爬蟲請求庫之selenium模塊


一 安裝

#安裝:selenium+chromedriver
pip3 install selenium
下載chromdriver.exe放到python安裝路徑的scripts目錄中即可,注意最新版本是2.29,並非2.9
國內鏡像網站地址:http://npm.taobao.org/mirrors/chromedriver/2.29/
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
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需要安裝geckodriver
下載鏈接:https://github.com/mozilla/geckodriver/releases
selenium+chromedriver
#安裝:selenium+phantomjs
pip3 install selenium
下載phantomjs,解壓后把phantomjs.exe所在的bin目錄放到環境變量
下載鏈接: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

 

二 基本使用

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 #鍵盤按鍵操作
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('美女') #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為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()

  

三 選擇器

一 基本用法

#官網鏈接: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 #鍵盤按鍵操作
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:
    #===============所有方法===================
    # 1、find_element_by_id
    # 2、find_element_by_link_text
    # 3、find_element_by_partial_link_text
    # 4、find_element_by_tag_name
    # 5、find_element_by_class_name
    # 6、find_element_by_name
    # 7、find_element_by_css_selector
    # 8、find_element_by_xpath
    # 強調:
    # 1、上述均可以改寫成find_element(By.ID,'kw')的形式
    # 2、find_elements_by_xxx的形式是查找到多個元素,結果為列表

    #===============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('登錄')
    # login.click()

    # 3、find_element_by_partial_link_text
    login=driver.find_elements_by_partial_link_text('')[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('lhf@094573')
    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()
View Code

二 xpath

復制代碼
#官網鏈接: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 #鍵盤按鍵操作
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//代表從整篇文檔中尋找,body之后的/代表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//代表從整篇文檔中尋找,body之后的//代表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標簽
    print(res1[0].text)

    #按照屬性查找,下述三者查找效果一樣
    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)


    #其他
    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"]') #找到子標簽img的src屬性為image3_thumb.jpg的a標簽
    print(res2.tag_name,res2.text)

    res3 = driver.find_element_by_xpath("//input[@name='continue'][@type='button']") #查看屬性name為continue且屬性type為button的input標簽
    res4 = driver.find_element_by_xpath("//*[@name='continue'][@type='button']") #查看屬性name為continue且屬性type為button的所有標簽
    
    
    time.sleep(5)

finally:
    driver.close()
View Code

三 獲取標簽屬性

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 #鍵盤按鍵操作
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')

#獲取標簽屬性,
print(tag.get_attribute('src'))


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


browser.close()
View Code

四  等待元素被加載

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

#2、等待的方式分兩種:
隱式等待:在browser.get('xxx')前就設置,針對所有元素有效
顯式等待:在browser.get('xxx')之后設置,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 #按照什么方式查找,By.ID,By.CSS_SELECTOR
from selenium.webdriver.common.keys import Keys #鍵盤按鍵操作
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:在查找所有元素時,如果尚未被加載,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(推薦)
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 #鍵盤按鍵操作
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('美女')
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()
顯示等待

實戰

#注意:網站都策略都是在不斷變化的,精髓在於學習流程。下述代碼生效與2017-11-7,不能保證永久有效
from selenium import webdriver
from selenium.webdriver import ActionChains
from selenium.webdriver.common.by import By
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.support.wait import WebDriverWait

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('18611453110')
    inp_pwd.send_keys('xxxx')
    button.click()

    #如果遇到驗證碼,可以把下面一小段打開注釋
    # import time
    # time.sleep(10)
    # button = browser.find_element_by_id('dologin')
    # 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標簽就是“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('378533872@qq.com')
    title.send_keys('聖旨')
    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('egon很帥,可以加工資了')

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

    #可以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(10000)

except Exception as e:
    print(e)
finally:
    browser.close()
自動登陸163郵箱並發送郵件
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 #鍵盤按鍵操作
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


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
            鏈接 : %s
            價錢 :%s
            評論 :%s
            ''' % (p_name,detail_url,price,p_commit)

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


        button=driver.find_element_by_partial_link_text('下一頁')
        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)  # 使用隱式等待
    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手機')
爬取京東商品信息

 


免責聲明!

本站轉載的文章為個人學習借鑒使用,本站對版權不負任何法律責任。如果侵犯了您的隱私權益,請聯系本站郵箱yoyou2525@163.com刪除。



 
粵ICP備18138465號   © 2018-2025 CODEPRJ.COM