爬虫请求库selenium（三）

一.介绍

selenium最初是一个自动化测试工具,而爬虫中使用它主要是为了解决requests无法直接执行JavaScript代码的问题

selenium本质是通过驱动浏览器，完全模拟浏览器的操作，比如跳转、输入、点击、下拉等，来拿到网页渲染之后的结果，可支持多种浏览器

from selenium import webdriver
browser=webdriver.Chrome()
browser=webdriver.Firefox()
browser=webdriver.PhantomJS()
browser=webdriver.Safari()
browser=webdriver.Edge() 

 

二.安装

1.有界面浏览器

#安装：selenium+chromedriver
pip3 install selenium
下载chromdriver.exe放到python安装路径的scripts目录中即可，注意最新版本是2.38，并非2.9
国内镜像网站地址：http://npm.taobao.org/mirrors/chromedriver/2.38/
最新的版本去官网找:https://sites.google.com/a/chromium.org/chromedriver/downloads

#验证安装
C:\Users\Administrator>python3
Python 3.6.1 (v3.6.1:69c0db5, Mar 21 2017, 18:41:36) [MSC v.1900 64 bit (AMD64)] on win32
Type "help", "copyright", "credits" or "license" for more information.
>>> from selenium import webdriver
>>> driver=webdriver.Chrome() #弹出浏览器
>>> driver.get('https://www.baidu.com')
>>> driver.page_source

#注意：
selenium3默认支持的webdriver是Firfox，而Firefox需要安装geckodriver
下载链接：https://github.com/mozilla/geckodriver/releases

 

2.无界面浏览器

在PhantomJS不再更新后，使用Chorme谷歌浏览器

#selenium:3.12.0
#webdriver:2.38
#chrome.exe: 65.0.3325.181（正式版本） （32 位）

from selenium import webdriver
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
chrome_options.add_argument('window-size=1920x3000') #指定浏览器分辨率
chrome_options.add_argument('--disable-gpu') #谷歌文档提到需要加上这个属性来规避bug
chrome_options.add_argument('--hide-scrollbars') #隐藏滚动条, 应对一些特殊页面
chrome_options.add_argument('blink-settings=imagesEnabled=false') #不加载图片, 提升速度
chrome_options.add_argument('--headless') #浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败
chrome_options.binary_location = r"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe" #手动指定使用的浏览器位置


driver=webdriver.Chrome(chrome_options=chrome_options)
driver.get('https://www.baidu.com')

print('hao123' in driver.page_source)

driver.close() #切记关闭浏览器，回收资源

 

三.基本使用

from selenium import webdriver
import time
from selenium.webdriver.common.keys import Keys #键盘按键操作
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
chrome_options.add_argument('window-size=1920x3000') #指定浏览器分辨率
chrome_options.add_argument('--disable-gpu') #谷歌文档提到需要加上这个属性来规避bug
chrome_options.add_argument('--hide-scrollbars') #隐藏滚动条, 应对一些特殊页面
chrome_options.add_argument('blink-settings=imagesEnabled=false') #不加载图片, 提升速度
chrome_options.add_argument('--headless') #浏览器不提供可视化页面. linux下如果系统不支持可视化不加这条会启动失败
# chrome_options.binary_location = r"C:\Program Files (x86)\Google\Chrome\Application\chrome.exe" #手动指定使用的浏览器位置


bro = webdriver.Chrome()
bro.get('http://www.baidu.com')

# print(bro.page_source)
# time.sleep(3)
# 拿到输入框
inp = bro.find_element_by_id('kw')
# 输入内容
inp.send_keys('美女')
inp.send_keys(Keys.ENTER)
time.sleep(3)
print(bro.page_source)
bro.close()

 

四.xpath选择器

1.基本选择器

#官网链接：http://selenium-python.readthedocs.io/locating-elements.html
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
import time

driver=webdriver.Chrome()
driver.get('https://www.baidu.com')
wait=WebDriverWait(driver,10)

try:
    #===============所有方法===================
    # 1、find_element_by_id   根据id找
    # 2、find_element_by_link_text     根据链接名字找到控件（a标签的文字）
    # 3、find_element_by_partial_link_text   根据链接名字找到控件（a标签的文字）模糊查询
    # 4、find_element_by_tag_name       根据标签名
    # 5、find_element_by_class_name     根据类名
    # 6、find_element_by_name           根据属性名
    # 7、find_element_by_css_selector   根据css选择器
    # 8、find_element_by_xpath          根据xpath选择
    # 强调：
    # 1、上述均可以改写成find_element(By.ID,'kw')的形式
    # 2、find_elements_by_xxx的形式是查找到多个元素，结果为列表

```
#===============示范用法===================
# 1、find_element_by_id
print(driver.find_element_by_id('kw'))

# 2、find_element_by_link_text
# login=driver.find_element_by_link_text('登录')
# login.click()

# 3、find_element_by_partial_link_text
login=driver.find_elements_by_partial_link_text('录')[0]
login.click()

# 4、find_element_by_tag_name
print(driver.find_element_by_tag_name('a'))

# 5、find_element_by_class_name
button=wait.until(EC.element_to_be_clickable((By.CLASS_NAME,'tang-pass-footerBarULogin')))
button.click()

# 6、find_element_by_name
input_user=wait.until(EC.presence_of_element_located((By.NAME,'userName')))
input_pwd=wait.until(EC.presence_of_element_located((By.NAME,'password')))
commit=wait.until(EC.element_to_be_clickable((By.ID,'TANGRAM__PSP_10__submit')))

input_user.send_keys('18611453110')
input_pwd.send_keys('xxxxxx')
commit.click()

# 7、find_element_by_css_selector
driver.find_element_by_css_selector('#kw')

# 8、find_element_by_xpath
```


    time.sleep(5)

finally:
    driver.close()

 

2.xpath选择器

doc='''
<html>
 <head>
  <base href='http://example.com/' />
  <title>Example website</title>
 </head>
 <body>
  <div id='images'>
   <a href='image1.html'>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)
# 1.所有节点
a = html.xpath('//*')

# 2.指定节点
a = html.xpath('//a')

# 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//img')

# 4.父节点
# a = html.xpath('//body//a[1]..')
a = html.xpath('//body//a[@href="image1.html"]/parent::*')

# 5.属性匹配
a = html.xpath('//body//a[@href="image2.html"]')

# 6.文本获取
a = html.xpath('//body//a[@href="image2.html"]/text()')

# 7.属性获取
# a[1]从1开始，不是从0开始
a = html.xpath('//body//a[1]/@href')

# 8.属性多值匹配，多个属性时
a = html.xpath('//body//a[@class="li"]')
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") or @name="items"]/text()')

# 10.按序选择
a = html.xpath('//a[6]/text()')
# 最后一个
a = html.xpath('//a[last()]/text()')
# 位置小于3的
a = html.xpath('//a[position()<5]/@href')
# 导数第三个
a = html.xpath('//a[last()-3]/@href')

# 11.节点轴选择
# 祖先节点ancestor
a = html.xpath('//img/ancestor::*')
# 获取指定节点
a = html.xpath('//img/ancestor::a')
# attribute:属性值
a = html.xpath('//a[5]/attribute::*')
# child:直接子节点
a = html.xpath('//a/child::img')
# descendant:所有子孙节点
a = html.xpath('//body/descendant::a')
# following:当前节点后的所有节点
a = html.xpath('//head/following::a')
a = html.xpath('//head/following::a/@href')
# following-sibling:当前节点后的同级节点
a = html.xpath('//a[1]/following-sibling::*[5]/@name')

print(a)

 

3.获取标签属性

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

browser=webdriver.Chrome()

browser.get('https://www.amazon.cn/')

wait=WebDriverWait(browser,10)
wait.until(EC.presence_of_element_located((By.ID,'cc-lm-tcgShowImgContainer')))

tag=browser.find_element(By.CSS_SELECTOR,'#cc-lm-tcgShowImgContainer img')

#获取标签属性，
print(tag.get_attribute('src'))

#获取标签ID，位置，名称，大小（了解）
print(tag.id)
print(tag.location)
print(tag.tag_name)
print(tag.size)

browser.close()

 

4.等待元素被加载

#1、selenium只是模拟浏览器的行为，而浏览器解析页面是需要时间的（执行css，js），一些元素可能需要过一段时间才能加载出来，为了保证能查找到元素，必须等待

#2、等待的方式分两种：
隐式等待：在browser.get（'xxx'）前就设置，针对所有元素有效
显式等待：在browser.get（'xxx'）之后设置，只针对某个元素有效

隐式等待

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

browser=webdriver.Chrome()

#隐式等待:在查找所有元素时，如果尚未被加载，则等10秒
browser.implicitly_wait(10)

browser.get('https://www.baidu.com')

input_tag=browser.find_element_by_id('kw')
input_tag.send_keys('美女')
input_tag.send_keys(Keys.ENTER)

contents=browser.find_element_by_id('content_left') #没有等待环节而直接查找，找不到则会报错
print(contents)

browser.close()

显式等待

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

browser=webdriver.Chrome()
browser.get('https://www.baidu.com')


input_tag=browser.find_element_by_id('kw')
input_tag.send_keys('美女')
input_tag.send_keys(Keys.ENTER)

#显式等待：显式地等待某个元素被加载
wait=WebDriverWait(browser,10)
wait.until(EC.presence_of_element_located((By.ID,'content_left')))

contents=browser.find_element(By.CSS_SELECTOR,'#content_left')
print(contents)

browser.close()

 

6.页面交互

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

browser=webdriver.Chrome()
browser.get('https://www.amazon.cn/')
wait=WebDriverWait(browser,10)



input_tag=wait.until(EC.presence_of_element_located((By.ID,'twotabsearchtextbox')))
input_tag.send_keys('iphone 8')
button=browser.find_element_by_css_selector('#nav-search > form > div.nav-right > div > input')
button.click()

import time
time.sleep(3)

input_tag=browser.find_element_by_id('twotabsearchtextbox')
input_tag.clear() #清空输入框
input_tag.send_keys('iphone7plus')
button=browser.find_element_by_css_selector('#nav-search > form > div.nav-right > div > input')
button.click()



# browser.close()

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
import time

driver = webdriver.Chrome()
driver.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
wait=WebDriverWait(driver,3)
# driver.implicitly_wait(3)  # 使用隐式等待

try:
    driver.switch_to.frame('iframeResult') ##切换到iframeResult
    sourse=driver.find_element_by_id('draggable')
    target=driver.find_element_by_id('droppable')

```
#方式一：基于同一个动作链串行执行
# actions=ActionChains(driver) #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：不同的动作链，每次移动的位移都不同
```

    ActionChains(driver).click_and_hold(sourse).perform()
    distance=target.location['x']-sourse.location['x']

```
track=0
while track < distance:
    ActionChains(driver).move_by_offset(xoffset=2,yoffset=0).perform()
    track+=2

ActionChains(driver).release().perform()

time.sleep(10)
```

finally:
    driver.close()

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()
    browser.get('https://www.baidu.com')
    browser.execute_script('alert("hello world")') #打印警告
finally:
    browser.close()

#模拟浏览器的前进后退
import time
from selenium import webdriver

browser=webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.get('https://www.taobao.com')
browser.get('http://www.sina.com.cn/')

browser.back()
time.sleep(10)
browser.forward()
browser.close()

import time
from selenium import webdriver

browser=webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.execute_script('window.open()')

print(browser.window_handles) #获取所有的选项卡
browser.switch_to_window(browser.window_handles[1])
browser.get('https://www.taobao.com')
time.sleep(10)
browser.switch_to_window(browser.window_handles[0])
browser.get('https://www.sina.com.cn')
browser.close()

from selenium import webdriver
from selenium.common.exceptions import TimeoutException,NoSuchElementException,NoSuchFrameException

try:
    browser=webdriver.Chrome()
    browser.get('http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
    browser.switch_to.frame('iframssseResult')

except TimeoutException as e:
    print(e)
except NoSuchFrameException as e:
    print(e)
finally:
    browser.close()

 

7.cookie存储（重点）

当我们运行爬虫项目爬取网站时一定会生成多个cookie模拟多个用户，否则很容易被识别并且禁用

#cookies
from selenium import webdriver

browser=webdriver.Chrome()
browser.get('https://www.zhihu.com/explore')
print(browser.get_cookies())
browser.add_cookie({'k1':'xxx','k2':'yyy'})
print(browser.get_cookies())

# browser.delete_all_cookies()

模拟登录博客园获取并存储cookie，得到后带cookie免登录进入博客园

import time
from selenium import webdriver
import json
import requests

bro = webdriver.Chrome()
bro.get('https://account.cnblogs.com/signin?returnUrl=https%3A%2F%2Fwww.cnblogs.com%2F')

time.sleep(30)
bro.refresh()
cookie = bro.get_cookies()
print(cookie)
with open('cookie.txt', 'w') as f:
    json.dump(cookie, f)



time.sleep(1)
with open('cookie.txt', 'r') as f:
    v = json.load(f)
cookies = {}
# 获取cookie中的name和value，转换成requests可以使用形式
for cookie in v:
    cookies[cookie['name']] = cookie['value']
print(cookies)


# 请求头
headers = {
    # 'authority': 'www.jd.com',
    # 'method': 'GET',
    # 'path': '/',
    # 'scheme': 'https',
    # 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    # 'accept-encoding': 'gzip, deflate, br',
    # 'accept-language': 'zh-CN,zh;q=0.9',
    # 'cache-control': 'max-age=0',
    # 'upgrade-insecure-requests': '1',
    'authority': 'i-beta.cnblogs.com',
    'method': 'GET',
    'path': '/',
    'scheme': 'https',
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3',
    'accept-encoding': 'gzip, deflate, br',
    'accept-language': 'zh-CN,zh;q=0.9',
    'cache-control': 'max-age=0',
    'if-modified-since': 'Sun, 24 Nov 2019 06:14:53 GMT',
    # 'if-modified-since': 'Sun, 24 Nov 2019 06:14:53 GMT,
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'none',
    'sec-fetch-user': '?1',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.108 Safari/537.36'

}
# 获取cookies后发送请求
response = requests.get('https://i-beta.cnblogs.com/api/user', headers=headers, cookies=cookies)
print('---------------------')
response.encoding = response.apparent_encoding
print(response.text)

 

8.项目

爬取淘宝（不完善）

淘宝的商品需要登录后才能查询，故每次爬取都需要人工手动登录，并且淘宝的安全等级较高，登录会发送验证码

from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time

bro = webdriver.Chrome()
bro.get('https://www.taobao.com/')
bro.implicitly_wait(10)


def get_goods(bro):
    print('----------------------------------------->')
    goods_list = bro.find_elements_by_class_name('J_MouserOnverReq ')
    for goods in goods_list:
        url = goods.find_element_by_css_selector('.J_ClickStat').get_attribute('href')
        img_url = goods.find_element_by_css_selector('.J_ItemPic').get_attribute('src')
        price = goods.find_element_by_css_selector('.price strong').text
        num = goods.find_element_by_css_selector('.deal-cnt').text
        title = goods.find_element_by_css_selector('.J_ClickStat').text
        print('''
                商品链接：%s
                商品图片：%s
                商品名字：%s
                商品价格：%s
                商品销量：%s

                ''' % (url, img_url, title, price, num))
    next_page = bro.find_element_by_partial_link_text('下一页')
    next_page.click()
    time.sleep(1)
    get_goods(bro)


inp = bro.find_element_by_id('q')
inp.send_keys('手机')  # 此处输入想搜索的商品
inp.send_keys(Keys.ENTER)  # 回车
bro.find_element_by_class_name('grid')


try:
    get_goods(bro)
except Exception as e:
    print(e)
finally:
    print('结束程序')
    bro.close()

京东不需登录就能爬取，相对不复杂

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
import time



def get_goods(driver):
    try:
        goods=driver.find_elements_by_class_name('gl-item')

```
    for good in goods:
        detail_url=good.find_element_by_tag_name('a').get_attribute('href')

        p_name=good.find_element_by_css_selector('.p-name em').text.replace('\n','')
        price=good.find_element_by_css_selector('.p-price i').text
        p_commit=good.find_element_by_css_selector('.p-commit a').text

        msg = '''
        商品 : %s
        链接 : %s
        价钱 ：%s
        评论 ：%s
        ''' % (p_name,detail_url,price,p_commit)

        print(msg,end='\n\n')

```

```
    button=driver.find_element_by_partial_link_text('下一页')
    button.click()
    time.sleep(1)
    get_goods(driver)
except Exception:
    pass

```

def spider(url,keyword):
    driver = webdriver.Chrome()
    driver.get(url)
    driver.implicitly_wait(3)  # 使用隐式等待
    try:
        input_tag=driver.find_element_by_id('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='iPhone8手机')

 

9.破解知乎登录获取cookie案例

小猿取经大神博客：https://www.cnblogs.com/xiaoyuanqujing/articles/11843045.html

 95