restructure files

website_clickjobs/_clickjob.py

@@ -0,0 +1,143 @@
+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
+
+add_tabs = [0,0,1,2,0,3,4,0,1,2,0,3,4,0,1,2,0,3,4,0]
+
+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_domain, brands, query):
+    print(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)
+
+    elmts=driver.find_elements("xpath","//div[@class='yuRUbf']/a")
+
+    print (len(elmts))
+    # driver.save_screenshot('c:/tmp/test.png')
+
+    for el in elmts:
+        href=el.get_attribute('href')
+        txt=el.text
+        if len(txt)>10:
+            if domain 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()
+                time.sleep(6)
+
+                new_windows_count = add_tabs[random.randint(0,19)]
+                print(str(new_windows_count) + " new tabs")
+                for i in range (0,new_windows_count):
+                    original_window = driver.current_window_handle
+                    driver.switch_to.new_window('window')
+                    driver.get(href)
+                    sleepoffset += 4
+                    time.sleep(6)
+                    driver.close()
+                    driver.switch_to.window(original_window)
+
+                if domain in target_domain:
+                    print("Target link found")
+                    time_stamp = datetime.fromtimestamp(time.time())
+                    time_stamp = time_stamp.strftime("%Y-%m-%d %H:%M:%S")
+                    db['click_results'].insert({"time_stamp": time_stamp, "brand": brands[domain], "domain": domain, "query": query, "url": href, "content": txt, "extra_windows": new_windows_count})
+                break
+
+    if domain in target_domain:
+        print("Target domain found")
+        time_stamp = datetime.fromtimestamp(time.time())
+        time_stamp = time_stamp.strftime("%Y-%m-%d %H:%M:%S")
+        db['query_results'].insert({"time_stamp": time_stamp, "brand": brands[domain], "domain": domain, "query": query, "googleurl": googleurl, "element_count": len(elmts), "domain_in_link_count": domain_in_link})
+            
+
+    print(domain_in_link)
+    
+
+def run_once(domain, target_domain, 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)
+
+    process_query(domain, target_domain, brands, query)
+    time.sleep(3)
+    driver.quit()
+
+#execution starts here
+
+def execute(domain, target_domain, brands, query_list):
+    while True:
+        try:
+            run_once(domain, target_domain, brands, random.choice(query_list))
+        except:
+            traceback.print_exc()
+        sleepint=random.randint(75,110) - sleepoffset
+        print("Completed (" + str(sleepint) + ")")
+        time.sleep(sleepint)

website_clickjobs/bennis.py

@@ -0,0 +1,8 @@
+from _clickjob import *
+
+domain = 'bennis.com.tw'
+target_domain = ['bennis.com.tw']
+brands={domain:'班尼斯'}
+query_list = ('班尼斯', '乳膠 墊 推薦', '床 墊 訂 做 價格', '乳膠 床 推薦')
+
+execute(domain, target_domain, brands, query_list)

website_clickjobs/yogoclean.py

@@ -0,0 +1,8 @@
+from _clickjob import *
+
+domain = 'yogoclean.com'
+target_domain = ['yogoclean.com']
+brands={domain:'有夠讚'}
+query_list = ('有夠讚','有夠讚')
+
+execute(domain, target_domain, brands, query_list)