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

INNNews/general_clickbot.py

@@ -8,6 +8,7 @@ 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
@@ -22,8 +23,6 @@ import fire
 #pymysql.install_as_MySQLdb()
 
 
-db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
-table=db['general_log']
 driver = None
 
 
@@ -48,19 +47,25 @@ def empty_query(q):
 
 
 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/search?q={}&num={}&hl={}'.format(urllib.parse.quote(q), 100,'zh-TW')
-    print(googleurl)
+    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)
 
-    elmts=driver.find_elements_by_xpath("//div[@class='yuRUbf']/a")
+    elmts=driver.find_elements(By.XPATH,"//div[@class='yuRUbf']/a")
 
     idx=1
     ranking=-1
-    print(len(elmts))
+    print('網頁數量',len(elmts))
 #    driver.save_screenshot('c:/tmp/test.png')
     if 'site' in q:
         href = elmts[0].get_attribute('href')
@@ -80,8 +85,8 @@ def process_query(qs):
         if len(txt)>10:
             if domain in href:
                 print('clicked....')
-                print(href)
-                print(txt)
+                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()
@@ -89,7 +94,7 @@ def process_query(qs):
                 time.sleep(5)
                 break
         idx+=1
-
+    db.close()
 def run_once(q):
     global driver
     result=[]
@@ -108,7 +113,6 @@ def run_once(q):
     driver.delete_all_cookies()
     driver.set_window_size(1400,1000)
 
-    print('到此')
     process_query(q)
     time.sleep(3)
     driver.quit()
@@ -126,7 +130,6 @@ def run_once(q):
 class JParams(object):
 
   def get(self, kw,domain,port):
-    print('關鍵字',kw)
     run_once( (kw,domain,port)   )
 
 

INNNews/run_sheet_2.py

@@ -22,7 +22,7 @@ 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!="毛怪"')
+    cursor = db.query('select term, domain from seo.selected_kw where client not in ("毛怪")')
     for c in cursor:
         lst.append([c['term'], c['domain']])
     
@@ -38,7 +38,7 @@ def run_once(pport, dockername):
     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')
@@ -59,7 +59,7 @@ def run_specific(pport, dockername):
     if intval == -1:
         print('-1')
         sys.exit()
-
+    db.close()
 
 class JParams(object):
     

INNNews/run_sns.py

@@ -22,7 +22,7 @@ def run_once(pport, dockername):
     db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
     lst = []
     
-    cursor = db.query('select term, url, client from seo.sns_kw')
+    cursor = db.query('select * from seo.sns_kw')
     for c in cursor:
         lst.append([c['term'], c['url'], c['client'], c['domain']])
     
@@ -40,20 +40,20 @@ def run_once(pport, dockername):
     if intval == -1:
         print('-1')
         sys.exit()
-
+    db.close()
 
 class JParams(object):
     
     def get(self, port=9222):
         while True:
             try:
-                os.system('docker container restart tiny6')
+                os.system('docker container restart tiny7')
                 time.sleep(1)
-                run_once(9927, 'tiny6')
+                run_once(9928, 'tiny7')
                 time.sleep(20)
                 break
             except:
-                os.system('docker container restart tiny6')
+                os.system('docker container restart tiny7')
                 time.sleep(15)
 
 if __name__ == '__main__':

INNNews/sns_clickbot.py

@@ -23,8 +23,6 @@ import fire
 #pymysql.install_as_MySQLdb()
 
 
-db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
-table=db['sns_log']
 driver = None
 
 
@@ -49,6 +47,8 @@ def empty_query(q):
 
 
 def process_query(qs):
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    table=db['sns_log']
     q=qs[0]
     url=qs[1]
     client=qs[2]
@@ -82,7 +82,7 @@ def process_query(qs):
                 time.sleep(5)
                 break
         idx+=1
-
+    db.close()
 def run_once(q):
     global driver
     s = Service('/root/driver/chromedriver')

SEO/news_clickbot.py

@@ -53,10 +53,12 @@ def restart_browser(pport):
 
 def process_one(pport):
     db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
-    lst = ['好睡王 引新聞','好睡王 Yahoo','好睡王 HiNet','好睡王 PCHOME','好睡王 蕃新聞','好睡王 新浪','好睡王 台北郵報','好睡王 LIFE.tw','好睡王 match生活網','好睡王炎炎夏日 POPDAILY','好睡王 LINE TODAY']
+    lst = []
     table = db['news_log']
-
-    for term in lst[7::]:
+    cursor = db.query("select * from seo.news_kw")
+    for c in cursor:
+        lst.append([c['term']])
+    for term in lst:
         print(term)
         logger.debug('[clickbot_100][' + term + ']')
         driver = restart_browser(pport)

choozmo/ads_csv_gdn.py

@@ -0,0 +1,100 @@
+import csv
+import sys
+import codecs
+import pandas as pd
+
+with codecs.open('/Users/zooeytsai/Documents/220628有夠讚GDN.csv', 'r', 'utf-16') as csvfile:
+    spamreader = csv.reader(csvfile, delimiter='\t', quotechar='|')
+    # df = pd.read_csv('/Users/zooeytsai/Documents/220628有夠讚GDN.csv', encoding='utf16')
+    kwdict = {}
+    addict = {}
+    d = {}
+    head = True
+    for row in spamreader:
+        # print(row)
+        if head:
+            head = False
+            continue
+        ll = len(row)
+        campaign = row[0]
+        adgroup = row[19]
+        # print(adgroup)
+        kw = row[47]
+
+        # if len(kw) > 0:
+            # print(campaign)
+            # print(adgroup)
+        if kwdict.get(adgroup) is None:
+            kwdict[adgroup] = []
+        if addict.get(adgroup) is None:
+            addict[adgroup] = []
+        if d.get(adgroup) is None:
+            d[adgroup] = []
+        kwdict[adgroup].append(kw)
+
+        for i in range(59, 65): #加了Long headline
+            hline = row[i]
+            # print(hline)
+            if len(hline) > 0:
+                print(addict[adgroup])
+                addict[adgroup].append(hline)
+        for i in range(65, 67):
+            hline = row[i]
+            # print(i, hline)
+            if len(hline) > 0:
+                d[adgroup].append(hline)
+        # print(addict)
+fw = codecs.open('/Users/zooeytsai/Documents/有夠讚GDN廣告datastudio.csv', 'w', 'utf-8')
+fw.write("活動,群組,關鍵字,廣告標題,廣告內容")
+for k, v in kwdict.items():
+    kwlen = len(v)
+    adlen = len(addict[k])
+    totlen = max(kwlen, adlen)
+    for i in range(totlen):
+        print(campaign)
+        try:
+            kw = v[i]
+        except:
+            kw = ' '
+        try:
+            ad = addict[k][i]
+            # print(ad)
+        except:
+            ad = ' '
+        try:
+            ad1 = d[k][i]
+            # print(ad)
+        except:
+            ad1 = ' '
+        data = "\n" + campaign + "," + k + "," + kw + "," + ad + "," + ad1
+        fw.write(data)
+
+fw.close()
+
+#    for k,v in addict.items():
+#        print('rectangle '+k+'_ad'+' {')
+#        print('card '+k+'廣告'+' [')
+
+#        for itm in v:
+#            print(itm)
+#        print(']')
+#        print('}')
+
+
+#        print(campaign+' -[#black]-> '+k+'_ad')
+
+
+#    print(kwdict)
+#    print(addict)
+
+
+#    for row in spamreader:
+#        ll=len(row)
+#
+#        for i in range(ll):
+#            print(i)
+#            print(row[i])
+#        break
+
+#
+#    sys.exit()

choozmo/ads_csv_local.py

@@ -0,0 +1,96 @@
+import csv
+import sys
+import codecs
+import pandas as pd
+
+with codecs.open('/Users/zooeytsai/Documents/220704有夠讚地標廣告.csv', 'r', 'utf-16') as csvfile:
+    spamreader = csv.reader(csvfile, delimiter='\t', quotechar='|')
+    # df = pd.read_csv('/Users/zooeytsai/Documents/220628有夠讚GDN.csv', encoding='utf16')
+    kwdict = {}
+    addict = {}
+    campagindict = {}
+    d = {}
+    head = True
+    for row in spamreader:
+        # print(row)
+        if head:
+            head = False
+            continue
+        ll = len(row)
+        campaign = row[0]
+        adgroup = row[18]
+        # print(adgroup)
+        # print(adgroup)
+        # kw = row[47]
+
+        # if len(kw) > 0:
+            # print(campaign)
+            # print(adgroup)
+        if kwdict.get(adgroup) is None:
+            kwdict[adgroup] = []
+        if addict.get(adgroup) is None:
+            addict[adgroup] = []
+        if d.get(adgroup) is None:
+            d[adgroup] = []
+        # kwdict[adgroup].append(kw)
+
+        for i in range(54, 59): #headline
+            hline = row[i]
+            # print(hline)
+            if len(hline) > 0:
+                # print(addict[adgroup])
+                addict[adgroup].append(hline)
+        for i in range(59, 64): #Description
+            hline = row[i]
+            # print(i, hline)
+            if len(hline) > 0:
+                d[adgroup].append(hline)
+    # print(addict)
+fw = codecs.open('/Users/zooeytsai/Documents/有夠讚地標廣告datastudio.csv', 'w', 'utf-8')
+fw.write("群組,廣告標題,廣告內容")
+
+
+for k,v in addict.items():
+    for i in range(len(v)):
+        try:
+            ad = addict[k][i]
+            # print(ad)
+        except:
+            ad = ' '
+        try:
+            ad1 = d[k][i]
+            print(ad1)
+        except:
+            ad1 = ' '
+        data = "\n" + k + "," + ad + "," + ad1
+        fw.write(data)
+
+fw.close()
+
+#    for k,v in addict.items():
+#        print('rectangle '+k+'_ad'+' {')
+#        print('card '+k+'廣告'+' [')
+
+#        for itm in v:
+#            print(itm)
+#        print(']')
+#        print('}')
+
+
+#        print(campaign+' -[#black]-> '+k+'_ad')
+
+
+#    print(kwdict)
+#    print(addict)
+
+
+#    for row in spamreader:
+#        ll=len(row)
+#
+#        for i in range(ll):
+#            print(i)
+#            print(row[i])
+#        break
+
+#
+#    sys.exit()