python+selenium爬取微博热搜存入Mysql的实现方法

import requests
from selenium.webdriver import Chrome, ChromeOptions
import time
from sqlalchemy import create_engine
import pandas as pd

all = browser.find_elements_by_xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr/td[2]/a') #得到所有数据
	context = [i.text for i in c] # 得到标题内容
  links = [i.get_attribute('href') for i in c] # 得到link

dc = zip(dates, context, links)
  pdf = pd.DataFrame(dc, columns=['date', 'hotsearch', 'link'])

enging = create_engine("mysql+pymysql://root:123456@localhost:3306/webo")
pdf.to_sql(name='infromation', con=enging, if_exists="append")

from selenium.webdriver import Chrome, ChromeOptions
import time
from sqlalchemy import create_engine
import pandas as pd

def get_data():
  url = r"https://s.weibo.com/top/summary" # 微博的地址
  option = ChromeOptions()
  option.add_argument('--headless')
  option.add_argument("--no-sandbox")
  browser = Chrome(options=option)
  browser.get(url)
  all = browser.find_elements_by_xpath('//*[@id="pl_top_realtimehot"]/table/tbody/tr/td[2]/a')
  context = [i.text for i in all]
  links = [i.get_attribute('href') for i in all]
  date = time.strftime("%Y-%m-%d-%H_%M_%S", time.localtime())
  dates = []
  for i in range(len(context)):
    dates.append(date)
  # print(len(dates),len(context),dates,context)
  dc = zip(dates, context, links)
  pdf = pd.DataFrame(dc, columns=['date', 'hotsearch', 'link'])
  # pdf.to_sql(name=in, con=enging, if_exists="append")
  return pdf

def w_mysql(pdf):
  try:
    enging = create_engine("mysql+pymysql://root:123456@localhost:3306/webo")
    pdf.to_sql(name='infromation', con=enging, if_exists="append")
  except:
    print('出错了')

if __name__ == '__main__':
  xx = get_data()
  w_mysql(xx)