Spider_Man_3 の selenium

一：介紹

selenium最初是一個自動化測試工具,而爬蟲中使用它主要是爲了解決requests沒法直接執行JavaScript代碼的問題

selenium本質是經過驅動瀏覽器，徹底模擬瀏覽器的操做，好比跳轉、輸入、點擊、下拉等，來拿到網頁渲染以後的結果，可支持多種瀏覽器

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

 

二：安裝

#安裝：selenium+chromedriver
pip3 install selenium
下載chromdriver.exe放到python安裝路徑的scripts目錄中便可，注意最新版本是2.35，並不是2.9
國內鏡像網站地址：http://npm.taobao.org/mirrors/chromedriver/
最新的版本去官網找:https://sites.google.com/a/chromium.org/chromedriver/downloads

#驗證安裝
C:\Users\Administrator>python3
Mac:/usr/local/bin

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() #彈出瀏覽器
>>> driver.get('https://www.baidu.com')
>>> driver.page_source

#注意：
selenium3默認支持的webdriver是Firfox，而Firefox須要安裝geckodriver
下載連接：https://github.com/mozilla/geckodriver/releases

#安裝：selenium+phantomjs
pip3 install selenium
下載phantomjs，解壓後把phantomjs.exe所在的bin目錄放到環境變量
下載連接：http://phantomjs.org/download.html

#驗證安裝
C:\Users\Administrator>phantomjs
phantomjs> console.log('egon gaga')
egon gaga
undefined
phantomjs> ^C
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.PhantomJS() #無界面瀏覽器
>>> driver.get('https://www.baidu.com')
>>> driver.page_source

selenium+phantomjs

 

三：基本使用

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素

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

    input_tag=browser.find_element_by_id('kw')
    input_tag.send_keys('666') #python2中輸入中文錯誤，字符串前加個u
    input_tag.send_keys(Keys.ENTER) #輸入回車

    wait=WebDriverWait(browser,10)
    wait.until(EC.presence_of_element_located((By.ID,'content_left'))) #等到id爲content_left的元素加載完畢,最多等10秒

    print(browser.page_source)
    print(browser.current_url)
    print(browser.get_cookies())

finally:
    browser.close()

 

四：選擇器

　　1：基本用法

#官網連接：http://selenium-python.readthedocs.io/locating-elements.html
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素
import time

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

try:
    #===============全部方法===================
    # 一、find_element_by_id
    # 二、find_element_by_link_text
    # 三、find_element_by_partial_link_text
    # 四、find_element_by_tag_name
    # 五、find_element_by_class_name
    # 六、find_element_by_name
    # 七、find_element_by_css_selector
    # 八、find_element_by_xpath
    # 強調：
    # 一、上述都可以改寫成find_element(By.ID,'kw')的形式
    # 二、find_elements_by_xxx的形式是查找到多個元素，結果爲列表

    #===============示範用法===================
    # 一、find_element_by_id
    print(driver.find_element_by_id('kw'))

    # 二、find_element_by_link_text
    # login=driver.find_element_by_link_text('登陸')
    # login.click()

    # 三、find_element_by_partial_link_text
    login=driver.find_elements_by_partial_link_text('錄')[0]
    login.click()

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

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

    # 六、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('lhf@094573')
    commit.click()

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

    # 八、find_element_by_xpath

    time.sleep(5)

finally:
    # driver.close()
    driver.quit()  # 這個是殺掉進程。

　　

　　2：xpath

#官網連接：http://selenium-python.readthedocs.io/locating-elements.html
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素
import time

driver=webdriver.PhantomJS()
driver.get('https://doc.scrapy.org/en/latest/_static/selectors-sample1.html')
# wait=WebDriverWait(driver,3)
driver.implicitly_wait(3) #使用隱式等待

try:
    # find_element_by_xpath
    #//與/
    # driver.find_element_by_xpath('//body/a')  # 開頭的//表明從整篇文檔中尋找,body以後的/表明body的兒子，這一行找不到就會報錯了

    driver.find_element_by_xpath('//body//a')  # 開頭的//表明從整篇文檔中尋找,body以後的//表明body的子子孫孫
    driver.find_element_by_css_selector('body a')

    #取第n個
    res1=driver.find_elements_by_xpath('//body//a[1]') #取第一個a標籤
    print(res1[0].text)

    #按照屬性查找,下述三者查找效果同樣
    res1=driver.find_element_by_xpath('//a[5]')
    res2=driver.find_element_by_xpath('//a[@href="image5.html"]')
    res3=driver.find_element_by_xpath('//a[contains(@href,"image5")]') #模糊查找
    print('==>', res1.text)
    print('==>',res2.text)
    print('==>',res3.text)


    #其餘
    res1=driver.find_element_by_xpath('/html/body/div/a')
    print(res1.text)

    res2=driver.find_element_by_xpath('//a[img/@src="image3_thumb.jpg"]') #找到子標籤img的src屬性爲image3_thumb.jpg的a標籤
    print(res2.tag_name,res2.text)

    res3 = driver.find_element_by_xpath("//input[@name='continue'][@type='button']") #查看屬性name爲continue且屬性type爲button的input標籤
    res4 = driver.find_element_by_xpath("//*[@name='continue'][@type='button']") #查看屬性name爲continue且屬性type爲button的全部標籤
    
    
    time.sleep(5)

finally:
    # driver.close()
    driver.quit()

 

　　3：獲取標籤屬性

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素

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')

#獲取標籤屬性，
print(tag.get_attribute('src'))


#獲取標籤ID，位置，名稱，大小（瞭解）
print(tag.id)
print(tag.location)
print(tag.tag_name)
print(tag.size)


# browser.close()
browser.quit()

 

五：等待元素被加載

#一、selenium只是模擬瀏覽器的行爲，而瀏覽器解析頁面是須要時間的（執行css，js），一些元素可能須要過一段時間才能加載出來，爲了保證能查找到元素，必須等待

#二、等待的方式分兩種：
隱式等待：在browser.get（'xxx'）前就設置，針對全部元素有效
顯式等待：在browser.get（'xxx'）以後設置，只針對某個元素有效

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素

browser=webdriver.Chrome()

#隱式等待:在查找全部元素時，若是還沒有被加載，則等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') #沒有等待環節而直接查找，找不到則會報錯
print(contents)

browser.close()

隱式等待

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素

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


input_tag=browser.find_element_by_id('kw')
input_tag.send_keys('555')
input_tag.send_keys(Keys.ENTER)


#顯式等待：顯式地等待某個元素被加載
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()

顯式等待

六：元素交互操做

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素

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() #清空輸入框
input_tag.send_keys('iphone7plus')
button=browser.find_element_by_css_selector('#nav-search > form > div.nav-right > div > input')
button.click()



# browser.close()

點擊、清空

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By  # 按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys  # 鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait  # 等待頁面加載某些元素
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)  # 使用隱式等待

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

    #方式一：基於同一個動做鏈串行執行
    # actions=ActionChains(driver) #拿到動做鏈對象
    # actions.drag_and_drop(sourse,target) #把動做放到動做鏈中，準備串行執行
    # actions.perform()

    #方式二：不一樣的動做鏈，每次移動的位移都不一樣
    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()

Action Chains

ActionChains

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素


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

在交互動做比較難實現的時候能夠本身寫JS（萬能方法）

在交互動做比較難實現的時候能夠本身寫JS（萬能方法）

#frame至關於一個單獨的網頁，在父frame裏是沒法直接查看到子frame的元素的，必須switch_to_frame切到該frame下，才能進一步查找

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素


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

    browser.switch_to.frame('iframeResult') #切換到id爲iframeResult的frame

    tag1=browser.find_element_by_id('droppable')
    print(tag1)

    # tag2=browser.find_element_by_id('textareaCode') #報錯，在子frame裏沒法查看到父frame的元素
    browser.switch_to.parent_frame() #切回父frame,就能夠查找到了
    tag2=browser.find_element_by_id('textareaCode')
    print(tag2)

finally:
    browser.close()

補充:frame的切換

frame的切換

 

七：其餘

#模擬瀏覽器的前進後退
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()

#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()

cookies

#選項卡管理：切換選項卡，有js的方式windows.open,有windows快捷鍵：ctrl+t等，最通用的就是js的方式
import time
from selenium import webdriver

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

print(browser.window_handles) #獲取全部的選項卡
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()

選項卡管理

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()

異常處理

 

八：項目練習

import time

from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素


# 該代碼生效與 2018-01-18     不知道何時會變。重在學習流程。

# username = '1111111'
# password = '2222222'
#
# try:
#     browser = webdriver.Chrome()
#     browser.get('https://mail.163.com')
#     browser.implicitly_wait(5)
#     frame = browser.find_element_by_id('x-URS-iframe')  # 這個163有點騷氣，須要進入到該id下的iframe
#     browser.switch_to.frame(frame)
#
#     user_tag = browser.find_element_by_id('auto-id-1516274652838')
#     user_tag.send_keys(username)
#     pwd_tag = browser.find_element_by_id('auto-id-1516274652839')
#     pwd_tag.send_keys(password)
#
#     pwd_tag.send_keys(Keys.ENTER)
#     login = browser.find_elements_by_id('dologin')
#
#     # 這裏若是有驗證碼。。。  原諒我，我還在學習破解該驗證碼方式。
#     # 。。。略略略



browser = webdriver.Chrome()
try:
    browser.get('http://mail.163.com/')

    wait = WebDriverWait(browser, 5)

    frame = wait.until(EC.presence_of_element_located((By.ID, 'x-URS-iframe')))
    browser.switch_to.frame(frame)

    wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '.m-container')))

    inp_user = browser.find_element_by_name('email')
    inp_pwd = browser.find_element_by_name('password')
    button = browser.find_element_by_id('dologin')
    inp_user.send_keys('66666')
    inp_pwd.send_keys('xxxx')
    button.click()


    wait.until(EC.presence_of_element_located((By.ID, 'dvNavTop')))
    write_msg = browser.find_elements_by_css_selector('#dvNavTop li')[1]  # 獲取第二個li標籤就是「寫信」了
    write_msg.click()

    wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'tH0')))
    recv_man = browser.find_element_by_class_name('nui-editableAddr-ipt')
    title = browser.find_element_by_css_selector('.dG0 .nui-ipt-input')
    recv_man.send_keys('666@qq.com')
    title.send_keys('8787')
    print(title.tag_name)

    frame = wait.until(EC.presence_of_element_located((By.CLASS_NAME, 'APP-editor-iframe')))
    browser.switch_to.frame(frame)
    body = browser.find_element(By.CSS_SELECTOR, 'body')
    body.send_keys('666，wenwenwen')

    browser.switch_to.parent_frame()  # 切回他爹
    send_button = browser.find_element_by_class_name('nui-toolbar-item')
    send_button.click()

    # 能夠睡時間久一點別讓瀏覽器關掉，看看發送成功沒有
    import time

    time.sleep(100)

except Exception as e:
    print(e)

finally:
    browser.quit()

自動登陸163併發送郵件

import time
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By #按照什麼方式查找，By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操做
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait #等待頁面加載某些元素
# 爬取天貓擼擼杯


def get_goods(browser):
    goods = browser.find_elements_by_class_name('J_MouserOnverReq')
    # print(goods)
    msgs=[]
    for detail_good in goods:
        tag_a = detail_good.find_element_by_css_selector('.pic > .pic-link')
        detail_url =tag_a.get_attribute('href')
        detail_name = tag_a.find_element_by_tag_name('img').get_attribute('alt')
        detail_price = tag_a.get_attribute('trace-price')
        detail_pic = tag_a.find_element_by_tag_name('img').get_attribute('src')

        msg="""
            🎃🎃🎃🎃🎃
            商品名稱：{0},
            商品連接：{1},
            商品價錢：{2}，
            商品圖片：{3} 
            """.format(detail_name,detail_url,detail_price,detail_pic)
        msgs.append(msg)

    with open('saosao','w') as f :
        for x in msgs:
            f.write(x)
def spider(url,keyword):
    try:
        browser = webdriver.Chrome()
        browser.get(url)
        browser.implicitly_wait(10)
        # 找到搜索框，並輸入關鍵字
        # browser.find_element_by_css_selector('div .s-combobox-input > input')
        search_tag = browser.find_element_by_id('q')
        search_tag.send_keys(keyword)
        search_tag.send_keys(Keys.ENTER)
        get_goods(browser)
        time.sleep(50)
        # print(browser)
    finally:
        browser.quit()

url='https://www.taobao.com'
keyword = '擼擼杯'

# 執行
if __name__ == '__main__':
    spider(url,keyword)

爬tb的lulubei