for el in elmts:
+        n+=1
+        href=el.get_attribute('href')
+        txt=el.text
+        if len(txt)>10:
+            if url in href:
+                domain_in_link += 1
+                print('clicked....')
+                print(href)
+                print(txt)
+                
+                webdriver.ActionChains(driver).move_to_element(el).perform()
+                webdriver.ActionChains(driver).move_to_element(el).click().perform()
+                print("Rank: " + str(n))
+                duration = random.randint(40,60)
+                time.sleep(duration)
+
+                print(domain_in_link)
+                return 200
+    
+    
+
+def run_once(url, 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(url, query)
+    driver.quit()
+
+    return statuscode
+
+#execution starts here
+
+def execute(url, query):
+    print("Ctrl+C or Ctrl+Z to stop.")
+    statuscode = 0
+    st = timeit.default_timer()
+    try:
+        statuscode = run_once(url, query)
+    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

website_clickjobs/type-GD/icons.py

@@ -0,0 +1,44 @@
+from _clickjob import *
+
+db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+
+def reset():
+    ds=db.query('select * from seo.seo_articles where cust="The Icons"')
+    #TAG ABOVE AND UNTAG BELOW FOR DEBUG
+    #ds=hhhdb.query('select * from seo.seo_articles where cust=')
+    data=[]
+    for i in ds:
+        for j in range(i['weight']):
+            data.append([i['kw'].replace('\xa0',' '),i['cust'].replace('\xa0',' '),i['url']])
+    random.shuffle(data)
+    return data
+
+#data = getdata()
+
+runcount=0
+while True:
+    try:
+        print("Gathering data...")
+        data = reset()
+        print('Data collected')
+        dataok = 1
+    except:
+        dataok = 0
+        print("Error while collecting data.")
+    if dataok == 1:
+        for i in range(10):
+            print("Run " + str(runcount+1))
+            target = random.choice(data) # START HERE
+            target_kw = target[0]
+            target_url = target[2]
+            print(target_kw)
+            print(target_url)
+            statuscode = execute(target_url, target_kw)
+            if statuscode == 444:
+                print("Completed ", runcount, " times before being caught")
+                time.sleep(300)
+            else:
+                runcount+=1
+                time.sleep(40)
+    else:
+        time.sleep(60)

website_clickjobs/type-GD/update.py

@@ -0,0 +1,17 @@
+import dataset
+import os
+import json
+
+db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+table=db['seo_articles']
+
+kw = "strong generation"
+cust = "The Icons"
+url = "http://finance.yahoo.com/news/strong-generation-revolution-starting-taiwan-102000191.html"
+weight = 1
+
+print(kw,cust,url)
+if kw != "" and cust != "" and url != "":
+    table.insert({'kw':kw,'cust':cust,'url':url,'weight':weight})
+else:
+    print("Empty data")