chromedriver与chrome的的对应版整理:
这个链接比较新一点
chromedriver版本 chrome版本
v2.9 v31-v34
v2.10 v33-v36
v2.11 v36-v40
v2.12 v38-v41
v2.14 v39-v42
v2.15 v40-v43
v2.16 v42-v45
v2.17 v42-v43
v2.18 v43-v46
v2.19 v43-v47
v2.20 v43-v48
v2.21 v46-v50
v2.22 v49-v52
v2.23 v51-v53
v2.24 v52-v54
v2.25 v53-v55
v2.26 v53-v55
v2.27 v54-v56
v2.28 v55-v57
v2.29 v56-v58
v2.30 v58-v60
v2.31 v58-v60
v2.32 v59-v61
v2.33 v60-v62
v2.34 v61-v63
v2.35 v62-v64
v2.36 v63-v65
v2.37 v63-v66
v2.38 v65-v67
v2.39 v66-v68
v2.40 v66-v68
chromedriver驱动下载地址:
http://chromedriver.storage.googleapis.com/index.html
同时提供geckodriver和iedriverserver的下载地址:
geckodriver:
https://github.com/mozilla/geckodriver/releases
iedriverserver:
http://selenium-release.storage.googleapis.com/index.html
msedgedriver:
Microsoft Edge WebDriver - Microsoft Edge Developer
注意:
firefox56以下不需要安装webdriver驱动,firefox57(firefox47及以上版本)需要安装geckodriver-v0.19.1-win32/64。
IEDriverServer的版本号和Selenium的版本号一定要一致
使用selenium去调用浏览器,需要一个驱动,浏览器的webdriver需要独立安装,
如果是chrome在浏览器输入框输入chrome://version/ 查看相应版本,
http://npm.taobao.org/mirrors/chromedriver/下载相应驱动即可
百度
# _*_ coding:utf-8 _*_ import time from selenium import webdriver from selenium.webdriver.chrome.service import Service from selenium.webdriver.common.by import By # 创建浏览器驱动对象 # 这行代码会打开一个空白的浏览器 driver = webdriver.Chrome() # 访问到项目所在的网址 driver.get("https://www.baidu.com") driver.maximize_window() # 最大化浏览器 time.sleep(1) # 找到页面上的搜索输入框 id="kw" # 找到元素以后,可以直接赋值给变量,再通过变量操作元素 # ele = driver.find_element_by_id("kw") # 旧版代码,新版用下面代码 ele = driver.find_element(By.ID, value='kw') ele.send_keys("韦神") # 对文本输入框输入内容 # 也可以直接操作元素, 百度一下 按钮的 id="su" driver.find_element(By.ID, value="su").click() # # 但不能操作元素后再赋值给变量 # ele = driver.find_element_by_id("su").click() # ele.click() # 相当于 None.click() # driver.quit()
京东:
# _*_ coding:gbk _*_ # 爬取 https://www.jd.com/ 京东图书 import csv import time from selenium import webdriver from selenium.webdriver.chrome.service import Service from selenium.webdriver.common.by import By # 创建浏览器驱动对象 # 这行代码会打开一个空白的浏览器 driver = webdriver.Chrome() # 京东所在网站 # 访问到项目所在的网址 driver.get("https://www.jd.com") # 输入需要查找的关键字 p_input = driver.find_element(By.ID, 'key') p_input.send_keys('python编程') # 找到输入框输入 time.sleep(1) # 点击搜素按钮 button=driver.find_element(By.CLASS_NAME,"button").click() time.sleep(1) all_book_info = [] num=200 head=['书名', '价格'] #csv文件的路径和名字 path='./book.csv' def write_csv(head,all_book_info,path): with open(path, 'w', newline='',encoding='gbk') as file: # utf-8 乱码建议用 gbk fileWriter = csv.writer(file) fileWriter.writerow(head) fileWriter.writerows(all_book_info) # 爬取一页 def get_onePage_info(num): driver.execute_script('window.scrollTo(0, document.body.scrollHeight);') time.sleep(2) # 书籍列表 J_goodsList = driver.find_element(By.ID, "J_goodsList") listbook = J_goodsList.find_elements(By.TAG_NAME, "li") for res in listbook: num = num-1 book_info = [] name =res.find_element(By.CLASS_NAME, "p-name").find_element(By.TAG_NAME, "em").text price = res.find_element(By.CLASS_NAME, "p-price").find_element(By.TAG_NAME, "i").text book_info.append(name) book_info.append(price) # bookdetail = res.find_element(By.CLASS_NAME, "p-bookdetails") # author = bookdetail.find_element(By.CLASS_NAME, "p-bi-name").find_element(By.TAG_NAME, "a").text # store = bookdetail.find_element(By.CLASS_NAME, "p-bi-store").find_element(By.TAG_NAME, "a").text # book_info.append(author) # book_info.append(store) all_book_info.append(book_info) if num==0: break return num while num!=0: num = get_onePage_info(num) driver.find_element(By.CLASS_NAME, 'pn-next').click() # 点击下一页 time.sleep(2) write_csv(head, all_book_info, path) # driver.close()