爬虫Selenium

-----启动浏览器，打开网页-----

from selenium import webdriver

# 指定webdive 存放位置
path = r'D:\Courses\P9s\selenium\edgedriver_win64\msedgedriver.exe'
# 实例化一个浏览器驱动对象(edge、chrome或者其他)
# 首字母大写

browser = webdriver.Edge(path)

# 打开指定的网页url
browser.get("https://www.baidu.com")

-----截图、关闭浏览器-----

from selenium import webdriver

path = r'D:\Courses\P9s\selenium\edgedriver_win64\msedgedriver.exe'
browser = webdriver.Edge(path)
browser.get('https://www.baidu.com')
# 截图预览
browser.get_screenshot_as_file('截图.png')
browser.close()

-----打开百度，搜索框输入内容，点击搜索-----

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys

path = r'D:\Courses\P9s\selenium\edgedriver_win64\msedgedriver.exe'
browser = webdriver.Edge(path)
browser.get('https://www.baidu.com')
ele = browser.find_element(By.ID, 'kw')  # 搜索框
ele.send_keys('世界杯' + Keys.RETURN)

-----爬取技术博客-----

from selenium import webdriver
from selenium.webdriver.common.by import By

wd = webdriver.Edge()
wd.get('https://v3u.cn/l_id_1')
articles = wd.find_elements(By.CSS_SELECTOR, 'body>div>section>div>div.col-md-8>articles.blog-post')
for article in articles:
    if article.find_element(By.CSS_SELECTOR, 'article>div>h2>a'):
        title = article.find_element(By.CSS_SELECTOR, "article > div > h2 > a").text
        link = article.find_element(By.CSS_SELECTOR, "article > div > h2 > a").get_attribute("href")
        print(title, '---', link)

-----反爬--识别selenium+webdriver-----

webdriver = window.navigator.webdriver;
if(webdriver){
    console.log('你这个xx,你以为使用Selenium模拟浏览器，我就不能发现你吗?')
    //执行封禁、拉黑代码。。。。
} else {
    console.log('正常浏览器')
}

-----使用版本的推荐方法 **find_element()**
**使用的时候需要导入模块  \**from selenium.webdriver.common.by import By\****
属性定位方法
原定位方法find_element_by_*
推荐定位方法find_element()-----

xpath

find_element_by_xpath("//*[@id='search']")

find_element(By.XPATH, "//*[@id='search']")

class_name

find_element_by_class_name("element_class_name")

find_element(By.CLASS_NAME, "element_class_name")

id

find_element_by_id("element_id")

find_element(By.ID,"element_id")

name

find_element_by_name("element_name")

find_element(By.NAME, "element_name")

link_text

find_element_by_link_text("element_link_text")

find_element(By.LINK_TEXT,"element_link_text")

css_selector

find_element_by_css_selector("element_css_selector")

find_element(By.CSS_SELECTOR, "element_css_selector")

tag_name

find_element_by_tag_name("element_tag_name")

find_element(By.TAG_NAME, "element_tag_name")

partial_link_text

ind_element_by_partial_link_text("element_partial_link_text")

find_element(By.PARTIAL_LINK_TEXT, "element_partial_link_text")