Merge branch 'master' of http://git.choozmo.com:3000/choozmo/kw_tools

INNNews/general_clickbot.py

@@ -82,19 +82,20 @@ def process_query(qs):
     for elmt in elmts:
         href=elmt.get_attribute('href')
         txt=elmt.text
-        if len(txt)>10:
-            if domain in href:
-                print('clicked....')
-                print('點擊網址',href)
-                print('標題',txt)
-                print("ranking", idx)
-                table.insert({'kw':q,'domain':domain,'ranking':idx,'title':txt,'url':href,'dt':datetime.datetime.now()})
-                webdriver.ActionChains(driver).move_to_element(elmt).perform()
-                webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
-                time.sleep(5)
-                break
+        if domain in href:
+            print('clicked....')
+            print('點擊網址',href)
+            print('標題',txt)
+            print("ranking", idx)
+            table.insert({'kw':q,'domain':domain,'ranking':idx,'title':txt,'url':href,'dt':datetime.datetime.now()})
+            webdriver.ActionChains(driver).move_to_element(elmt).perform()
+            webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
+            time.sleep(5)
+            break
         idx+=1
     db.close()
+    driver.quit()
+
 def run_once(q):
     global driver
     result=[]
@@ -115,7 +116,6 @@ def run_once(q):
 
     process_query(q)
     time.sleep(3)
-    driver.quit()
 
 
 #for c in lst:

INNNews/general_clickbot_3.py

@@ -0,0 +1,133 @@
+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.chrome.service import Service
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.support import expected_conditions as EC
+import codecs
+import random
+import requests
+import datetime
+import dataset
+import time
+import traceback
+import sys
+import fire
+import redis
+
+driver = None
+
+
+def process_query(qs):
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    table = db['general_log']
+    q = qs[0]
+    domain = qs[1]
+    global driver
+    googleurl = 'https://www.google.com/?num=100'
+    driver.get(googleurl)
+    time.sleep(6)
+    send_kw_elmt = WebDriverWait(driver, 10).until(EC.presence_of_element_located(
+        (By.XPATH, '/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')))
+    send_kw_elmt.send_keys(q)
+    time.sleep(3)
+    send_kw_elmt.send_keys(Keys.ENTER)
+    time.sleep(6)
+    print(driver.current_url)
+    elmts = driver.find_elements(By.XPATH, "//div[@class='yuRUbf']/a")
+    
+    idx = 1
+    ranking = -1
+    print('網頁數量', len(elmts))
+    #    driver.save_screenshot('c:/tmp/test.png')
+    if 'site' in q:
+        href = elmts[0].get_attribute('href')
+        txt = elmts[0].text
+        print('clicked....')
+        print(href)
+        print(txt)
+        print("ranking", idx)
+        table.insert(
+            {'kw': q, 'domain': domain, 'ranking': idx, 'title': txt, 'url': href, 'dt': datetime.datetime.now()})
+        webdriver.ActionChains(driver).move_to_element(elmts[0]).perform()
+        time.sleep(3)
+        webdriver.ActionChains(driver).move_to_element(elmts[0]).click().perform()
+        time.sleep(5)
+    else:
+        for elmt in elmts:
+            href = elmt.get_attribute('href')
+            txt = elmt.text
+            if len(txt) > 10:
+                if domain in href:
+                    print('clicked....')
+                    print('點擊網址', href)
+                    print('標題', txt)
+                    print("ranking", idx)
+                    webdriver.ActionChains(driver).move_to_element(elmt).perform()
+                    time.sleep(3)
+                    webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
+                    table.insert({'kw': q, 'domain': domain, 'ranking': idx, 'title': txt, 'url': href,'dt': datetime.datetime.now()})
+                    time.sleep(5)
+                    break
+            idx += 1
+    db.close()
+    print('資料庫關閉')
+    driver.quit()
+
+
+def run_once(q):
+    global driver
+    s = Service('/root/driver/chromedriver')
+    options = webdriver.ChromeOptions()
+    options.add_argument("--no-sandbox")
+    options.add_argument("--disable-dev-shm-usage")
+    options.add_argument('--headless')
+    # options.add_argument('--remote-debugging-port=9222')
+    # options.add_experimental_option("debuggerAddress", f"127.0.0.1:{q[2]}")
+    # options.add_argument("--user-agent=" +user_agent)
+    options.add_argument("--incognito")
+    r = redis.Redis(host='db.ptt.cx', port=6379, db=2, password='choozmo9')
+    data = r.get('google_proxy')
+    jstext = data.decode('utf-8')
+    jsobj = json.loads(jstext)
+    # print('Free proxy',jsobj)
+    proxy = random.choice(jsobj)
+    i5 = "--proxy-server=socks5://172.104.93.163:41800"
+    change_ip_list = ['--proxy-server=%s' % proxy, "--proxy-server=socks5://127.0.0.1:9050",
+                      "--proxy-server=socks5://192.53.174.202:8180"]
+    change_ip = random.choice(change_ip_list)
+    options.add_argument(i5)
+    # print('使用代理ip',change_ip)
+    
+    driver = webdriver.Chrome(options=options, service=s)
+    
+    driver.delete_all_cookies()
+    driver.set_window_size(1400, 1000)
+    
+    process_query(q)
+
+
+# for c in lst:
+# while True:
+#    try:
+#        c=random.choice(lst)
+#    except:
+#        traceback.print_exc()
+#    sleepint=random.randint(320,520)
+#    time.sleep(sleepint)
+
+class JParams(object):
+    
+    def get(self, kw, domain):
+        run_once((kw, domain))
+
+
+if __name__ == '__main__':
+    fire.Fire(JParams)
+

INNNews/general_clickbot_proxy.py

@@ -25,26 +25,6 @@ import redis
 driver = None
 
 
-def rua():
-    pool = [
-        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0",
-        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0",
-        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
-        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36",
-        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
-        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",
-        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36 OPR/68.0.3618.125",
-    ]
-    return random.choice(pool)
-
-
-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):
     db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
     table=db['general_log']
@@ -54,12 +34,12 @@ def process_query(qs):
     googleurl = 'https://www.google.com/?num=100'
     driver.get(googleurl)
     time.sleep(6)
-    send_kw_elmt = driver.find_element(By.XPATH, '/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')
+    send_kw_elmt = WebDriverWait(driver,10).until(EC.presence_of_element_located((By.XPATH, '/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')))
     send_kw_elmt.send_keys(q)
     time.sleep(3)
     send_kw_elmt.send_keys(Keys.ENTER)
     time.sleep(6)
-
+    print(driver.current_url)
     elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']/a")
 
     idx=1
@@ -76,55 +56,57 @@ def process_query(qs):
         table.insert(
             {'kw': q, 'domain': domain, 'ranking': idx, 'title': txt, 'url': href, 'dt': datetime.datetime.now()})
         webdriver.ActionChains(driver).move_to_element(elmts[0]).perform()
+        time.sleep(3)
         webdriver.ActionChains(driver).move_to_element(elmts[0]).click().perform()
         time.sleep(5)
-    for elmt in elmts:
-        href=elmt.get_attribute('href')
-        txt=elmt.text
-        if len(txt)>10:
-            if domain in href:
-                print('clicked....')
-                print('點擊網址',href)
-                print('標題',txt)
-                print("ranking", idx)
-                table.insert({'kw':q,'domain':domain,'ranking':idx,'title':txt,'url':href,'dt':datetime.datetime.now()})
-                webdriver.ActionChains(driver).move_to_element(elmt).perform()
-                webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
-                time.sleep(5)
-                break
-        idx+=1
+    else:
+        for elmt in elmts:
+            href=elmt.get_attribute('href')
+            txt=elmt.text
+            if len(txt)>10:
+                if domain in href:
+                    print('clicked....')
+                    print('點擊網址',href)
+                    print('標題',txt)
+                    print("ranking", idx)
+                    webdriver.ActionChains(driver).move_to_element(elmt).perform()
+                    time.sleep(3)
+                    webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
+                    table.insert({'kw':q,'domain':domain,'ranking':idx,'title':txt,'url':href,'dt':datetime.datetime.now()})
+                    time.sleep(5)
+                    break
+            idx+=1
     db.close()
+    print('資料庫關閉')
+    driver.quit()
+
 def run_once(q):
     global driver
-    result=[]
     s = Service('/root/driver/chromedriver')
-    user_agent = rua()
     options = webdriver.ChromeOptions()
     options.add_argument('--headless')
     options.add_argument('--remote-debugging-port=9222')
-    options.add_experimental_option("debuggerAddress", f"127.0.0.1:{q[2]}")
+    options.add_experimental_option("debuggerAddress",f"127.0.0.1:{q[2]}")
     # options.add_argument("--user-agent=" +user_agent)
     options.add_argument("--incognito")
-    if 'sorry' in driver.current_url:
-        r = redis.Redis(host='db.ptt.cx', port=6379, db=2,password='choozmo9')
-        data=r.get('google_proxy')
-        jstext=data.decode('utf-8')
-        jsobj=json.loads(jstext)
-        print('Free proxy',jsobj)
-        proxy=random.choice(jsobj)
-        change_ip_list = ['--proxy-server=%s' % proxy,"--proxy-server=socks5://127.0.0.1:9050","--proxy-server=socks5://192.53.174.202:8180"]
-        change_ip = random.choice(change_ip_list)
-        options.add_argument(change_ip)
-        print('使用代理ip',change_ip)
-        
+    r = redis.Redis(host='db.ptt.cx', port=6379, db=2,password='choozmo9')
+    data=r.get('google_proxy')
+    jstext=data.decode('utf-8')
+    jsobj=json.loads(jstext)
+    #print('Free proxy',jsobj)
+    proxy=random.choice(jsobj)
+    i5 = "--proxy-server=socks5://172.104.93.163:41800"
+    change_ip_list = ['--proxy-server=%s' % proxy,"--proxy-server=socks5://127.0.0.1:9050","--proxy-server=socks5://192.53.174.202:8180"]
+    change_ip = random.choice(change_ip_list)
+    options.add_argument(i5)
+    #print('使用代理ip',change_ip)
+    
     driver = webdriver.Chrome(options=options,service=s)
 
     driver.delete_all_cookies()
     driver.set_window_size(1400,1000)
 
     process_query(q)
-    time.sleep(3)
-    driver.quit()
 
 
 #for c in lst:

INNNews/general_clickbot_proxy.py.save

@@ -0,0 +1,157 @@
+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.chrome.service import Service
+from selenium.webdriver.common.keys import Keys
+from selenium.webdriver.support import expected_conditions as EC
+import codecs
+import random
+import requests
+import datetime
+import dataset
+import time
+import traceback
+import sys
+import fire
+import redis
+
+
+driver = None
+
+
+def rua():
+    pool = [
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:73.0) Gecko/20100101 Firefox/73.0",
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0",
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36"
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.101 Safari/537.36",
+        "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36",
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36",
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36 OPR/68.0.3618.125",
+    ]
+    return random.choice(pool)
+
+
+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):
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    table=db['general_log']
+    q=qs[0]
+    domain=qs[1]
+    global driver
+    googleurl = 'https://www.google.com/?num=100'
+    driver.get(googleurl)
+    time.sleep(6)
+    send_kw_elmt = driver.find_element(By.XPATH, '/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')
+    send_kw_elmt.send_keys(q)
+    time.sleep(3)
+    send_kw_elmt.send_keys(Keys.ENTER)
+    time.sleep(6)
+    print(driver.current_url)
+    elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']/a")
+
+    idx=1
+    ranking=-1
+    print('網頁數量',len(elmts))
+#    driver.save_screenshot('c:/tmp/test.png')
+    if 'site' in q:
+        href = elmts[0].get_attribute('href')
+        txt = elmts[0].text
+        print('clicked....')
+        print(href)
+        print(txt)
+        print("ranking", idx)
+        table.insert(
+            {'kw': q, 'domain': domain, 'ranking': idx, 'title': txt, 'url': href, 'dt': datetime.datetime.now()})
+        webdriver.ActionChains(driver).move_to_element(elmts[0]).perform()
+        webdriver.ActionChains(driver).move_to_element(elmts[0]).click().perform()
+        time.sleep(5)
+    for elmt in elmts:
+        href=elmt.get_attribute('href')
+        txt=elmt.text
+        if len(txt)>10:
+            if domain in href:
+                print('clicked....')
+                print('點擊網址',href)
+                print('標題',txt)
+                print("ranking", idx)
+                table.insert({'kw':q,'domain':domain,'ranking':idx,'title':txt,'url':href,'dt':datetime.datetime.now()})
+                webdriver.ActionChains(driver).move_to_element(elmt).perform()
+                webdriver.ActionChains(driver).move_to_element(elmt).click().perform()
+                time.sleep(5)
+                break
+        idx+=1
+    db.close()
+def run_once(q):
+    global driver
+    result=[]
+    s = Service('/root/driver/chromedriver')
+    user_agent = rua()
+    options = webdriver.ChromeOptions()
+    options.add_argument('--headless')
+    options.add_argument('--remote-debugging-port=9222')
+    options.add_experimental_option("debuggerAddress", "127.0.0.1:9922")
+    # options.add_argument("--user-agent=" +user_agent)
+    options.add_argument("--incognito")
+    r = redis.Redis(host='db.ptt.cx', port=6379, db=2,password='choozmo9')
+    data=r.get('google_proxy')
+    jstext=data.decode('utf-8')
+    jsobj=json.loads(jstext)
+    proxy=random.choice(jsobj)
+    print('Freeproxy',proxy)
+    change_ip = ["'--proxy-server='+proxy","--proxy-server=socks5://127.0.0.1:9050","--proxy-server=socks5://192.53.174.202:8180"]
+    options.add_argument('--proxy-server=socks5://192.53.174.202:8180')
+    driver = webdriver.Chrome(
+    options=options,service=s)
+    if 'sorry' in driver.current_url:
+        r = redis.Redis(host='db.ptt.cx', port=6379, db=2,password='choozmo9')
+        data=r.get('google_proxy')
+        jstext=data.decode('utf-8')
+        jsobj=json.loads(jstext)
+        print('Free proxy',jsobj)
+        proxy=random.choice(jsobj)
+        change_ip_list = ['--proxy-server=%s' % proxy,"--proxy-server=socks5://127.0.0.1:9050","--proxy-server=socks5://192.53.174.202:8180"]
+        change_ip = random.choice(change_ip_list)
+        options.add_argument(change_ip)
+        print('使用代理ip',change_ip)
+        
+    driver = webdriver.Chrome(options=options,service=s)
+
+    driver.delete_all_cookies()
+    driver.set_window_size(1400,1000)
+
+    process_query(q)
+    time.sleep(3)
+    driver.quit()
+
+
+#for c in lst:
+#while True:
+#    try:
+#        c=random.choice(lst)
+#    except:
+#        traceback.print_exc()
+#    sleepint=random.randint(320,520)
+#    time.sleep(sleepint)
+
+class JParams(object):
+
+  def get(self, kw,domain,port):
+    run_once( (kw,domain,port) )
+
+
+if __name__ == '__main__':
+  fire.Fire(JParams)
+

INNNews/run_sheet_2.py

@@ -22,23 +22,23 @@ def run_once(pport, dockername):
     db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
     lst = []
     
-    cursor = db.query('select term, domain from seo.selected_kw where client not in ("毛怪")')
+    cursor = db.query('select term, domain from seo.selected_kw where client not in ("毛怪","hhh")')
     for c in cursor:
         lst.append([c['term'], c['domain']])
-    
+    #lst2=[['台灣仁本生命服務團隊','sctt.com.tw']]
     obj = random.choice(lst)
     kw = obj[0]
     domain = obj[1]
     print(kw, domain)
+    db.close()
     
-    intval = os.system(f'python3 general_clickbot.py get --kw="{kw}" --domain="{domain}" --port="{str(pport)}"')
+    intval = os.system(f'python3 general_clickbot_proxy.py get --kw="{kw}" --domain="{domain}" --port="{str(pport)}"')
     
     print('執行完成genetal_clickbot')
     
     if intval == -1:
         print('-1')
         sys.exit()
-    db.close()
 
 def run_specific(pport, dockername):
     db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
@@ -47,19 +47,34 @@ def run_specific(pport, dockername):
     cursor = db.query('select term, domain from seo.selected_kw where client="神助物流"')
     for c in cursor:
         lst.append([c['term'], c['domain']])
-    
+    db.close()
+
     obj = random.choice(lst)
-    kw = obj[0]
+    print('隨機',obj)
+    #obj = ['貨架','gs-rack.com']
+    if obj[0]=='重型 架':
+        lst_1 = ['重型架 無軌式重型移動','重型架 無軌移動貨架','重型 架 神助物流']
+        kw = random.choice(lst_1)
+    elif obj[0]=='貨架':
+        lst_2=['貨架 無軌式重型移動','貨架 無軌式重型移動貨架','貨架 無軌移動貨架儲存方案']
+        kw = random.choice(lst_2)
+    #elif obj[0]=='倉儲 設備':
+    #    kw = '倉儲 設備'
+    #    print(kw)
+    else:
+        lst_3=[]
+        lst_3.append(obj[0]+' 神助物流')
+        lst_3.append(obj[0])
+        kw = random.choice(lst_3)
     domain = obj[1]
-    print(kw,domain)
+    print('執行的關鍵字',kw,domain)
 
-    intval = os.system(f'python3 general_clickbot.py get --kw="{kw}" --domain="{domain}" --port="{str(pport)}"')    
+    intval = os.system(f'python3 general_clickbot_proxy.py get --kw="{kw}" --domain="{domain}" --port="{str(pport)}"')    
     print('執行完成神助genetal_clickbot')
 
     if intval == -1:
         print('-1')
         sys.exit()
-    db.close()
 
 class JParams(object):
     
@@ -70,15 +85,17 @@ class JParams(object):
                 os.system('docker container restart tiny2')
                 os.system('docker container restart tiny3')
                 os.system('docker container restart tiny8')
+                #os.system('docker container restart tiny10')
                 time.sleep(1)
                 run_once(9922, 'tiny1')
                 run_once(9923, 'tiny2')
                 run_once(9924, 'tiny3')
+                #run_once(9930, 'tiny10')  
                 run_specific(9929, 'tiny8')
                 time.sleep(20)
                 break           
             except:
-                os.system('docker container restart tiny1')
+                os.system('docker container restart tiny8')
                 time.sleep(15)
 
 

INNNews/run_sheet_3.py

@@ -0,0 +1,85 @@
+import sys
+import codecs
+import traceback
+import requests
+import re
+import pandas as pd
+import random
+import urllib
+import json
+import gspread
+import datetime
+from gspread_pandas import Spread, Client
+from oauth2client.service_account import ServiceAccountCredentials
+import os
+import redis
+import time
+import fire
+import dataset
+
+
+def run_once():
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    lst = []
+    
+    cursor = db.query('select term, domain from seo.selected_kw where client not in ("毛怪","hhh")')
+    for c in cursor:
+        lst.append([c['term'], c['domain']])
+    #lst2=[['台灣仁本生命服務團隊','sctt.com.tw']]
+    obj = random.choice(lst)
+    kw = obj[0]
+    domain = obj[1]
+    print(kw, domain)
+    db.close()
+    
+    intval = os.system(f'python3 general_clickbot_proxy.py get --kw="{kw}" --domain="{domain}"')
+    
+    print('執行完成genetal_clickbot')
+    
+    if intval == -1:
+        print('-1')
+        sys.exit()
+
+def run_specific():
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    lst = []
+    
+    cursor = db.query('select term, domain from seo.selected_kw where client="神助物流"')
+    for c in cursor:
+        lst.append([c['term'], c['domain']])
+    db.close()
+
+    obj = random.choice(lst)
+    print('隨機',obj)
+    #obj = ['貨架','gs-rack.com']
+    if obj[0]=='重型 架':
+        lst_1 = ['重型架 無軌式重型移動','重型架 無軌移動貨架','重型 架 神助物流']
+        kw = random.choice(lst_1)
+    elif obj[0]=='貨架':
+        lst_2=['貨架 無軌式重型移動','貨架 無軌式重型移動貨架','貨架 無軌移動貨架儲存方案']
+        kw = random.choice(lst_2)
+    #elif obj[0]=='倉儲 設備':
+    #    kw = '倉儲 設備'
+    #    print(kw)
+    else:
+        lst_3=[]
+        lst_3.append(obj[0]+' 神助物流')
+        lst_3.append(obj[0])
+        kw = random.choice(lst_3)
+    domain = obj[1]
+    print('執行的關鍵字',kw,domain)
+
+    intval = os.system(f'python3 general_clickbot_proxy.py get --kw="{kw}" --domain="{domain}"')
+    print('執行完成神助genetal_clickbot')
+
+    if intval == -1:
+        print('-1')
+        sys.exit()
+
+
+while True:
+    run_once()
+    time.sleep(random.randint(180,200))
+    run_specific()
+    time.sleep(random.randint(180,200))
+

SEO/choozmointernal-2e314f3d4e12.json

@@ -0,0 +1,12 @@
+{
+  "type": "service_account",
+  "project_id": "choozmointernal",
+  "private_key_id": "2e314f3d4e1249f255cbc0668a8ce4ccf1cbd6b9",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nhucDeA0a767QtKpGDi9hi2iZ\n-----END PRIVATE KEY-----\n",
+  "client_email": "gdrive@choozmointernal.iam.gserviceaccount.com",
+  "client_id": "111207848091817318160",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gdrive%40choozmointernal.iam.gserviceaccount.com"
+}

SEO/seo_monitor.py

@@ -0,0 +1,143 @@
+#!/usr/bin/python
+# -*- coding: UTF-8 -*-
+import pandas as pd
+
+from datetime import datetime
+import pymysql
+pymysql.install_as_MySQLdb()
+import dataset
+import requests
+import gspread
+from gspread_pandas import Spread, Client
+from oauth2client.service_account import ServiceAccountCredentials
+
+db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+
+data = pd.DataFrame()
+
+def notify_group(msg):
+    gid='WekCRfnAirSiSxALiD6gcm0B56EejsoK89zFbIaiZQD'
+    headers = {"Authorization": "Bearer " + gid,"Content-Type": "application/x-www-form-urlencoded"}
+    r = requests.post("https://notify-api.line.me/api/notify",headers=headers, params={"message": msg})
+
+def download(client, date, newest=True):
+    """關鍵字清單"""
+    lst_kw = []
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    cursor_kw = db.query(f"SELECT term FROM seo.selected_kw where client='{client}'")
+    for c in cursor_kw:
+        for i in c.values():
+            lst_kw.append(i)
+    print(len(lst_kw))
+    
+    """抓取general_log關鍵字"""
+    last_check_lst = []
+    for i in lst_kw:
+        if newest:
+            cursor_last_check = db.query(f"select kw,ranking from seo.general_log where kw='{i}' order by dt desc limit 1")
+        else:
+            cursor_last_check = db.query(f"select kw,ranking from seo.general_log where kw='{i}' order by dt limit 1")
+        group = []
+        n = 0
+        for c in cursor_last_check:
+            for j in c.values():
+                if 'site' in str(j):
+                    n+=1
+                if n==1 and j==1:
+                    group.append(101)
+                else:
+                    group.append(j)
+            n = 0
+        last_check_lst.append(group)
+    # df2 = pd.DataFrame(not_match_kw_lst,columns=['關鍵字組','搜尋排名'])
+    df3 = pd.DataFrame(last_check_lst, columns=['關鍵字組', '搜尋排名'])
+    # df_all = pd.concat([df, df3])
+    df3.to_csv(f"./排名CSV/{client}當日排名{date}.csv", index=False, encoding='utf_8_sig')
+    db.close()
+
+
+def combine_df(client, date1, date2):
+    df = pd.read_csv(f'./排名CSV/{client}當日排名{date1}.csv')
+    df2 = pd.read_csv(f'./排名CSV/{client}當日排名{date2}.csv')
+    df_result = pd.merge(df, df2, on='關鍵字組', how='outer').fillna(0)
+    date1 = arrange_date(date1)
+    date2 = arrange_date(date2)
+    df_result.columns = ['kw', 'starting_rank', 'current_rank']
+        
+    p = df_result['starting_rank'].tolist()
+    l = df_result['current_rank'].tolist()
+
+    c = [u"\u2197 "+str(abs(int(i)-int(j))) if int(i)-int(j)>0 \
+        else u"\u2198 "+str(abs(int(i)-int(j))) if int(i)-int(j)<0 \
+        else u"\u2192 "+str(abs(int(i)-int(j))) for (i, j) in zip(p, l)]
+
+    df_result['client'] = client
+    df_result['change'] = c
+    df_result['kw'] = df_result['kw'].str.split('site',0).str[0]
+    df_result.to_csv(f"./排名CSV/combine/{client}排名變化.csv", index=False, encoding='utf_8_sig')
+    return df_result, date1, date2
+
+def arrange_date(date):
+    if date[0] == 0 :
+        date = date[1]+'/'+date[2:]
+    else:
+        date = date[:2]+'/'+date[2:]
+    return date
+
+def checkrank(data):
+    msg = "以下是排名下降的關鍵字：\n"
+    msg2 = "以下是目前排名於百名外的關鍵字：\n"
+    flag1=0
+    flag2=0
+    for row in data.index:
+            #print(row)
+            delta = int(data['starting_rank'][row])-int(data['current_rank'][row])
+            if (delta < 0):
+                msg += "[" + data['client'][row] + "] " + data['kw'][row] + ": " + str(int(data['starting_rank'][row])) + " -> " + str(int(data['current_rank'][row])) + " (" + str(int(delta)) + ")\n"
+                flag1=1
+            if (int(data['current_rank'][row]) == 101):  #out of range...
+                msg2 += "[" + data['client'][row] + "] " + data['kw'][row] + "\n"
+                flag2=1
+    print(msg)
+    print(msg2)
+    return msg, msg2, flag1, flag2
+
+if __name__ == "__main__":
+    date1 = '0707'
+    date2 = '0717'
+    lst = ['清原', '神助物流', '班尼斯', '有夠讚', '仁本', '火柴星人', '呷茶']
+    for client in lst:
+        date1 = '0707'
+        date2 = '0718'
+        download(client, date1, newest=False)
+        download(client, date2, newest=True)
+        res, d1, d2 = combine_df(client, date1, date2)
+        data = data.append(res, ignore_index=True)
+    data.to_csv(f"./排名CSV/combine/__排名變化.csv", index=False, encoding='utf_8_sig')
+
+    scope = ['https://spreadsheets.google.com/feeds','https://www.googleapis.com/auth/drive']
+    credentials = ServiceAccountCredentials.from_json_keyfile_name("choozmointernal-2e314f3d4e12.json", scope)
+    gc = gspread.authorize(credentials)
+    spread = Spread("kw_ranking_tracker",creds=credentials)
+    spread.df_to_sheet(data, index=False, sheet="main", start="A1", replace=False)
+    time_stamp = datetime.now()
+    time_stamp = time_stamp.strftime("%Y-%m-%d %H:%M:%S")
+    
+    spread.sheet.update('G1', '最後更新:' + time_stamp)
+    
+    msg, msg2, flag1, flag2=checkrank(data)
+
+    msg += "\n完整資料請至https://cmm.ai/seo1"
+    msg2 += "\n完整資料請至https://cmm.ai/seo1"
+
+    if flag1 == 1:
+        msg01 = [msg[i:i+1000] for i in range(0, len(msg), 1000)]
+        for m1 in msg01:
+            notify_group(m1)
+            print(m1)
+    
+    if flag2 == 1:
+        msg02 = [msg2[i:i+1000] for i in range(0, len(msg2), 1000)]
+        for m2 in msg02:
+            notify_group(m2)
+            print(m2)

joblist/choozmointernal-2e314f3d4e12.json

@@ -0,0 +1,12 @@
+{
+  "type": "service_account",
+  "project_id": "choozmointernal",
+  "private_key_id": "2e314f3d4e1249f255cbc0668a8ce4ccf1cbd6b9",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nhucDeA0a767QtKpGDi9hi2iZ\n-----END PRIVATE KEY-----\n",
+  "client_email": "gdrive@choozmointernal.iam.gserviceaccount.com",
+  "client_id": "111207848091817318160",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gdrive%40choozmointernal.iam.gserviceaccount.com"
+}

joblist/jobcheck.py

@@ -0,0 +1,81 @@
+import requests
+import datetime
+from dateutil import parser
+import gspread
+from oauth2client.service_account import ServiceAccountCredentials
+import time
+
+# drop this at PUBLIC2
+
+# TASK LIST HERE
+# https://docs.google.com/spreadsheets/d/153w046qHhpnZTYU7FJ-S2xyGIH_BXbycLYfLI2fFsZc/edit#gid=0
+
+scope = ['https://spreadsheets.google.com/feeds','https://www.googleapis.com/auth/drive']
+creds = ServiceAccountCredentials.from_json_keyfile_name('choozmointernal-2e314f3d4e12.json', scope)
+client = gspread.authorize(creds)
+message = "提醒近期預定執行的作業如下：\n\n"
+message2 = "提醒近期需完成的作業如下：\n\n"
+
+def notify_group(msg):
+    gid='WekCRfnAirSiSxALiD6gcm0B56EejsoK89zFbIaiZQD'
+    headers = {"Authorization": "Bearer " + gid,"Content-Type": "application/x-www-form-urlencoded"}
+    r = requests.post("https://notify-api.line.me/api/notify",headers=headers, params={"message": msg})
+
+sheet = client.open('ChoozMo 專案執行表單_20220720')
+sheet_instance = sheet.get_worksheet(0)
+
+records_data = sheet_instance.get_all_records()
+#print(records_data[0])
+
+for data in records_data:
+    try:
+        print(parser.parse(data["完成日"]))
+        print(datetime.date.today())
+        deltastart = (parser.parse(data["起始日"]).date()-datetime.date.today()).days
+        deltaend = (parser.parse(data["完成日"]).date()-datetime.date.today()).days
+        print(deltastart, deltaend)
+
+        if(deltastart <= 7 and data["完成度"] == "預定執行"):
+            message += "專案：" + data["專案"] + "\n"
+            message += "專案項目：" + data["專案項目"] + "\n"
+            message += "作業：" + data["執行項目"] + "\n"
+            message += "執行人員：" + data["指派對象"] + "\n"
+            message += "PM：" + data["PM"] + "\n"
+            message += "執行期間：" + data["起始日"] + "-" + data["完成日"]
+            if(deltastart>0):
+                message += " (尚有"+ str(deltastart) + "天)\n\n"
+            elif(deltastart==0):
+                message += " (當天開始執行)\n\n"
+            else:
+                message += " (過期"+ str(deltastart).replace('-','') + "天)\n\n"
+
+        elif(deltaend <= 7 and data["完成度"] == "執行中"):
+            message2 += "專案：" + data["專案"] + "\n"
+            message2 += "專案項目：" + data["專案項目"] + "\n"
+            message2 += "作業：" + data["執行項目"] + "\n"
+            message2 += "執行人員：" + data["指派對象"] + "\n"
+            message2 += "PM：" + data["PM"] + "\n"
+            message2 += "完成日：" + data["完成日"]
+            if(deltaend>0):
+                message2 += " (尚有"+ str(deltaend) + "天)\n\n"
+            elif(deltaend==0):
+                message2 += " (當天完成)\n\n"
+            else:
+                message2 += " (過期"+ str(deltaend).replace('-','') + "天)\n\n"
+
+    except:
+        print("PASS")
+
+msg1 = [message[i:i+1000] for i in range(0, len(message), 1000)]
+for m1 in msg1:
+    #notify_group(m1) #annotated to prevent unintentional trigger
+    print(m1)
+
+msg2 = [message2[i:i+1000] for i in range(0, len(message2), 1000)]
+for m2 in msg2:
+    #notify_group(m2)
+    print(m2)
+
+'''notify_group(message)
+time.sleep(5)
+notify_group(message2)'''

web/main.py

@@ -28,6 +28,7 @@ import traceback
 import time
 from selenium.webdriver.common.keys import Keys
 from selenium.webdriver.common.by import By
+from selenium.webdriver.chrome.service import Service
 # import pymysql
 # pymysql.install_as_MySQLdb()
 
@@ -50,7 +51,7 @@ app.add_middleware(
 db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/gtrends?charset=utf8mb4')
 
 # app.mount("/web", StaticFiles(directory="static"), name="static")
-app.mount("/web", StaticFiles(directory="/Users/zooeytsai/kw_tools/web/static"), name="static")
+app.mount("/web", StaticFiles(directory="/root/src/kw_tools/web/static"), name="static")
 
 def thread_function(kw):
     global db
@@ -127,56 +128,83 @@ async def func_expand(kw: str = Form(...),kw2:Optional[str] = Form(None),kw3:Opt
     return RedirectResponse(url="/tree_list",status_code=302)
 #    return HTMLResponse('<html><head><meta http-equiv="refresh" content="0; URL="/tree_list" /></head></html>')
 
-    
-@app.post("/ranking/")
-async def ranking(kw: str = Form(...), domain:str = Form(...)):
+
+def restart_browser():
     global driver
-    options = webdriver.ChromeOptions()
-    options.add_argument("--no-sandbox")
-    options.add_argument("--disable-dev-shm-usage")
-    options.add_argument('--headless')
-    driver = webdriver.Chrome(options=options)
-    driver.set_window_size(950, 20000)
-
-    # db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
-    db_local = dataset.connect('mysql://root:jondae350@localhost/ig_tags')
-    table = db_local['google_rank']
-
-    # escaped_search_term=urllib.parse.quote(term)
-    googleurl = 'https://www.google.com/?num=100'
-    driver.get(googleurl)
-    time.sleep(6)
-    send_kw_elmt = driver.find_element(By.XPATH,
-                                       '/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')
-    send_kw_elmt.send_keys(kw)
-    time.sleep(3)
-    send_kw_elmt.send_keys(Keys.ENTER)
-    time.sleep(6)
-    elmts = driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")
-
-    cnt = 1
-    datadict = {'搜尋詞': [], '結果標題': [], '結果網址': [], '結果名次': []}
-
-    for elmt in elmts:
+    if driver is not None:
+        print('closing')
+        driver.quit()
+        driver = None
+    try: 
+        options = webdriver.ChromeOptions()
+        options.add_argument("--no-sandbox")
+        options.add_argument("--disable-dev-shm-usage")
+        options.add_argument('--headless')
+        # options.add_experimental_option("debuggerAddress", "127.0.0.1:9923")
+        options.add_argument("--incognito")
         try:
-            href = elmt.get_attribute('href')
-            if domain in href:
-                datadict['搜尋詞'].append(kw)
-                datadict['結果標題'].append(elmt.text)
-                datadict['結果網址'].append(href)
-                datadict['結果名次'].append(str(cnt))
-            cnt += 1
+            driver = webdriver.Chrome(options=options,executable_path='/root/driver/chromedriver103')
+            #driver = webdriver.Remote(command_executor='http://127.0.0.1:'+str(portnum)+'/wd/hub',options=options)
         except:
-            print('href2 exception')
-            traceback.print_exc()
+            return None
+    except:
+       print('開啟失敗')
+       driver=None
+       return None
+    return driver
+    
+@app.post("/ranking/")
+async def ranking(kw: str = Form(...), domain:str = Form(...),kw2:Optional[str] = Form(None),domain2:Optional[str] = Form(None),kw3:Optional[str] = Form(None),domain3:Optional[str] = Form(None),kw4:Optional[str] = Form(None),domain4:Optional[str] = Form(None),kw5:Optional[str] = Form(None),domain5:Optional[str] = Form(None)):
+    kwlst = []
+    kwlst.append([kw,domain])
+    if kw2 is not None:
+        kwlst.append([kw2,domain2])
+    if kw3 is not None:
+        kwlst.append([kw3,domain3])
+    if kw4 is not None:
+        kwlst.append([kw4,domain4])
+    if kw5 is not None:
+        kwlst.append([kw5,domain5])
+    result = []
+    for i in kwlst:
+        driver = restart_browser()
+        # escaped_search_term=urllib.parse.quote(term)
+        googleurl = 'https://www.google.com/?num=100'
+        driver.get(googleurl)
+        time.sleep(6)
+        send_kw_elmt = driver.find_element(By.XPATH,
+                                           '/html/body/div[1]/div[3]/form/div[1]/div[1]/div[1]/div/div[2]/input')
+        send_kw_elmt.send_keys(i[0])
+        time.sleep(3)
+        send_kw_elmt.send_keys(Keys.ENTER)
+        time.sleep(6)
+        elmts = driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")
+
+        cnt = 1
+        datadict = {'搜尋詞': [], '結果標題': [], '結果網址': [], '結果名次': []}
+        domain_name = i[1]
+        for elmt in elmts:
+            try:
+                href = elmt.get_attribute('href')
+                if domain_name in href:
+                    datadict['搜尋詞'].append(i[0])
+                    datadict['結果標題'].append(elmt.text)
+                    datadict['結果網址'].append(href)
+                    datadict['結果名次'].append(str(cnt))
+                cnt += 1
+            except:
+                print('href2 exception')
+                traceback.print_exc()
+        result.append(datadict)
+        print(domain_name)
+        print(datadict)
+        driver.quit()
+        print('數量',len(elmts))
+        time.sleep(90)
 
-    driver.quit()
-    time.sleep(60)
-    # db.close()
-    db_local.close()
     # return "ok"
     # return RedirectResponse(url="/ranking_result",)
-    html = "<html><body><h2>"+str(datadict)+"</br></br>"
+    html = f"<html><body>{result}</body></html>"
     return html
 
 @app.get("/ranking_result/")
@@ -185,4 +213,4 @@ async def tree_list():
 
     # html += "<tr><td>" + c['kw'] + "</td>"
     
-    return html
+    return html

web/runserver.py

@@ -3,4 +3,4 @@ import sys,os
 sys.path.append(os.getcwd())
 
 if __name__ == "__main__":
-    uvicorn.run("main:app", host="0.0.0.0", port=4321, log_level="info",reload=True, debug=True)
+    uvicorn.run("main:app", host="0.0.0.0", port=9005, log_level="info",reload=True, debug=True)

web/static/ranking.html

@@ -3,6 +3,14 @@
         <form action="/ranking" method="post">
             KW: <input type="text" id="kw" name="kw" value=""></br>
             domain: <input type="text" id="domain" name="domain" value=""></br>
+            KW2: <input type="text" id="kw2" name="kw2" value=""></br>
+            domain2: <input type="text" id="domain2" name="domain2" value=""></br>
+            KW3: <input type="text" id="kw3" name="kw3" value=""></br>
+            domain3: <input type="text" id="domain3" name="domain3" value=""></br>
+            KW4: <input type="text" id="kw4" name="kw4" value=""></br>
+            domain4: <input type="text" id="domain4" name="domain4" value=""></br>
+            KW5: <input type="text" id="kw5" name="kw5" value=""></br>
+            domain5: <input type="text" id="domain5" name="domain5" value=""></br>
             <input type="submit" value="開始">
         </form>
     </br>

website_clickjobs/type-2/hhh.py

@@ -0,0 +1,5 @@
+from _clickjob import *
+
+target = 'https://www.hhh.com.tw'
+
+execute(target)

website_clickjobs/type-FD-N/_clickjob.py

@@ -0,0 +1,86 @@
+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
+from selenium.webdriver.firefox.options import *
+
+add_tabs = [4,5,6,7,8,4,5,6,7,8,4,5,6,7,8,4,5,6,7,8]
+sleepint=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(domain)
+    time.sleep(6)
+    print(driver.current_url)
+    
+
+def run_once(domain, target_domain, brands, query):
+    global driver
+    result=[]
+    options = Options()
+    options.headless = True
+#    options.add_argument("--user-agent=" +user_agent)
+#    options.add_argument('-no-sandbox')
+#    options.add_argument('-disable-dev-shm-usage')
+
+    firefox_profile = webdriver.FirefoxProfile()
+    firefox_profile.set_preference("browser.privatebrowsing.autostart", True)
+
+    driver = webdriver.Firefox(
+    options=options, firefox_profile=firefox_profile)
+
+    driver.delete_all_cookies()
+    driver.set_window_size(1400,1000)
+
+    process_query(domain, target_domain, brands, query)
+    driver.quit()
+
+#execution starts here
+
+def execute(domain, target_domain, brands, query_list, times, sleepinterval):
+    for i in range (0,times):
+        print("Run " + str(i))
+        try:
+            run_once(domain, target_domain, brands, random.choice(query_list))
+        except:
+            traceback.print_exc()
+        #sleepint=random.randint(75,90) - sleepoffset
+        print("Completed (")
+        time.sleep(sleepinterval)

website_clickjobs/type-FD-N/bennis.py

@@ -0,0 +1,10 @@
+from _clickjob import *
+
+domain = 'https://www.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')
+times = 1666
+sleepinterval = 0.5
+
+execute(domain, target_domain, brands, query_list, times, sleepinterval)

website_clickjobs/type-FD-N/yogoclean.py

@@ -0,0 +1,10 @@
+from _clickjob import *
+
+domain = 'https://www.yogoclean.com'
+target_domain = ['yogoclean.com']
+brands={domain:'有夠讚'}
+query_list = ('有夠讚','有夠讚')
+times = 1666
+sleepinterval = 15
+
+execute(domain, target_domain, brands, query_list, times, sleepinterval)

website_clickjobs/type-FD/_clickjob.py

@@ -0,0 +1,88 @@
+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
+from selenium.webdriver.firefox.options import *
+
+add_tabs = [4,5,6,7,8,4,5,6,7,8,4,5,6,7,8,4,5,6,7,8]
+sleepint=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(domain)
+    time.sleep(6)
+    print(driver.current_url)
+    
+
+def run_once(domain, target_domain, brands, query):
+    global driver
+    result=[]
+    options = Options()
+    options.headless = True
+#    options.add_argument("--user-agent=" +user_agent)
+#    options.add_argument('-no-sandbox')
+#    options.add_argument('-disable-dev-shm-usage')
+
+    firefox_profile = webdriver.FirefoxProfile()
+    firefox_profile.set_preference("browser.privatebrowsing.autostart", True)
+
+    driver = webdriver.Firefox(
+    options=options, firefox_profile=firefox_profile)
+
+    driver.delete_all_cookies()
+    driver.set_window_size(1400,1000)
+
+    process_query(domain, target_domain, brands, query)
+    driver.quit()
+
+#execution starts here
+
+def execute(domain, target_domain, brands, query_list):
+    i=1
+    while True:
+        print("Run " + str(i))
+        i+=1
+        try:
+            run_once(domain, target_domain, brands, random.choice(query_list))
+        except:
+            traceback.print_exc()
+        #sleepint=random.randint(75,90) - sleepoffset
+        print("Completed (")
+        time.sleep(15)

website_clickjobs/type-FD/bennis.py

@@ -0,0 +1,8 @@
+from _clickjob import *
+
+domain = 'https://www.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/type-FD/gsrack.py

@@ -0,0 +1,8 @@
+from _clickjob import *
+
+domain = 'https://gs-rack.com/'
+target_domain = ['gs-rack.com']
+brands={domain:'神助'}
+query_list = ('神助','神助 物流')
+
+execute(domain, target_domain, brands, query_list)

website_clickjobs/type-FD/yogoclean.py

@@ -0,0 +1,8 @@
+from _clickjob import *
+
+domain = 'https://www.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)