廣告爬取

choozmo/ads_selenium.py

@@ -0,0 +1,99 @@
+import time
+import json
+from selenium.webdriver.common.desired_capabilities import DesiredCapabilities
+import os
+import urllib.parse
+from selenium.webdriver.support.ui import WebDriverWait
+from selenium import webdriver
+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 pymysql
+pymysql.install_as_MySQLdb()
+
+driver = None
+
+
+def process_query(qs):
+    db = dataset.connect('mysql://choozmo:pAssw0rd@db.ptt.cx:3306/seo?charset=utf8mb4')
+    table = db['ads']
+    q = qs[0]
+    client = qs[1]
+    global driver
+    googleurl = 'https://www.google.com/webhp?hl=zh-TW&sa=X&ved=0ahUKEwj84vXliMX4AhUYqFYBHcUMAlgQPAgI'
+    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_title = driver.find_elements(By.XPATH, "//div[@class='CCgQ5 vCa9Yd QfkTvb MUxGbd v0nnCb']/span")
+    elmts_content = driver.find_elements(By.XPATH, "//div[@class='MUxGbd yDYNvb lyLwlc']")
+    print(len(elmts_title))
+    print(len(elmts_content))
+    
+    for i, j in zip(elmts_title,elmts_content):
+        title = i.text
+        content = j.text
+        
+        table.insert({'kw': q, 'client': client, 'title': title, 'content': content,
+                              'dt': datetime.datetime.now()})
+
+    db.close()
+
+
+def run_once(q):
+    global driver
+    result = []
+    user_agent = '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'
+    s = Service('/Users/zooeytsai/Downloads/chromedriver 4')
+    op = 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")
+    op.add_argument('--disable-dev-shm-usage')
+    op.add_argument('--no-sandbox')
+    op.add_argument(r'user-data-dir=C:\Users\Administrator\AppData\Local\Google\Chrome\User Data')
+    op.add_argument(f"profile-directory=Profile 25")
+    op.add_experimental_option("excludeSwitches", ["enable-automation"])
+    op.add_experimental_option('useAutomationExtension', False)
+    driver = webdriver.Chrome(options=op,
+                              executable_path=r'C:\Users\Administrator\Downloads\chromedriver_win32 (4)\chromedriver')
+    
+    driver = webdriver.Chrome(
+        options=op, service=s)
+    str1 = driver.capabilities['browserVersion']
+    print('版本', str1)
+    driver.delete_all_cookies()
+    driver.set_window_size(1400, 1000)
+    
+    print(q)
+    process_query(q)
+    time.sleep(3)
+    driver.quit()
+
+
+class JParams(object):
+    
+    def get(self, kw, domain):
+        print(kw)
+        print(domain)
+        run_once((kw, domain))
+
+
+if __name__ == '__main__':
+    # fire.Fire(JParams)
+    run_once(('新北 家具 推薦','班尼斯'))