kw_tools/SEO/feature_snippets.py

from selenium import webdriver
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.common.by import By
import urllib
import time
import csv
from random import randint
import dataset
import pandas as pd
import pymysql


def restart_browser():
    s = Service('/Users/zooeytsai/Downloads/chromedriver 4')
    options = webdriver.ChromeOptions()
    # options.add_argument("user-agent=%s" % rua())
    options.add_argument('--headless')
    options.add_argument("--incognito")
    driver = webdriver.Chrome(options=options, service=s)
    str1 = driver.capabilities['chrome']['chromedriverVersion'].split(' ')[0]
    print('這裡',str1)
    driver.delete_all_cookies()
    driver.set_window_size(950, 20000)
    return driver



def read_csv():
    lst = []
    df = pd.read_csv('/Users/zooeytsai/Documents/幸福空間FAQ關鍵字.csv')
    for i, row in df.iterrows():
        lst.append(row['熱門查詢項目'])
    return lst

lst = read_csv()
for term in lst:
    print(term)
    driver = restart_browser()
    escaped_search_term = urllib.parse.quote(term)
    googleurl = 'https://www.google.com/search?q={}&num={}&hl={}'.format(escaped_search_term, 20, 'zh-TW')
    
    driver.get(googleurl)
    print(driver.current_url)
    time.sleep(6)
    
    # df = pd.DataFrame()
    
    elmts = driver.find_elements(By.XPATH,
                                 '/html/body/div[7]/div/div[10]/div/div[2]/div[2]/div/div/div[1]/div/block-component/div/div[1]/div/div/div/div/div[1]/div/div/div/div/div/div[2]/div/div/div[1]/a')
    
    datalist = []
    print(len(elmts))
    for elmt in elmts:
        href = elmt.get_attribute('href')
        txt = elmt.text
        print(txt)
        
        datalist.append([term, elmt.text, href])
    
    with open('/Users/zooeytsai/Documents/幸福空間FAQ統計2.csv', 'a') as f:
        writer = csv.writer(f)
        for i in datalist:
            print(i)
            writer.writerow(i)
    
    driver.quit()
    
    print('中場休息')
    time.sleep(randint(45, 50))