# /usr/bin/env python# -*- coding: utf-8 -*-# @Time : 18-4-27 下午8:21# @Author : 杨星星# @Email : yangshilong_liu@# @File : selenium_jingdong.py# @Software: PyCharmimport refrom mon.action_chains import ActionChainsfrom selenium import webdriverfrom mon.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECfrom lxml import etreeimport timebrowser = webdriver.Chrome()def jd_search():try:# browser = webdriver.Chrome()browser.get('/')wait = WebDriverWait(browser, 10)input = wait.until(EC.presence_of_element_located((By.ID, 'key')))input.send_keys('shouji')button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '.button')))button.click()total = wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#J_bottomPage > span.p-skip > em:nth-child(1) > b')))return total.textexcept TimeoutError:print('---error----')def next_page():try:wait = WebDriverWait(browser, 10)button = wait.until(EC.element_to_be_clickable((By.CSS_SELECTOR, '#J_bottomPage > span.p-num > a.pn-next > em')))# button = browser.find_element_by_class_name('btn btn-default') #button.click()wait.until(EC.presence_of_element_located((By.CSS_SELECTOR, '#J_goodsList > ul')))html = browser.page_sourceparse_item(html)except TimeoutError:print('----error---')def parse_item(html_data):html = re.search(r'<ul class="gl-warp clearfix" data-tpl="3">(.*?)<span class="clr">', html_data,re.S).group(0)# print(html)res = pile(r'target="_blank" title="(.*?)"')data_list = res.findall(html)for title in data_list:print(title)def main():total_num = jd_search()print(total_num)for page_num in range(2,int(total_num)):time.sleep(3)next_page()main()
selenium用法详解selenium主要是用来做自动化测试，支持多种浏览器，爬虫中主要用来解决JavaScript渲染问题。模拟浏览器进行网页加载，当requests,urllib无法正常获取网页内容的时候一、声明浏览器对象注意点一，Python文件名或者包名不要命名为selenium，会导致无法导入from selenium import webdriver#webdriver可以认为是浏览器的驱动器，要驱动浏览器必须用到webdriver，支持多种浏览器，这里以Chrome为例browser = webdriver.Chrome()二、访问页面并获取网页htmlfrom selenium import webdriverbrowser = webdriver.Chrome()browser.get('')print(browser.page_source)#browser.page_source是获取网页的全部htmlbrowser.close()三、查找元素单个元素from selenium import webdriverbrowser = webdriver.Chrome()browser.get('')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()常用的查找方法find_element_by_namefind_element_by_xpathfind_element_by_link_textfind_element_by_partial_link_textfind_element_by_tag_namefind_element_by_class_namefind_element_by_css_selector也可以使用通用的方法from selenium import webdriverfrom mon.by import Bybrowser = webdriver.Chrome()browser.get('')input_first = browser.find_element(BY.ID,'q')#第一个参数传入名称，第二个传入具体的参数print(input_first)browser.close()多个元素，elements多个sinput_first = browser.find_elements_by_id('q')四、元素交互操作-搜索框传入关键词进行自动搜索from selenium import webdriverimport timebrowser = webdriver.Chrome()browser.get('')input = browser.find_element_by_id('q')#找到搜索框input.send_keys('iPhone')#传送入关键词time.sleep(5)input.clear()#清空搜索框input.send_keys('男士内裤')button = browser.find_element_by_class_name('btn-search')#找到搜索按钮button.click()更多操作: http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.remote.webelement#可以有属性、截图等等五、交互动作，驱动浏览器进行动作，模拟拖拽动作，将动作附加到动作链中串行执行from selenium import webdriverfrom selenium.webdriver import ActionChains#引入动作链browser = webdriver.Chrome()url = '/try/try.php?filename=jqueryui-api-droppable'browser.get(url)browser.switch_to.frame('iframeResult')#切换到iframeResult框架source = browser.find_element_by_css_selector('#draggable')#找到被拖拽对象target = browser.find_element_by_css_selector('#droppable')#找到目标actions = ActionChains(browser)#声明actions对象actions.drag_and_drop(source, target)actions.perform()#执行动作更多操作: http://selenium-python.readthedocs.io/api.html#module-mon.action_chains六、执行JavaScript有些动作可能没有提供api，比如进度条下拉，这时，我们可以通过代码执行JavaScriptfrom selenium import webdriverbrowser = webdriver.Chrome()browser.get('/explore')browser.execute_script('window.scrollTo(0, document.body.scrollHeight)')browser.execute_script('alert("To Bottom")')七、获取元素信息获取属性from selenium import webdriverfrom selenium.webdriver import ActionChainsbrowser = webdriver.Chrome()url = '/explore'browser.get(url)logo = browser.find_element_by_id('zh-top-link-logo')#获取网站logoprint(logo)print(logo.get_attribute('class'))browser.close()获取文本值from selenium import webdriverbrowser = webdriver.Chrome()url = '/explore'browser.get(url)input = browser.find_element_by_class_name('zu-top-add-question')print(input.text)#input.text文本值browser.close()# 获取Id，位置，标签名，大小from selenium import webdriverbrowser = webdriver.Chrome()url = '/explore'browser.get(url)input = browser.find_element_by_class_name('zu-top-add-question')print(input.id)#获取idprint(input.location)#获取位置print(input.tag_name)#获取标签名print(input.size)#获取大小browser.close()八、Frame操作frame相当于独立的网页，如果在父类网frame查找子类的，则必须切换到子类的frame，子类如果查找父类也需要先切换from selenium import webdriverfrom mon.exceptions import NoSuchElementExceptionbrowser = webdriver.Chrome()url = '/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)九、等待隐式等待当使用了隐式等待执行测试的时候，如果 WebDriver没有在 DOM中找到元素，将继续等待，超出设定时间后则抛出找不到元素的异常,换句话说，当查找元素或元素并没有立即出现的时候，隐式等待将等待一段时间再查找 DOM，默认的时间是0from selenium import webdriverbrowser = webdriver.Chrome()browser.implicitly_wait(10)#等待十秒加载不出来就会抛出异常，10秒内加载出来正常返回browser.get('/explore')input = browser.find_element_by_class_name('zu-top-add-question')print(input)显式等待指定一个等待条件，和一个最长等待时间，程序会判断在等待时间内条件是否满足，如果满足则返回，如果不满足会继续等待，超过时间就会抛出异常from selenium import webdriverfrom mon.by import Byfrom selenium.webdriver.support.ui import WebDriverWaitfrom selenium.webdriver.support import expected_conditions as ECbrowser = webdriver.Chrome()browser.get('/')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 标题是某内容title_contains 标题包含某内容presence_of_element_located 元素加载出，传入定位元组，如(By.ID, 'p')visibility_of_element_located 元素可见，传入定位元组visibility_of 可见，传入元素对象presence_of_all_elements_located 所有元素加载出text_to_be_present_in_element 某个元素文本包含某文字text_to_be_present_in_element_value 某个元素值包含某文字frame_to_be_available_and_switch_to_it frame加载并切换invisibility_of_element_located 元素不可见element_to_be_clickable 元素可点击staleness_of 判断一个元素是否仍在DOM，可判断页面是否已经刷新element_to_be_selected 元素可选择，传元素对象element_located_to_be_selected 元素可选择，传入定位元组element_selection_state_to_be 传入元素对象以及状态，相等返回True，否则返回Falseelement_located_selection_state_to_be 传入定位元组以及状态，相等返回True，否则返回Falsealert_is_present 是否出现Alert详细内容：http://selenium-python.readthedocs.io/api.html#module-selenium.webdriver.support.expected_conditions十一、前进后退-实现浏览器的前进后退以浏览不同的网页import timefrom selenium import webdriverbrowser = webdriver.Chrome()browser.get('/')browser.get('/')browser.get('/')browser.back()time.sleep(1)browser.forward()browser.close()十二、Cookiesfrom selenium import webdriverbrowser = webdriver.Chrome()browser.get('/explore')print(browser.get_cookies())browser.add_cookie({'name': 'name', 'domain': '', 'value': 'germey'})print(browser.get_cookies())browser.delete_all_cookies()print(browser.get_cookies())选项卡管理 增加浏览器窗口import timefrom selenium import webdriverbrowser = webdriver.Chrome()browser.get('')browser.execute_script('window.open()')print(browser.window_handles)browser.switch_to_window(browser.window_handles[1])browser.get('')time.sleep(1)browser.switch_to_window(browser.window_handles[0])browser.get('')十三、异常处理from selenium import webdriverbrowser = webdriver.Chrome()browser.get('')browser.find_element_by_id('hello')from selenium import webdriverfrom mon.exceptions import TimeoutException, NoSuchElementExceptionbrowser = webdriver.Chrome()try:browser.get('')except TimeoutException:print('Time Out')try:browser.find_element_by_id('hello')except NoSuchElementException:print('No Element')finally:browser.close()# 详细文档：http://selenium-python.readthedocs.io/api.html#module-mon.exceptions
