from selenium import webdriver
from selenium.webdriver.support.ui import Select,WebDriverWait
from selenium.webdriver.common.action_chains import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.remote.webelement import WebElement
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from lxml import etree
import time
class LagouSpeider():
def __init__(self):
self.driver=webdriver.Chrome()
self.url="https://www.lagou.com/jobs/list_python?labelWords=&fromSearch=true&suginput="
self.position=[]
def run(self):
self.driver.get(self.url)
while True:
source = self.driver.page_source
WebDriverWait(driver=self.driver,timeout=10).until(
EC.presence_of_element_located((By.XPATH,'//div[@class="pager_container"]/span[last()]'))
selenium完美实现拉勾网爬虫
最新推荐文章于 2022-04-25 00:21:00 发布
本文介绍如何利用Selenium库进行动态网页爬取,以拉勾网为例,详细讲解设置webdriver、定位元素、模拟点击及数据提取等步骤,帮助读者掌握动态爬虫的实践技巧。
摘要由CSDN通过智能技术生成