|
求大神帮忙看一下
import time
from selenium import webdriver
from bs4 import BeautifulSoup
from selenium.webdriver.common.action_chains import ActionChains
def search(keys):
driver=webdriver.Chrome()
driver.maximize_window()
#打开google,搜索关键词,并点击搜索结果第1个
try:
driver.get('https://www.google.com/search?q='+ keys+'&rlz=1C1CHBF_enUS886US886&oq='+keys+'&aqs=chrome.0.69i59j69i60.4967j0j15&sourceid=chrome&ie=UTF-8')
time.sleep(2)
driver.find_element_by_css_selector('div>h3>a').get_attribute("href")
#打印搜索结果的尺寸,文本,并进入第一条记录
except:
tem=' '
else:
tem = driver.find_element_by_css_selector('div>h3>a').get_attribute("href")
driver.close()
return tem
import pandas as pd
url = []
df = pd.read_excel('实验2.xlsx',index_col=0)
for i in range(len(df)):
keys = df.iloc[i,0]+' '+df.iloc[i,1]
url.append(search(keys))
df['website'] = url
df.to_excel('final123.xlsx')
最后excel里面只有website,但是这一列下面没有数据 |
|