xpath selenium scrapy

Posted 2023-03-20 DragonY

0 selenium 登录cnblogs

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

bro = webdriver.Chrome(executable_path=\'./chromedriver.exe\')

try:
    ####1 获取cookie
    # bro.get(\'https://www.cnblogs.com/\')
    # bro.implicitly_wait(10)
    # login_btn = bro.find_element(by=By.LINK_TEXT, value=\'登录\')
    # login_btn.click()
    # username = bro.find_element(By.ID, \'mat-input-0\')
    # password = bro.find_element(By.ID, \'mat-input-1\')
    # submit_btn = bro.find_element(By.CSS_SELECTOR,
    #                               \'body > app-root > app-sign-in-layout > div > div > app-sign-in > app-content-container > div > div > div > form > div > button\')
    # username.send_keys(\'[e-mail]\')
    # # 手动输入密码，手动点击登录 搞好验证码，都成功，敲回车
    # input()
    #
    # # 取出cookies
    # cookie = bro.get_cookies()
    # print(cookie)
    # # 保存到本地文件
    # with open(\'cnblogs.json\', \'w\', encoding=\'utf-8\') as f:
    #     json.dump(cookie, f)

    ### 2 打开首页
    bro.get(\'https://www.cnblogs.com/\')  # 没有登录状态
    bro.implicitly_wait(10)
    time.sleep(2)
    # 打开本地的cookie的json文件
    with open(\'cnblogs.json\', \'r\', encoding=\'utf-8\') as f:
        cookies = json.load(f)
    for cookie in cookies:
        bro.add_cookie(cookie)

    bro.refresh()  # 刷新

    time.sleep(5)

except Exception as e:
    print(e)

finally:
    bro.close()

1 抽屉半自动点赞

# 1 使用selenium 半自动登录---》取到cookie
# 2 使用requests模块，解析出点赞的请求地址---》模拟发送请求---》携带cookie

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
import json
import requests

# bro = webdriver.Chrome(executable_path=\'./chromedriver.exe\')

try:

    ####1 先登录，获取cookie
    # bro.get(\'https://dig.chouti.com/\')
    # bro.maximize_window()
    # bro.implicitly_wait(10)
    #
    # login_btn = bro.find_element(By.LINK_TEXT, \'登录\')
    # # login_btn.click() # 会报错，不能这么点击了
    #
    # # 使用js点击它,把传入的对象，点击一下
    # bro.execute_script("arguments[0].click()", login_btn)
    # time.sleep(3)
    #
    # username = bro.find_element(By.CSS_SELECTOR,
    #                             \'body > div.login-dialog.dialog.animated2.scaleIn > div > div.login-body > div.form-item.login-item.clearfix.phone-item.mt24 > div.input-item.input-item-short.left.clearfix > input\')
    # password = bro.find_element(By.NAME, \'password\')
    #
    # username.send_keys(\'18953675221\')
    # password.send_keys(\'lqz123\')
    # time.sleep(1)
    # submit_btn = bro.find_element(By.CSS_SELECTOR,
    #                               \'body > div.login-dialog.dialog.animated2.scaleIn > div > div.login-footer > div:nth-child(4) > button\')
    # submit_btn.click()
    #
    # input(\'\')  # 万一有验证码，手动操作一下
    # with open(\'chouti.json\', \'w\', encoding=\'utf-8\') as f:
    #     json.dump(bro.get_cookies(), f)

    ### 使用request模拟点赞，携带cookie
    # 先把cookie打开
    with open(\'chouti.json\', \'r\', encoding=\'utf-8\') as f:
        cookies = json.load(f)

    # selenium 的cookie不能直接给requests模块使用，需要额外处理一下

    request_cookies = 
    for cookie in cookies:
        request_cookies[cookie[\'name\']] = cookie[\'value\']

    print(request_cookies)
    headers = 
        \'User-Agent\': \'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/111.0.0.0 Safari/537.36\'
    
    res = requests.get(\'https://dig.chouti.com/top/24hr?_=1679277434856\', headers=headers)

    for item in res.json().get(\'data\'):
        id_link = item.get(\'id\')
        data = 
            \'linkId\': id_link
        
        res2 = requests.post(\'https://dig.chouti.com/link/vote\', headers=headers, data=data, cookies=request_cookies)
        print(res2.text)

except Exception as e:
    print(e)

finally:
    # bro.close()
    pass

2 xpath的使用

# 每个解析器，都会有自己的查找方法
	-bs4  find 和find_all
    -selenium  find_element和 find_elements 
    -lxml 也是个解析器，支持xpath和css
# 这些解析器，基本上都会支持两种统一的 css和xpath
	-css咱们会了
    -xpath需要学习
    
    
    
# xpath是什么？
	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
    
    
# 有终极大招，只需要记住几个用法就可以了
	- /     从当前路径下开始找 
    - /div  从当前路径下开始找div
    -//     递归查找，子子孙孙
    -//div  递归查找div
    -@      取属性
    - .    当成
    - ..   上一层
    
    

3 selenium 动作链

# 人可以滑动某些标签

# 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

3.1 动作链案例

import time

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By  # 按照什么方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys  # 键盘按键操作
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait  # 等待页面加载某些元素

try:
    browser = webdriver.Chrome(executable_path=\'./chromedriver.exe\')
    browser.get(\'http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable\')

    browser.switch_to.frame(\'iframeResult\')  # 切换到id为iframeResult的frame

    target = browser.find_element(By.ID, \'droppable\')  # 目标
    source = browser.find_element(By.ID, \'draggable\')  # 源

    # 方案1
    # actions = ActionChains(browser)  # 拿到动作链对象
    # actions.drag_and_drop(source, target)  # 把动作放到动作链中，准备串行执行
    # actions.perform()



    # 方案2
    # ActionChains(browser).click_and_hold(source).perform()
    # distance = target.location[\'x\'] - source.location[\'x\']
    # track = 0
    # while track < distance:
    #     ActionChains(browser).move_by_offset(xoffset=2, yoffset=0).perform()
    #     track += 2

    time.sleep(2)





finally:
    browser.close()

4 自动登录12306

# selenium自动登录12306

import time

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By  # 按照什么方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys  # 键盘按键操作
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait  # 等待页面加载某些元素
from selenium.webdriver.chrome.options import Options

try:
    options = Options()
    options.add_argument("--disable-blink-features=AutomationControlled")  # 去掉自动化控制
    browser = webdriver.Chrome(executable_path=\'./chromedriver.exe\', chrome_options=options)
    browser.get(\'https://kyfw.12306.cn/otn/resources/login.html\')
    browser.maximize_window()
    username = browser.find_element(By.ID, \'J-userName\')
    password = browser.find_element(By.ID, \'J-password\')
    username.send_keys(\'\')
    password.send_keys(\'\')
    login_btn = browser.find_element(By.ID, \'J-login\')

    time.sleep(2)
    login_btn.click()
    time.sleep(5)

    span = browser.find_element(By.ID, \'nc_1_n1z\')
    ActionChains(browser).click_and_hold(span).perform()
    ActionChains(browser).move_by_offset(xoffset=300, yoffset=0).perform()

    # 滑动完成了，但是进不去，原因是它检测到我们使用了selenium，屏蔽掉
    time.sleep(3)

finally:
    browser.close()

5 打码平台使用

# 登录网站，会有些验证码，可以借助于第三方的打码平台，破解验证码，只需要花钱解决

# 免费的：纯数字，纯字母的----》python有免费模块破解，失败率不高
# 云打码，超级鹰(以它为例)

# 云打码：https://zhuce.jfbym.com/price/


# 价格体系：破解什么验证码，需要多少钱
	http://www.chaojiying.com/price.html

6 使用打码平台自动登录

# 使用selenium打开页面---》截取整个屏幕----》使用pillow---》根据验证码图片位置，截取出验证码图片---》使用第三方打码平台破解---》写入到验证码框中，点击登录
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()

7 使用selenium爬取京东商品信息

import time

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys  # 键盘按键操作


def get_goods(bro):
    # 找到所有类名叫gl-item 的li标签
    li_list = bro.find_elements(By.CLASS_NAME, \'gl-item\')
    for li in li_list:
        try:
            img_url = li.find_element(By.CSS_SELECTOR, \'.p-img img\').get_attribute(\'src\')
            if not img_url:
                img_url = \'https:\' + li.find_element(By.CSS_SELECTOR, \'.p-img img\').get_attribute(\'data-lazy-img\')
            price = li.find_element(By.CSS_SELECTOR, \'.p-price i\').text
            name = li.find_element(By.CSS_SELECTOR, \'.p-name a\').text
            url = \'https:\' + li.find_element(By.CSS_SELECTOR, \'.p-img a\').get_attribute(\'href\')
            commit = li.find_element(By.CSS_SELECTOR, \'.p-commit a\').text
            print(\'\'\'
            商品图片地址：%s
            商品地址：%s
            商品名字：%s
            商品价格：%s
            商品评论数：%s
            \'\'\' % (img_url, url, name, price, commit))
        except Exception as e:
            print(e)
            continue

    # 查找下一页，点击，在执行get_goods
    next = bro.find_element(By.PARTIAL_LINK_TEXT, \'下一页\')
    time.sleep(1)
    next.click()
    get_goods(bro)


try:
    bro = webdriver.Chrome(executable_path=\'./chromedriver.exe\')
    bro.get(\'http://www.jd.com\')
    bro.implicitly_wait(10)

    input_key = bro.find_element(By.ID, \'key\')
    input_key.send_keys(\'茅台\')
    input_key.send_keys(Keys.ENTER)  # 敲回车
    # 滑动屏幕到最底部
    bro.execute_script(\'scrollTo(0,5000)\')
    get_goods(bro)



except Exception as e:
    print(\'sasdfsadfasdfa\',e)
finally:
    bro.close()

8 scrapy介绍

# requsets  bs4 selenium  模块
 
# 框架 ：django ，scrapy--->专门做爬虫的框架，爬虫界的django，大而全，爬虫有的东西，它都自带


# 安装 （win看人品，linux，mac一点问题没有）
	-pip3.8 install  scrapy
    
    -装不上，基本上是因为twisted装不了，单独装
        1、pip3 install wheel #安装后，便支持通过wheel文件安装软件，wheel文件官网：https://www.lfd.uci.edu/~gohlke/pythonlibs
        3、pip3 install lxml
        4、pip3 install pyopenssl
        5、下载并安装pywin32：https://sourceforge.net/projects/pywin32/files/pywin32/
        6、下载twisted的wheel文件：http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted
        7、执行pip3 install 下载目录\\Twisted-17.9.0-cp36-cp36m-win_amd64.whl
        8、pip3 install scrapy
        
        
        
# 架构分析
	-爬虫：spiders(自己定义的，可以有很多)，定义爬取的地址，解析规则
	-引擎：engine ---》控制整个框架数据的流动，大总管
    -调度器：scheduler---》要爬取的 requests对象，放在里面，排队
    -下载中间件：DownloaderMiddleware---》处理请求对象，处理响应对象
    -下载器：Downloader ----》负责真正的下载，效率很高，基于twisted的高并发的模型之上
    
    -爬虫中间件：spiderMiddleware----》处于engine和爬虫直接的(用的少)
    -管道：piplines---》负责存储数据
    
    
    
    
# 创建出scrapy项目
	scrapy startproject firstscrapy  # 创建项目
    scrapy genspider 名字 网址        # 创建爬虫   等同于 创建app
    
    # pycharm打开