python 定时自动爬取_python 定时抓取

from selenium.webdriver.common.keys import Keys from selenium import webdriver import pandas as pd import time #driver = webdriver.Chrome() driver = webdriver.Firefox() def getPage(driver): data=[] driver.get("url") #driver.page_source element=driver.find_element_by_css_selector('html') html=element.get_attribute('outerHTML') #do sonme analyze c=element.find_elements_by_css_selector(".jiedian") index=0 for i in c: if i.find_elements_by_css_selector(".ec-tuiguang") and i.find_elements_by_css_selector(".ec_title"): t=i.find_element_by_css_selector(".ec_title h3") u=i.find_element_by_css_selector("span.c-showurl") item=[time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()),str(index),t.text,u.text] data.append(item) print "/".join(item) index+=1 return data allData=[] for j in range(0,10): d=getPage(driver) allData.extend(d) time.sleep(10) df=pd.DataFrame(allData,columns=['time','index','title','url']) df.to_csv("data.csv",encoding='utf8',index=False) driver.close()