更新

INNNews/run_sheet_2.py

@@ -43,8 +43,11 @@ def run_specific():
     # db_local = dataset.connect('mysql://root:jondae350@localhost/ig_tags')
     lst = []
 
-    ####形象SEO####
-    # cursor = db.query('select json from seo.seo_jobs where id between 937 and 946')
+    # ####形象SEO####
+    cursor = db.query('select cust, json from seo.seo_jobs where cust="啟翔" order by rand() limit 1')
+    # cursor = db.query('select cust, json from seo.seo_jobs where cust=""')
+    # cursor = db.query('select json from seo.seo_jobs where id between 2775 and 2793')
+    ### 測試開始部分 ###
     # for c in cursor:
     #     print(c['json'])
     #     js = json.loads(c['json'])
@@ -56,29 +59,49 @@ def run_specific():
     #     kw1 = random.choice(positive)
     #     kw2 = random.choice(rnd)
     #     kw = prefix + " " + kw1 + " " + kw2
-    #     # print(kw, domain)
-
-    ###形象SEO###
-    cursor = db.query('select term, domain from seo.selected_kw where client="plantA"')
+    #     print(kw, domain)
+    ### 測試結束部分 ###
     for c in cursor:
-        lst.append([c['term'], c['domain']])
-
-    obj = random.choice(lst)
-    kw = obj[0]
-    domain = obj[1]
-    print(kw, domain)
+        js = json.loads(c['json'])
+        prefix = js['prefix']
+        postfix = js['postfix']
+        domain = js['domain'][0]
+        positive = js['positive']
+        rnd = js['rnd']
+        client = c['cust']
+    print(prefix)
+    kw1 = random.choice(positive)
+    kw2 = random.choice(rnd)
+    kw = prefix + " " + kw1 + " " + kw2
+
+
+##########
+    # cursor = db.query('select term, domain from seo.selected_kw where client="歌林"')
+    # for c in cursor:
+    #     lst.append([c['term'], c['domain']])
+    #
+    # obj = random.choice(lst)
+    # kw = obj[0]
+    # domain = obj[1]
+    # print(kw, domain)
 
-    intval = os.system(f'python3 general_clickbot_local.py get --kw="{kw}" --domain="{domain}"')
+    intval = os.system(f'python3 general_clickbot_local.py get --kw="{kw}" --domain="{domain}" --client="{client}"')
     print('執行完成genetal_clickbot')
 
     if intval == -1:
         print('-1')
         sys.exit()
     db.close()
-
-# run_specific()
+    # run_specific()
 while True:
     # run_once()
     run_specific()
     time.sleep(random.randint(120, 150))
 
+os.system('docker container stop sel2')
+time.sleep(3)
+os.system('docker container rm sel2')
+time.sleep(3)
+os.system('docker run -d -p 9922:4444 --name sel1 --add-host=host.docker.internal:host-gateway --shm-size="2g" selenium/standalone-chrome:103.0')
+time.sleep(6)
+

SEO/clickbot_100.py

@@ -25,7 +25,7 @@ driver = None
 def restart_browser():
     global driver
     user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
-    s = Service('C:\/Users\/s1301\/Downloads\/chromedriver_109/chromedriver')
+    s = Service('C:\/Users\/s1301\/Downloads\/chromedriver_116\/chromedriver-win32\/chromedriver')
     options = webdriver.ChromeOptions()
     options.add_argument('--headless')
     # options.add_argument('--remote-debugging-port=9222')
@@ -43,29 +43,29 @@ def restart_browser():
 
 def process_one():
     db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
-    lst=[]
+    lst = []
     table=db['google_rank']
-    # cursor = db.query('select term,domain from seo.selected_kw where client="CLIQ露營椅"')
-    # cursor = db.query('select term,url from seo.sns_kw where client="英雄難國美人酒"')
-    # cursor = db.query('select term from seo.selected_kw where client="plantA"')
-    # cursor = db.query('select term,domain from seo.select_kw where id between 2216 and 2255')
-    cursor = db.query('select term,domain from seo.select_kw where client="美麗馨"')
+    # cursor = db.query('select term,domain from seo.selected_kw where client="新飛0721"')
+    # cursor = db.query('select term,url from seo.sns_kw where client="理茶"')
+    # cursor = db.query('select term,domain from seo.selected_kw where client="好晴天"')
+    # cursor = db.query('select term,domain from seo.select_kw where id between 1661 and 1672')
+    cursor = db.query('select term,domain from seo.select_kw where client="幸福空間"')
     # cursor=db.query('select term from selected_kw and term not in (SELECT distinct(keyword) FROM ig_tags.save_result where url like "%beastparadise.net%" and datediff(now(),dt)=0)')
     for c in cursor:
         lst.append([c['term'],c['domain']])
+        # lst.append([c['term'],c['url']])
         # lst.append(c['term'])
-    # domain = 'pinews.asia'
+    # domain = 'fleurancenature.tw'
     for i in lst:
         print(i)
         driver=restart_browser()
         escaped_search_term=urllib.parse.quote(i[0])
-        googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(escaped_search_term, 100,'zh-TW')
+        googleurl = 'https://www.google.com/search?q={}&num={}&hl={}&gl=tw'.format(escaped_search_term, 100,'zh-TW')
         driver.get(googleurl)
-        time.sleep(60)
         print(driver.current_url)
-        # driver.save_screenshot('C:\/Users\/s1301\/Pictures\/Saved Pictures\/'+i[0]+'.png')
+        # driver.save_screenshot('C:\/Users\/s1301\/Pictures\/Saved Pictures\/新飛\/0721\/'+i[0]+'.png')
         df=pd.DataFrame()
-        elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']/a")
+        elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']//a")
         print('結果數量',len(elmts))
         cnt=1
         datadict={'搜尋詞':[],'結果標題':[],'結果網址':[],'結果名次':[]}
@@ -77,6 +77,11 @@ def process_one():
                     table.insert({'title':elmt.text,'url':href,'keyword':i[0],'dt':datetime.datetime.now(),'ranking':cnt})
                     print(href)
                     print(elmt.text)
+                # if 'hhh.com.tw' in href:
+                #     table.insert({'title': elmt.text, 'url': href, 'keyword': i, 'dt': datetime.datetime.now(),
+                #                   'ranking': cnt})
+                #     print(href)
+                #     print(elmt.text)
                 datadict['搜尋詞'].append(i[0])
                 datadict['結果標題'].append(elmt.text)
                 datadict['結果網址'].append(href)
@@ -93,11 +98,11 @@ def process_one():
         df['結果網址']=datadict['結果網址']
         df['結果名次']=datadict['結果名次']
 
-        df.to_excel('C:\/Users\/s1301\/Pictures\/Saved Pictures\soapdays\/'+i[0]+".xls")
+        # df.to_excel('C:\/Users\/s1301\/Pictures\/Saved Pictures\/芙樂思\/0720\/'+i+'.png')
 
         driver.quit()
         print('等待')
-        time.sleep(random.randint(100,120))
+        time.sleep(random.randint(70,90))
     db.close()
 process_one()
 

SEO/clickbot_100_one.py

@@ -25,13 +25,13 @@ driver = None
 def restart_browser():
     global driver
     user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.88 Safari/537.36'
-    s = Service('C:\/Users\/s1301\/Downloads\/chromedriver_109\/chromedriver')
+    s = Service('C:\/Users\/s1301\/Downloads\/chromedriver_116\/chromedriver-win32\/chromedriver')
     options = webdriver.ChromeOptions()
     options.add_argument('--headless')
     # options.add_argument('--remote-debugging-port=9222')
     # options.add_experimental_option("debuggerAddress", "192.168.192.45:9922")
     options.add_argument("--user-agent=" + user_agent)
-    options.add_argument("--incognito")
+    # options.add_argument("--incognito")
     # options.add_argument('--proxy-server=socks5://172.104.93.163:41800')
     driver = webdriver.Chrome(options=options, service=s)
 
@@ -42,23 +42,34 @@ def restart_browser():
 
 def process_one():
     # lst=['信義房屋','信義 房屋','信義房仲','信義 房仲']
-    # lst=['雙響泡','双響泡','雙響砲']
-    # lst = ['清原']
-    # lst = ['龔國權']
+    # lst=["親子育兒交流 奶爸","產後瘦身益生菌","產後瘦身推薦"]
+    lst=['雙響泡','双響泡','雙響砲']
+    # lst = ['小羊水果']
     # lst = ['巨力搬家']
-    lst = ['樂活眼鏡評價','lohas眼鏡評價','lohas評價']
-    date='0220'
+    # lst = ['台中搬家推薦','桃園搬家推薦','新竹搬家推薦']
+    # lst = ['地面課程','出國學飛','自訓學飛']
+    # lst = ['台北牙周病醫生推薦 ','微創水雷射','水雷射牙周病']
+    # lst = ['地面課程','出國學飛','自訓學飛']
+    # lst = ['樂活眼鏡評價','樂活眼鏡']
+    # lst = ['新竹搬家推薦','台中搬家推薦','桃園搬家推薦']
+    # lst = ['芙樂思蜂王漿乳霜','蜂王漿乳霜']
+    # lst = ['涼夏清爽','夏季口罩','石墨烯','透氣 口罩','夏天口罩推薦','夏天立體口罩']
+    # lst = ['啟翔輕金屬','啟翔','陳百欽']
+    date='0907'
+
     for term in lst:
         driver=restart_browser()
         escaped_search_term=urllib.parse.quote(term)
-        googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(escaped_search_term, 100,'zh-TW')
+        googleurl = 'https://www.google.com/search?q={}&num={}&hl={}&gl=tw'.format(escaped_search_term, 100,'zh-TW')
+        # googleurl='https://www.google.com/search?q=%E9%9B%99%E9%9F%BF%E7%A0%B2&num=100&rlz=1C1ONGR_zh-TWTW1033TW1033&oq=%E9%9B%99%E9%9F%BF%E7%A0%B2&aqs=chrome..69i57j69i61.414j0j1&sourceid=chrome&ie=UTF-8#ip=1&gl=tw&hl=zh-TW'
         driver.get(googleurl)
         time.sleep(6)
         print(driver.current_url)
 
-        driver.save_screenshot('C:\/Users\/s1301\/Pictures\/Saved Pictures\/'+date+term+'.png')
+        driver.save_screenshot('C:\/Users\/s1301\/OneDrive\/Pictures\/Saved Pictures\/'+date+term+'.png')
         df=pd.DataFrame()
-        elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']/a")
+        elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']//a")
+        print(len(elmts))
         cnt=1
         datadict={'搜尋詞':[],'結果標題':[],'結果網址':[],'結果名次':[]}
 
@@ -84,7 +95,7 @@ def process_one():
         df['結果網址']=datadict['結果網址']
         df['結果名次']=datadict['結果名次']
 
-        df.to_excel('C:\/Users\/s1301\/Pictures\/Saved Pictures\/'+date+term+".xls")
+        df.to_excel('C:\/Users\/s1301\/OneDrive\/Pictures\/Saved Pictures\/'+date+term+".xls")
 
         driver.quit()
         print('等待')

SEO/csv_to_sql.py

@@ -11,13 +11,13 @@ db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb
 # table=db['selected_kw']
 # table=db['sns_kw']
 table=db['select_kw']
-client='美麗馨'
-domain='lisinbeauty.com'
+client='幸福空間'
+domain='hhh.com.tw'
 # for index,row in df.iterrows():
 # with open("C:\/Users\/s1301\/Documents\/新飛國際遊學SEO - 關鍵字12.08.csv") as f:
 #     data_all = f.readlines()
-# print(data_all)
-f = open("C:\/Users\/s1301\/Documents\/456.csv",encoding='utf-8')
+# print(data_all)C:\Users\s1301\OneDrive\Documents
+f = open("C:\/Users\/s1301\/OneDrive\/Documents\/456.csv",encoding='utf-8')
 # df = pd.read_csv(f,header=None, names=['kw', 'url'])
 df = pd.read_csv(f,header=None, names=['kw'])
 # df = pd.read_csv(f,header=None, names=['prefix','id', 'positive','domain','rnd'])
@@ -28,7 +28,7 @@ lst=[]
 for index,row in df.iterrows():
     # print(row)
     # prefix='"'+row['prefix']+'"'
-    # # positive='"'+row['positive']+'"'
+    # positive='"'+row['positive']+'"'
     # positive=row['positive']
     # domain='"'+row['domain']+'"'
     # rnd='"'+str(row['rnd'])+'"'
@@ -40,9 +40,9 @@ for index,row in df.iterrows():
     # table.insert({'cust':client,'plan':'形象SEO','json':json})
     table.insert({'term':row['kw'],'client':client,'domain':domain})
     # table.insert({'term': row['kw'], 'client': client, 'url': row['url']})
-print(lst)
-{"prefix": "護佳", "postfix": "", "domain": ["www.hujiai-international.com"], "positive": ["細胞食物","紅蔘"], "rnd": [""]}
+# print(lst)
 
 db.close()
 
-####先從雲端下載csv 再用記事本打開另存一個csv#########
+####先從雲端下載csv 再用記事本打開另存一個csv#########
+