爬虫选择器使用selenium

1 xpath的使用

# html中选择标签,可以使用的通用方式
	-css选择
    -xpath选择
    	-XPath即为XML路径语言(XML Path Language),它是一种用来确定XML文档中某部分位置的语言
# 语法的简单介绍
	-nodename	选取此节点的所有子节点
    -/	        从根节点选取    /body/div
    -//        从匹配选择的当前节点选择文档中的节点,而不考虑它们的位置  //div
    -.	       选取当前节点。
	-..	      选取当前节点的父节点。
	-@	      选取属性。
    
# 终极大招
	-复制
    
# 案例

doc='''
<html>
 <head>
  <base href='http://example.com/' />
  <title>Example website</title>
 </head>
 <body>
  <div id='images'>
   <a href='image1.html' id='id_a'>Name: My image 1 <br/><img src='image1_thumb.jpg' /></a>
   <a href='image2.html'>Name: My image 2 <br /><img src='image2_thumb.jpg' /></a>
   <a href='image3.html'>Name: My image 3 <br /><img src='image3_thumb.jpg' /></a>
   <a href='image4.html'>Name: My image 4 <br /><img src='image4_thumb.jpg' /></a>
   <a href='image5.html' class='li li-item' name='items'>Name: My image 5 <br /><img src='image5_thumb.jpg' /></a>
   <a href='image6.html' name='items'><span><h5>test</h5></span>Name: My image 6 <br /><img src='image6_thumb.jpg' /></a>
  </div>
 </body>
</html>
'''

from lxml import etree

html=etree.HTML(doc)
# html=etree.parse('search.html',etree.HTMLParser())
# 1 所有节点
# a=html.xpath('//*')
# 2 指定节点(结果为列表)
# a=html.xpath('//head')

# 3 子节点,子孙节点
# a=html.xpath('//div/a')
# a=html.xpath('//body/a') #无数据
# a=html.xpath('//body//a')
# 4 父节点
# a=html.xpath('//body//a[@href="image1.html"]/..')
# a=html.xpath('//body//a[1]/..')
# 也可以这样
# a=html.xpath('//body//a[1]/parent::*')
# a=html.xpath('//body//a[1]/parent::div')
# 5 属性匹配
# a=html.xpath('//body//a[@href="image1.html"]')

# 6 文本获取  text()    ********
# a=html.xpath('//body//a[@href="image1.html"]/text()')

# 7 属性获取            ******
# a=html.xpath('//body//a/@href')
# a=html.xpath('//body//a/@id')
# # 注意从1 开始取(不是从0)
# a=html.xpath('//body//a[1]/@id')
# 8 属性多值匹配
#  a 标签有多个class类,直接匹配就不可以了,需要用contains
# a=html.xpath('//body//a[@class="li"]')
# a=html.xpath('//body//a[@name="items"]')
# a=html.xpath('//body//a[contains(@class,"li")]')
# a=html.xpath('//body//a[contains(@class,"li")]/text()')
# 9 多属性匹配
# a=html.xpath('//body//a[contains(@class,"li") or @name="items"]')
# a=html.xpath('//body//a[contains(@class,"li") and @name="items"]/text()')

# 10 按序选择
# a=html.xpath('//a[2]/text()')
# a=html.xpath('//a[3]/@href')
# 取最后一个
# a=html.xpath('//a[last()]/@href')
# 位置小于3的
# a=html.xpath('//a[position()<3]/@href')
# 倒数第二个
# a=html.xpath('//a[last()-2]/@href')
# 11 节点轴选择
# ancestor:祖先节点
# 使用了* 获取所有祖先节点
# a=html.xpath('//a/ancestor::*')
# # 获取祖先节点中的div
# a=html.xpath('//a/ancestor::div')
# attribute:属性值
# a=html.xpath('//a[1]/attribute::*')
# a=html.xpath('//a[1]/attribute::href')
# child:直接子节点
# a=html.xpath('//a[1]/child::*')
# descendant:所有子孙节点
# a=html.xpath('//a[6]/descendant::*')

# following:当前节点之后所有节点
# a=html.xpath('//a[1]/following::*')
# a=html.xpath('//a[1]/following::*[1]/@href')
# following-sibling:当前节点之后同级节点
# a=html.xpath('//a[1]/following-sibling::*')
# a=html.xpath('//a[1]/following-sibling::a')
# a=html.xpath('//a[1]/following-sibling::*[2]')
a=html.xpath('//a[1]/following-sibling::*[2]/@href')

print(a)

2 selenium 动作链

# 网站中有些按住鼠标,滑动的效果
	-滑动验证码
    
    
# 两种形式
	-形式一:
        actions=ActionChains(bro) #拿到动作链对象
        actions.drag_and_drop(sourse,target) #把动作放到动作链中,准备串行执行
        actions.perform()
    -方式二:
    	ActionChains(bro).click_and_hold(sourse).perform()
    	distance=target.location['x']-sourse.location['x']
        track=0
        while track < distance:
            ActionChains(bro).move_by_offset(xoffset=2,yoffset=0).perform()
            track+=2

3 自动登录12306

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
from selenium.webdriver import ActionChains
from selenium.webdriver.chrome.options import Options

options = Options()
options.add_argument("--disable-blink-features=AutomationControlled")  # 去掉自动化控制的提示
bro = webdriver.Chrome(executable_path='./chromedriver.exe', options=options)

bro.get('https://kyfw.12306.cn/otn/resources/login.html')

bro.maximize_window()
# 12306检测到了我们使用了selenium控制了浏览器,所以它的滑块出不来
bro.implicitly_wait(10)

try:
    username = bro.find_element(by=By.ID, value='J-userName')
    username.send_keys('')
    password = bro.find_element(by=By.ID, value='J-password')
    password.send_keys('')
    time.sleep(3)
    btn = bro.find_element(by=By.ID, value='J-login')
    btn.click()
    span = bro.find_element(by=By.ID, value='nc_1_n1z')

    ActionChains(bro).click_and_hold(span).perform()  # 鼠标点主
    ActionChains(bro).move_by_offset(xoffset=300, yoffset=0).perform() #滑动

    time.sleep(10)

except Exception as e:
    print(e)

finally:
    bro.close()

4 打码平台使用

# 咱们把验证码图片发给第三方,第三方帮咱们解决,我们只需要用钱就可以了

5 使用打码平台自动登录

import time

from selenium import webdriver
from selenium.webdriver.common.by import By
from chaojiying import ChaojiyingClient
from PIL import Image
bro = webdriver.Chrome(executable_path='./chromedriver.exe')
bro.get('http://www.chaojiying.com/apiuser/login/')
bro.implicitly_wait(10)
bro.maximize_window()
try:
    username = bro.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[1]/input')
    password = bro.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[2]/input')
    code = bro.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[3]/input')
    btn = bro.find_element(by=By.XPATH, value='/html/body/div[3]/div/div[3]/div[1]/form/p[4]/input')
    username.send_keys('306334678')
    password.send_keys('lqz123')
    # 获取验证码:
    #1 整个页面截图
    bro.save_screenshot('main.png')
    # 2 使用pillow,从整个页面中截取出验证码图片 code.png
    img = bro.find_element(By.XPATH, '/html/body/div[3]/div/div[3]/div[1]/form/div/img')
    location = img.location
    size = img.size
    print(location)
    print(size)
    # 使用pillow扣除大图中的验证码
    img_tu = (int(location['x']), int(location['y']), int(location['x'] + size['width']), int(location['y'] + size['height']))
    # # 抠出验证码
    # #打开
    img = Image.open('./main.png')
    # 抠图
    fram = img.crop(img_tu)
    # 截出来的小图
    fram.save('code.png')
    # 3 使用超级鹰破解
    chaojiying = ChaojiyingClient('306334678', 'lqz123', '937234')  # 用户中心>>软件ID 生成一个替换 96001
    im = open('code.png', 'rb').read()  # 本地图片文件路径 来替换 a.jpg 有时WIN系统须要//
    print(chaojiying.PostPic(im, 1902))  # 1902 验证码类型  官方网站>>价格体系 3.4+版 print 后要加()
    res_code=chaojiying.PostPic(im, 1902)['pic_str']
    code.send_keys(res_code)
    time.sleep(5)
    btn.click()
    time.sleep(10)
except Exception as e:
    print(e)
finally:
    bro.close()

6 使用selenium爬取京东商品信息

from selenium import webdriver
from selenium.webdriver.common.by import By  # 按照什么方式查找,By.ID,By.CSS_SELECTOR
import time
from selenium.webdriver.common.keys import Keys


def get_goods(driver):
    try:
        goods = driver.find_elements(by=By.CLASS_NAME, value='gl-item')
        for good in goods:
            name = good.find_element(by=By.CSS_SELECTOR, value='.p-name em').text
            price = good.find_element(by=By.CSS_SELECTOR, value='.p-price i').text
            commit = good.find_element(by=By.CSS_SELECTOR, value='.p-commit a').text
            url = good.find_element(by=By.CSS_SELECTOR, value='.p-name a').get_attribute('href')
            img = good.find_element(by=By.CSS_SELECTOR, value='.p-img img').get_attribute('src')
            if not img:
                img ='https://'+ good.find_element(by=By.CSS_SELECTOR, value='.p-img img').get_attribute('data-lazy-img')

            print('''
            商品名字:%s
            商品价格:%s
            商品链接:%s
            商品图片:%s
            商品评论:%s
            ''' % (name, price, url, img, commit))

        button = driver.find_element(by=By.PARTIAL_LINK_TEXT, value='下一页')
        button.click()
        time.sleep(1)
        get_goods(driver)
    except Exception as e:
        print(e)


def spider(url, keyword):
    driver = webdriver.Chrome(executable_path='./chromedriver.exe')
    driver.get(url)
    driver.implicitly_wait(10)  # 使用隐式等待
    try:
        input_tag = driver.find_element(by=By.ID, value='key')
        input_tag.send_keys(keyword)
        input_tag.send_keys(Keys.ENTER)
        get_goods(driver)
    finally:
        driver.close()


if __name__ == '__main__':
    spider('https://www.jd.com/', keyword='精品内衣')

posted @ 2022-12-06 20:26  懒羊羊A  阅读(127)  评论(0)    收藏  举报