python selenium

Selenium

自動化測試工具，支持多種瀏覽器。
爬蟲中主要用來解決JavaScript渲染的問題

安裝Selenium

pip3 isntall selenium

Selenium

基本使用

from selenium import webdriver
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('https://www.baidu.com')
    input = browser.find_element_by_id('kw')
    input.send_keys('Python')
    input.send_keys(Keys.ENTER)
    wait = WebDriverWait(browser,10)
    wait.until(EC.presence_of_element_located((By.ID,'content_left')))
    print(browser.current_url)
    print(browser.get_cookies())
    print(browser.page_source)
finally:
    browser.close()

聲明瀏覽器對象

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

訪問頁面

from selenium import webdriver
browser = webdriver.Chrome()
browser.get("https://www.taobao.com")
print(browser.page_source)
browser.close()

查找元素

單個元素

from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input_first = browser.find_element_by_id('q')
input_second = browser.find_element_by_css_selector('#q')
input_third = browser.find_element_by_xpath('//*[@id="q"]')
print(input_first,input_second,input_third)
browser.close()

• find_element_by_name
• find_element_by_xpath
• find_element_by_link_text
• find_element_by_partial_link_text
• find_element_by_tag_name
• find_element_by_class_name
• find_element_by_css_selector

from selenium import webdriver
from selenium.webdriver.common.by import By
browser = webdriver.Chrome()
browser.get("https://www.taobao.com")
input_first = browser.find_element(By.ID,'q')
print(input_first)
browser.close()

多個元素

from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
lis = browser.find_elements_by_css_selector('.service-bd li')
print(lis)
browser.close()

from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
lis = broser.find_elements(By.CSS_SELECTOR,'.service-bd li')
print(lis)
browser.close()

• find_elements_by_name
• find_elements_by_xpath
• find_elements_by_link_text
• find_elements_by_partial_link_text
• find_elements_by_tag_name
• find_elements_by_class_name
• find_elements_by_css_selector

元素交互操做

對獲取的元素調用交互方法

from selenium import webdriver
import time
browser = webdriver.Chrome()
browser.get('https://www.taobao.com')
input = browser.find_element_by_id('q')
input.send_keys('iPhone')
time.sleep(1)
input.clear()
input.send_keys('iPad')
button = browser.find_element_by_class_name('btn-search')
button.click()

交互動做

將動做附加到動做鏈中串行執行

from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
url='http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable'
browser.get(url)
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
target = browser.find_element_by_css_selector('#droppable')
actions = ActionChains(browser)
actions.drag_and_drop(source,target)
actions.perform()

執行JavaScript

from selenium import webdriver
browser.get("https://www.zhihu.com/explore")
browser.execute_script('window.scrollTo(0,document.body.scrollHeight)')
browser.execute_script('alert('To Bottom')')

獲取元素信息

獲取屬性

from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
url = 'https://www.zhihu.com/explore'
browser.get(url)
logo = browser.find_element_by_id('zh-top-link-logo')
print(logo)
print(logo.get_attribute('class'))

獲取文本值

from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
url = 'https://www.zhihu.com/explore'
browser.get(url)
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.text)

獲取ID、位置、標籤名、大小

from selenium import webdriver
browser = webdriver.Chrome()
url='https://www.zhihu.com/explore'
browser.get(url)
input = browser.find_element_by_class_name('zu-top-add-question')
print(input.id)
print(input.location)
print(input.tag_name)
print(input.size)

Frame

import time
from selenium import webdriver
from selenium.common.exceptions import NoSuchElementException
url='http://www.runoob.com/try/try.php?filename=jqueryui-api-droppable'
browser.get(url)
browser.switch_to.frame('iframeResult')
source = browser.find_element_by_css_selector('#draggable')
print(source)
try:
    logo = browser.find_element_by_class_name('logo')
except NoSuchElementException:
    print('NO LOGO')
browser.switch_to.parent_frame()
logo = browser.find_element_by_class_name('logo')
print(logo)
print(logo.text)

等待

隱式等待

當使用了隱式等待執行測試的時候，若是WebDriver沒有在DOM中找到元素，將繼續等待，超出設定時間後則拋出找不到元素的異常，換句話說，當查找元素或元素並無當即出現的時候，隱式等待將等待一端時間再查找DOM，默認時間是0

from selenium import webdriver
browser.implicitly_wait(10)
browser.get('https://www.zhihu.com/explore')
input = browser.find_element_by_class_name('zu-top-add-question')
print(input)

顯示等待

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
browser = webdriver.Chrome()
browser.get('https://www.taobao.com/')
wait = WebDriverWait(browser,10)
input = wait.until(EC.presence_of_element_located((By.ID,'q')))
button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR,'btn-search')))
print(input,button)

• title_is標題是某內容
• title_contains標題包含某內容
• presence_of_element_located 元素加載出，傳入定位元組，如(By.ID,'p')
• visility_of_element_located元素可見，傳入定位元組
• visility_of可見，傳入元素對象
• presence_of_all_elements_located全部元素加載出
• text_to_be_avalable_and_switch_to_it frame加載並切換
• invisibity_of_element_located元素不可見
• element_to_be_clickable元素可點擊
• stateness_of判斷一個元素是否仍在DOM，可判斷頁面是否已經刷新
• element_to_be_selected元素可選擇，傳元素對象
• element_located_to_be_selected元素可選擇，傳入定位元組
• element_selection_state_to_be傳入元素對象從狀態，相等返回True，不然返回False
• alert_is_prosent是否出現Alert

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('https://www.python.org/')
browser.back
time.sleep(1)
browser.forward()
browser.close()

cookies

from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.zhihu.com')
print(browser.get_cookies())
browser.add_cookies{'name':'name','domain':'www.zhihu.com','value':'puqunzhu'}
print(browser.get_cookies())
browser.delete_all_cookies()
print(browser.get_cookies())

選項卡管理

import time
from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.execute_script('window.open()')
print(browser.window_handles)
browser.switch_to_window(browser.window_handles[1])
browser.get('https://www.taobao.com')
time.sleep(1)
browser.switch_to_window(browser.window_handles[0])
browser.get('https://python.org')

異常處理

from selenium import webdriver
browser = webdriver.Chrome()
browser.get('https://www.baidu.com')
browser.find_element_by_id('hello')

from selenium import webdriver
from selenium.common.exceptions import TimeoutException,NoSuchElementException
browser = webdriver.Chrome()
try:
    browser.get('http://www.baidu.com')
except TimeoutException:
    print('Time Out')
except NoSuchElementException:
    print('No Element')
finally:
    browser.close()