from selenium.webdriver.common.keys import Keys
from selenium.webdriver import ActionChains
from selenium.webdriver.chrome.options import Options
chrome_options = Options()
chrome_options.add_argument("--headless")
driver = webdriver.Chrome(executable_path='/usr/bin/chromedriver',
options=chrome_options)
driver.get('http://pythonscraping.com/pages/files/form.html')
firstnameField = driver.find_element_by_name('firstname')
lastnameField = driver.find_element_by_name('lastname')
submitButton = driver.find_element_by_id('submit')
### METHOD 1 ###
#firstnameField.send_keys('Philip')
#lastnameField.send_keys('Tung')
#submitButton.click()
#####################
### METHOD 2 ####
actions = ActionChains(driver).click(firstnameField).send_keys('Philip').click(
lastnameField).send_keys('Tung').send_keys(Keys.RETURN)
actions.perform()
#####################
print(driver.find_element_by_tag_name('body').text)
driver.close()
from selenium import webdriver
from selenium.webdriver import ActionChains
browser = webdriver.Chrome()
browser.get('http://www.baidu.com')
set_node = browser.find_element_by_xpath('//*[@id="u1"]/a[8]')
mouse_obj = ActionChains(browser)
mouse_obj.move_to_element(set_node)
mouse_obj.perform()
browser.find_element_by_link_text('高级搜索').click()
# browser.quit()
def get_constituency_candidates_table(constituency_object, year):
print(constituency_object.candidate_table_savepath)
if not Path(constituency_object.candidate_table_savepath).exists():
logging.info(f'current constituency :{constituency_object.name}')
browser = Scraper().launch_browser()
# open homepage
browser.get(constituency_object.page_url)
# open given constituency candidates table page
try:
# if constituency name matches completely
if year == 2014:
constituency_url = browser.find_element_by_link_text(
constituency_object.name.upper()).get_attribute('href')
browser.get(constituency_url)
else:
constituency_url = browser.find_element_by_link_text(
constituency_object.name).get_attribute('href')
browser.get(constituency_url)
except Exception as e:
logging.info(e)
try:
if year == 2014:
# if constituency name matches partially
constituency_url = browser.find_element_by_partial_link_text(
constituency_object.name.upper()).get_attribute('href')
browser.get(constituency_url)
else:
constituency_url = browser.find_element_by_partial_link_text(
constituency_object.name).get_attribute('href')
browser.get(constituency_url)
except Exception as e2:
logging.info(e2)
# constituency is missing
logger.info(
f'missing data for constituency {constituency_object.name}\n'
)
browser.close()
try:
element = browser.find_element_by_xpath(
constituency_object.candidate_table_xpath)
candidates_table_html = element.get_attribute('outerHTML')
with open(constituency_object.candidate_table_savepath,
'w') as handle:
handle.write(candidates_table_html)
browser.close()
except Exception as e:
logging.info(e)
try:
logging.info(e)
browser.refresh()
browser.get(constituency_url)
time.sleep(5)
element = browser.find_element_by_xpath(
constituency_object.candidate_table_xpath)
mouse = ActionChains(browser)
mouse.move_to_element(element)
mouse.perform()
candidates_table_html = element.get_attribute('outerHTML')
with open(constituency_object.candidate_table_savepath,
'w') as handle:
handle.write(candidates_table_html)
browser.close()
except Exception as e2:
logging.info(e2)
logger.info(
f'missing data for constituency {constituency_object.name}\n'
)
else:
logging.info('loading from archive')
logging.info(f'{constituency_object.name} already exists')
async def play(ctx, url: str):
song_there = os.path.isfile("song.mp3")
try:
if song_there:
os.remove("song.mp3")
print("Removed old song file\n")
except PermissionError:
print("Trying to delete song file, but it is playing")
await ctx.send("Error: Song is currently playing")
return
speak("Getting everything ready now")
await ctx.send("Getting everything ready now.")
voice = get(bot.voice_clients, guild=ctx.guild)
ydl_opts = {
'format':
'bestaudio/best',
'postprocessors': [{
'key': 'FFmpegExtractAudio',
'preferredcodec': 'mp3',
'preferredquality': '192',
}],
}
driver = webdriver.Chrome(PATH)
driver.get("https://www.youtube.com")
search_bar = driver.find_element_by_xpath(
'/html/body/ytd-app/div/div/ytd-masthead/div[3]/div[2]/ytd-searchbox/form/div/div[1]/input'
)
search_bar.send_keys(url)
search_bar.send_keys(Keys.RETURN)
first_video = driver.find_element_by_xpath(
'/html/body/ytd-app/div/ytd-page-manager/ytd-search/div[1]/ytd-two-column-search-results-renderer/div/ytd-section-list-renderer/div[2]/ytd-item-section-renderer/div[3]/ytd-video-renderer[1]/div[1]/ytd-thumbnail/a/yt-img-shadow/img'
)
action = ActionChains(driver)
action.move_to_element(first_video).click()
time.sleep(2)
action.perform()
uurl = driver.current_url
url = uurl
driver.quit()
with youtube_dl.YoutubeDL(ydl_opts) as ydl:
print("Downloding audio now\n")
ydl.download([url])
for file in os.listdir("./"):
if file.endswith(".mp3"):
name = file
os.rename(file, "song.mp3")
print(f"Rename file {name}\n")
voice.play(discord.FFmpegPCMAudio("song.mp3"),
after=lambda e: print(f"{name} has stoped playing\n"))
voice.source = discord.PCMVolumeTransformer(voice.source)
voice.source.volume = 0.2
nname = name.rsplit("-", 2)
await ctx.send(f"Playing: {nname[0]}")
print("Playing")
speak("Playing the song")
from selenium import webdriver
import time
options = webdriver.ChromeOptions()
# options.set_headless()
driver = webdriver.Chrome(executable_path='/home/bc/桌面/chromedriver', )
driver.get('http://www.baidu.com')
# driver.save_screenshot('baudu.png')
# driver.find_element_by_id('kw').send_keys('帅哥')
# driver.find_element_by_id('su').click()
# driver.find_element_by_name('bg s_btn').click()
time.sleep(2)
# driver.find_element_by_link_text('下一页>').click
# driver.find_element_by_class_name('n').click()
# print(driver.page_source)
# print(driver.get_cookie)
# cookies = driver.get_cookies()
# for cookie in cookies:
# print(cookie['name']+':'+cookie['value'])
from selenium.webdriver import ActionChains
elelment = driver.find_element_by_xpath('//div[@id="ul"]/a[1]')
ActionChains(driver).move_to_element(elelment).perform()
ActionChains(driver).move_to_element(elelment).click(elelment).perform()
time.sleep(5)
driver.quit()
def test_Buyflow(self):
action = ActionChains(self.driver)
self.driver.get("http://automationpractice.com/index.php")
product1 = self.driver.find_element(Locator.product1[0],Locator.product1[1])
product1_add = self.driver.find_element(Locator.product1_add_btn[0],Locator.product1_add_btn[1])
action.move_to_element(product1).move_to_element(product1_add).click().perform()
长按点击操作：action.click_and_hold(btn)
进行页面的移动，设置移动像素： action.move_by_offset(17, 0)
立即执行动作链：action.move_by_offset(17, 0).perform()
释放动作链：action.release()
"""
from selenium import webdriver
from selenium.webdriver import ActionChains # 导入动作链
from time import sleep
bro = webdriver.Chrome('chromedriver.exe')
bro.get('https://www.runoob.com/try/try.php?filename=jqueryui-api-droppable')
bro.switch_to.frame("iframeResult")
btn = bro.find_element_by_id("draggable")
action = ActionChains(bro)
action.click_and_hold(btn) # 点击长按指定的标签
for i in range(5):
action.move_by_offset(17, 0).perform() # 立即执行动作链操作
sleep(0.3)
action.release() # 释放动作链
bro.quit()
def ali_pay(email, alipay_url, noWin=False, st_input=False):
try:
print('打开支付宝， 进行付款...')
driver = Base(no_win=noWin)
driver.get_driver()
if noWin:
driver.driver.set_window_size(2000, 1500)
for _ in range(10):
x = alipay_login(driver, email, alipay_url, st_input=st_input)
if x == 1:
break
elif x == 11:
return
else:
return 0
print('输入付款账号结束，进入确认付款')
for i in range(2, 13):
try:
driver.Wait("payPassword_container", sleep=1)
time.sleep(1)
print('输入支付密码！...')
ActionChains(driver.driver).send_keys(*alipay_Keys).perform()
# sms_code = input("\n是否有短信息验证码？填写完成后按回车\n>>>")
# ====================================== #
# 短信验证码
# ====================================== #
st = timess()
try:
driver.Wait(xpath='//*[@id="J_authSubmit"]', text=NC)
ls = re.findall(r"id=['\"]ackcode['\"]",
driver.driver.page_source)
if ls and ls[0]:
driver.driver.find_element_by_id('ackcode')
driver.Wait("ackcode", input("发现短信验证码,请输入短信验证码\n>>>"))
except Exception:
pass
print(timess() - st)
driver.Wait(xpath='//*[@id="J_authSubmit"]', sleep=1)
# try:
# # driver.driver.switch_to.frame(driver.Wait(xpath='//iframe[@frameborder="no"]', text=NC, sleep=2))
# # driver.Wait("riskackcode")
# # time.sleep(15)
# # if "信息校验" in driver.driver.page_source:
# # sms_code = input("\n请输入短信验证码\n>>>")
# # driver.Wait("riskackcode", sms_code)
# time.sleep(20)
# pay_over(email)
# return
# # driver.Wait("J_authSubmit")
# except Exception:
# pass
time.sleep(1)
for _ in range(60):
page = driver.driver.page_source
if "确认付款" in page or '您已成功付款' in page:
with open("logs/email_pay.log", "a",
encoding="utf8") as f:
f.write(
f"付款完成: {email: <25}{time.strftime('%Y-%m-%d %H:%M:%S')}\n\n"
)
driver.driver.save_screenshot(
'visa_photo/successful.png')
return 1
elif "无法完成付款" in page:
break
elif "抱歉，您操作超时，请重新登录" in page:
print("需要登录")
return -1
else:
time.sleep(0.1)
# driver.driver.save_screenshot(f"visa_photo/fail{time.strftime('%m%d-%H%M%S')}.png")
driver.Wait(xpath='//*[@id="J_GoBack_nobodyknows"]')
driver.Wait(xpath='//div[@id="J-rcChannels"]/div/div/a[1]',
sleep=0.5)
driver.Wait(xpath=f'//*[@id="J_SavecardList"]/li[{i}]',
sleep=0.5)
time.sleep(1)
except Exception as e:
with open("logs/error.log", "a", encoding="utf-8") as f:
f.write(f"\n\n{time.strftime('%m%d-%H%M%S')}\n" + e)
else:
driver.driver.save_screenshot('visa_photo/successful.png')
return 1
except Exception:
pass
finally:
driver.driver.quit()
def hover(self, *locator):
element = self.driver.find_element(*locator)
hover = ActionChains(self.driver).move_to_element(element)
hover.perform()
def balance_excel(self, menu, value):
print(menu)
print(value)
self.base = TestExcel()
basedata = [Excel_basedata_zs, sheet48]
# 点击一级菜单
self.findxpath_click(self.base.first_menu(basedata[0]).get(menu[1]))
# 点击二级菜单
self.findxpath_click(
self.base.second_menu(basedata[0]).get(f'{menu[1]}-{menu[2]}'))
targetsheet = self.base.sheet_xpath_dic(basedata[0], basedata[1])
wait = (By.XPATH, targetsheet.get('加载等待'))
# 根据自定义顺序执行操作
l = len(menu)
n = 3
while n < l:
if menu[n] not in self.base.operable_list(basedata[0],
basedata[1]):
print(f'操作元素"{menu[n]}"输入错误，请检查')
return False
else:
findelement = self.findxpath(targetsheet.get(menu[n]))
# 所有操作为"点击"或"勾选"的元素
if menu[n] in ['导出', '搜索']:
findelement.click()
if menu[n] in ['搜索']:
self.wait_for_miss(120, wait)
# 所有操作为"输入"的元素
elif menu[n] in ['查询日期']:
if value[n] == '置空':
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
else:
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
findelement.send_keys(value[n])
# 所有操作为"输入后选择"的元素
elif menu[n] in ['投组单元', '所在账户']:
if value[n] == '置空':
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
else:
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
sleep(1)
findelement.send_keys(value[n] + Keys.SPACE +
Keys.BACK_SPACE)
sleep(1)
if menu[n] in ['投组单元', '所在账户']:
self.findxpath_click(targetsheet.get('投组下拉选择'))
# 所有操作为"点击后选择"的元素
elif menu[n] in ['是否穿透', '产品类型']:
a = self.base.enumeration_list2(basedata[0], basedata[1],
menu[n])
if menu[n] == '产品类型':
a.append('置空')
if value[n] not in a:
print(f'值"{value[n]}"输入错误，请检查')
return False
else:
findelement.click()
if menu[n] in ['是否穿透']:
self.findxpath_click(f'//li[text()="{value[n]}"]')
elif menu[n] in ['产品类型']:
if value[n] == '置空':
selectall = self.findxpath(
'//div[text()=" 全选"]')
action = ActionChains(self.driver)
action.double_click(selectall).perform()
findelement.click()
elif value[n] == '全选':
self.findxpath_click('//div[text()=" 全选"]')
findelement.click()
else:
self.findxpath_click(
f'//li[text()=" {value[n]}"]')
n = n + 1
return True
def balance_compare(self, menu, value):
print(menu)
print(value)
self.base = TestExcel()
basedata = [Excel_basedata_zs, sheet48]
# 点击一级菜单
self.findxpath_click(self.base.first_menu(basedata[0]).get(menu[2]))
# 点击二级菜单
self.findxpath_click(
self.base.second_menu(basedata[0]).get(f'{menu[2]}-{menu[3]}'))
targetsheet = self.base.sheet_xpath_dic(basedata[0], basedata[1])
wait = (By.XPATH, targetsheet.get('加载等待'))
# 根据自定义顺序执行操作
l = len(menu)
n = 4
while n < l:
if menu[n] not in self.base.operable_list(basedata[0],
basedata[1]):
print(f'操作元素"{menu[n]}"输入错误，请检查')
return False
else:
findelement = self.findxpath(targetsheet.get(menu[n]))
# 所有操作为"点击"或"勾选"的元素
if menu[n] in ['导出', '搜索']:
findelement.click()
if menu[n] in ['搜索']:
self.wait_for_miss(120, wait)
# 所有操作为"输入"的元素
elif menu[n] in ['查询日期']:
if value[n] == '置空':
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
else:
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
findelement.send_keys(value[n])
# 所有操作为"输入后选择"的元素
elif menu[n] in ['投组单元', '所在账户']:
if value[n] == '置空':
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
else:
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
sleep(1)
findelement.send_keys(value[n] + Keys.SPACE +
Keys.BACK_SPACE)
sleep(1)
if menu[n] in ['投组单元', '所在账户']:
self.findxpath_click(targetsheet.get('投组下拉选择'))
# 所有操作为"点击后选择"的元素
elif menu[n] in ['是否穿透', '产品类型']:
a = self.base.enumeration_list2(basedata[0], basedata[1],
menu[n])
if menu[n] == '产品类型':
a.append('置空')
if value[n] not in a:
print(f'值"{value[n]}"输入错误，请检查')
return False
else:
findelement.click()
if menu[n] in ['是否穿透']:
self.findxpath_click(f'//li[text()="{value[n]}"]')
elif menu[n] in ['产品类型']:
if value[n] == '置空':
selectall = self.findxpath(
'//div[text()=" 全选"]')
action = ActionChains(self.driver)
action.double_click(selectall).perform()
findelement.click()
elif value[n] == '全选':
self.findxpath_click('//div[text()=" 全选"]')
findelement.click()
else:
self.findxpath_click(
f'//li[text()=" {value[n]}"]')
n = n + 1
# 触发判断定位点
m = self.base.checkpoint_list(basedata[0], basedata[1])
point = self.findxpath(
self.base.checkpoint_dic(basedata[0], basedata[1]).get(m[0]))
# 旧环境的记录值
p = len(m)
if point.is_displayed():
i = 0
x = {}
while i < p:
o = self.findxpath(
self.base.checkpoint_dic(basedata[0], basedata[1]).get(
m[i])).get_attribute('textContent')
x.setdefault(m[i], o)
i = i + 1
else:
print('案例最终结果不存在查询数据，请合理调整步骤')
return False
# 关闭浏览器
self.end()
# 新环境重复操作
self.start(value[1])
# 点击一级菜单
self.findxpath_click(self.base.first_menu(basedata[0]).get(menu[2]))
# 点击二级菜单
self.findxpath_click(
self.base.second_menu(basedata[0]).get(f'{menu[2]}-{menu[3]}'))
# 根据自定义顺序执行操作
l = len(menu)
n = 4
while n < l:
if menu[n] not in self.base.operable_list(basedata[0],
basedata[1]):
print(f'操作元素"{menu[n]}"输入错误，请检查')
return False
else:
findelement = self.findxpath(targetsheet.get(menu[n]))
# 所有操作为"点击"或"勾选"的元素
if menu[n] in ['导出', '搜索']:
findelement.click()
if menu[n] in ['搜索']:
self.wait_for_miss(120, wait)
# 所有操作为"输入"的元素
elif menu[n] in ['查询日期']:
if value[n] == '置空':
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
else:
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
findelement.send_keys(value[n])
# 所有操作为"输入后选择"的元素
elif menu[n] in ['投组单元', '所在账户']:
if value[n] == '置空':
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
else:
findelement.send_keys(Keys.CONTROL,
'a' + Keys.BACK_SPACE)
sleep(1)
findelement.send_keys(value[n] + Keys.SPACE +
Keys.BACK_SPACE)
sleep(1)
if menu[n] in ['投组单元', '所在账户']:
self.findxpath_click(targetsheet.get('投组下拉选择'))
# 所有操作为"点击后选择"的元素
elif menu[n] in ['是否穿透', '产品类型']:
a = self.base.enumeration_list2(basedata[0], basedata[1],
menu[n])
if menu[n] == '产品类型':
a.append('置空')
if value[n] not in a:
print(f'值"{value[n]}"输入错误，请检查')
return False
else:
findelement.click()
if menu[n] in ['是否穿透']:
self.findxpath_click(f'//li[text()="{value[n]}"]')
elif menu[n] in ['产品类型']:
if value[n] == '置空':
selectall = self.findxpath(
'//div[text()=" 全选"]')
action = ActionChains(self.driver)
action.double_click(selectall).perform()
findelement.click()
elif value[n] == '全选':
self.findxpath_click('//div[text()=" 全选"]')
findelement.click()
else:
self.findxpath_click(
f'//li[text()=" {value[n]}"]')
n = n + 1
# 新环境的记录值
r = 0
y = {}
while r < p:
s = self.findxpath(
self.base.checkpoint_dic(basedata[0], basedata[1]).get(
m[r])).get_attribute('textContent')
y.setdefault(m[r], s)
r = r + 1
# 局部校验
z = 0
if x.get(m[z]) == y.get(m[z]):
# 全局校验
t = 0
while t < p:
if x.get(m[t]) == y.get(m[t]):
t = t + 1
else:
print(f'对比结果：{m[t]}：{x.get(m[t])}数据核对不一致，请检查并联系开发')
return False
else:
print(f'对比结果：{m[z]}：{x.get(m[z])}数据核对不一致，请检查并联系开发')
return False
print('对比结果：数据核对一致')
return True
def start_crawl(journal, start_year, end_year, output_file):
global type_browser, url, WAIT_SECONDS, MAX_NUM_PAPERS
print('Start crawling papers from {} published during {} - {}'.format(
journal, start_year, end_year))
browser = get_browser(type_browser, headless=False, use_proxy=False)
browser.get(url)
# 等待高级检索按键加载完成并点击
try:
a_high_search = WebDriverWait(browser, WAIT_SECONDS).until(
EC.element_to_be_clickable((By.LINK_TEXT, '高级检索')))
except TimeoutException as e:
print('Timeout during waiting for loading of high search buttom.')
browser.quit()
return False
a_high_search.click()
time.sleep(1)
# 切换到最新打开的窗口
windows = browser.window_handles
browser.switch_to.window(windows[-1])
# 找到文献来源标签，用于后面判断点击刷新完成
try:
span_src = browser.find_element_by_xpath(
'//*[@id="gradetxt"]/dd[3]/div[2]/div[1]/div[1]/span')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
# 等待学术期刊按键加载完成并点击
try:
span_journal = WebDriverWait(browser, WAIT_SECONDS).until(
EC.element_to_be_clickable(
(By.XPATH,
'//ul[@class="doctype-menus keji"]/li[@data-id="xsqk"]/a/span'
)))
except TimeoutException as e:
print('Timeout during waiting for loading of journal buttom.')
browser.quit()
return False
browser.execute_script('arguments[0].click();', span_journal)
# 通过文献来源标签的过期判断刷新完成
try:
WebDriverWait(browser, WAIT_SECONDS).until(EC.staleness_of(span_src))
except TimeoutException as e:
print('Timeout during refresh after clicking journal buttom')
browser.quit()
return False
# 等待期刊名称输入框加载完成
try:
input_journal = WebDriverWait(browser, WAIT_SECONDS).until(
EC.presence_of_element_located(
(By.XPATH, '//*[@id="gradetxt"]/dd[3]/div[2]/input')))
except TimeoutException as e:
print('Timeout during waiting for input box for jounral name.')
browser.quit()
return False
input_journal.send_keys(journal) # 输入期刊名
time.sleep(1)
# 找到起始年输入框并输入起始年
try:
input_start_year = browser.find_element_by_xpath(
'//input[@placeholder="起始年"]')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
input_start_year.send_keys(start_year)
# 找到结束输入框并输入结束年
try:
input_end_year = browser.find_element_by_xpath(
'//input[@placeholder="结束年"]')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
input_end_year.send_keys(end_year)
# 找到检索键并点击
try:
input_search = browser.find_element_by_xpath('//input[@value="检索"]')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
input_search.click()
# 根据搜索结果总数标签的出现判断页面是否刷新完成
try:
em_total = WebDriverWait(browser, WAIT_SECONDS).until(
EC.visibility_of_element_located(
(By.XPATH, '//*[@id="countPageDiv"]/span[1]/em')))
except TimeoutException as e:
print('Timeout during waiting for paper number cell.')
browser.quit()
return False
'''
# 检查筛选后的文献总数是否超过1500条，超过1500条需要输入验证码，这里直接放弃
total = str2int(em_total.text)
if total > MAX_NUM_PAPERS:
print('Number of papers: {} > {}. Journal: {}, year: {} - {}.'.format(total, MAX_NUM_PAPERS, journal, start_year, end_year))
browser.quit()
return False
'''
# 找到每页文献数标签并点击使其展开
try:
div_perpage = browser.find_element_by_id(
'perPageDiv').find_element_by_tag_name('div')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
browser.execute_script("arguments[0].scrollIntoView();", div_perpage)
div_perpage.click()
# 等待文本为50的标签加载完成并点击
try:
li_50 = WebDriverWait(browser, WAIT_SECONDS).until(
EC.element_to_be_clickable(
(By.XPATH, '//div[@id="perPageDiv"]/ul/li[@data-val="50"]')))
except TimeoutException as e:
print(
'Timeout during waiting for loading of buttom perPageDiv. Journal: {}, year: {} - {}.'
.format(journal, start_year, end_year))
browser.quit()
return False
# 寻找每页文献数量标签
try:
span = browser.find_element_by_id(
'perPageDiv').find_element_by_tag_name('span')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
li_50.click()
# 通过每页文献数量标签的过期，判断文献列表刷新完成
try:
WebDriverWait(browser, WAIT_SECONDS).until(EC.staleness_of(span))
except TimeoutException as e:
print(
'Timeout during waiting for refresh of search results after clciking buttom perPageDiv. Journal: {}, year: {} - {}.'
.format(journal, start_year, end_year))
browser.quit()
return False
cols = ['篇名', '作者', '期刊名称', '发表时间', '被引次数', '被下载次数'] # 需要保存的信息种类
col2index = {}
for i, col in enumerate(cols):
col2index[col] = i + 1
result = []
page_cnt = 0
# 保存所有页的文献信息
while True:
page_cnt += 1
# 文献信息保存在表格中，表格的一行(tr)对应一篇文献信息
try:
trs = browser.find_elements_by_xpath(
'//*[@id="gridTable"]/table/tbody/tr')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
# 保存当前页的所有文献信息
for tr in trs:
# 表格的一列(td)对应一篇文献的特定信息，如篇名、作者
try:
tds = tr.find_elements_by_tag_name('td')
except NoSuchElementException as e:
print(str(e))
browser.quit()
return False
'''
# 检查期刊名是否符合预期(可能模糊匹配)
if not(tds[3].text == journal or tds[3].text.startswith(journal + '(')):
print('Actual source: {}, expected source: {}'.format(tds[3].text, journal))
continue
# 检查发表时间是否符合预期
y = int(tds[4].text.split('-')[0])
if not check_date(y, start_year, end_year):
print('Actual year: {}, expected year: {} - {}. Journal: {}, year: {} - {}.'.format(y, start_year, end_year, journal, start_year, end_year))
continue
'''
info = OrderedDict()
info['时间段'] = '2012-2020'
for col in cols:
if col == '发表时间':
info[col] = tds[col2index[col]].text
else:
try:
a = tds[col2index[col]].find_element_by_tag_name('a')
except NoSuchElementException as e:
info[col] = ''
continue
info[col] = a.text
result.append(info)
# 寻找下一页按键
try:
next_page = WebDriverWait(browser, WAIT_SECONDS).until(
EC.element_to_be_clickable((By.ID, 'PageNext')))
except TimeoutException:
break
# 将鼠标拖动到下一页按键附近并点击
browser.execute_script("arguments[0].scrollIntoView();", next_page)
span = browser.find_element_by_xpath('//span[@class="cur"]')
ActionChains(browser).move_to_element(next_page).click().perform()
# 30页必出验证码
if (page_cnt % 30) == 0:
time.sleep(15)
# 通过当前页码标签判断页面是否刷新
try:
WebDriverWait(browser, WAIT_SECONDS).until(EC.staleness_of(span))
except TimeoutException as e:
print(
'Timeout during waiting for refresh of current page after clicking next page. Journal: {}, year: {} - {}.'
.format(journal, start_year, end_year))
browser.quit()
return False
# 将爬取结果保存到excel中
if len(result):
df = pd.DataFrame(data=result)
df.to_excel(output_file)
browser.quit()
print(
'Finish crawling papers from {} published in year: {} - {}, number of papers: {}'
.format(journal, start_year, end_year, len(result)))
return len(result) > 0
def sel_click(driver,element):
ActionChains(driver).move_to_element(element).click(element).perform()
def sel_input_text(driver,element,text):
ActionChains(driver).move_to_element(element).click(element).send_keys(text, Keys.ENTER).perform()
driver.get(url)
date_l,headline_l,des_l,author_l,vertical_l = [],[],[],[],[]
links = driver.find_elements_by_xpath("//td[@align='center']//a")
for link in links[9:]:
if link.get_attribute('text') != '':
######## set date block -> start ########
window_before = driver.window_handles[0] # get root tab
ActionChains(driver).key_down(Keys.CONTROL).click(link).key_up(Keys.CONTROL).perform() # open the link in new tab
window_after = driver.window_handles[-1]
driver.switch_to.window(window_after)
#%%%%%%%%%% iterate thorugh links of the selected date -> start %%%%%%%%%%%%%%
for i in range(len(driver.find_elements_by_xpath("//tr/td/span/a"))):
ActionChains(driver).move_to_element(driver.find_elements_by_xpath("//tr/td/span/a")[i]).click().perform()
#driver.find_elements_by_xpath("//tr/td/span/a")[i].click()
#&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&& get data block -> start &&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&&
driver.find_element_by_id('departCityName').send_keys(from_station)
sleep(1)
#到达城市
driver.find_element_by_id('arriveCityName').send_keys(arrive_station)
sleep(1)
#移除出发时间的’readonly‘属性
driver.execute_script(
"document.getElementById('departDate').removeAttribute('readonly')")
#出发时间
departDate = driver.find_element_by_id('departDate')
departDate.clear()
departDate.send_keys(tommorrow)
sleep(1)
#为了解决日期控件弹出框在输入日期后无法消失的问题，要让鼠标单击一下页面的空白处
ActionChains(driver).move_by_offset(0, 0).click().perform()
#开始搜索
searchbtn = driver.find_element_by_class_name('searchbtn')
searchbtn.click()
sleep(1)
#选择G7674班次的二等座
driver.find_element_by_css_selector(
'body > div:nth-child(32) > div > div.lisBox > div.List-Box > div > div:nth-child(14) > div.w6 > div:nth-child(1) > a'
).click()
sleep(3)
driver.find_element_by_class_name('input-name').send_keys('小丸子')
#注意的点：
# 1、日期弹框可能无法输入，要考虑JavaScrip来消除日期选框的readonly
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)
# 动作链联练习
browser.switch_to.frame('iframeResult')
# 拖拽位置
source = browser.find_element_by_css_selector('#draggable')
# 目标位置
target = browser.find_element_by_css_selector('#droppable')
# 声明ActionChains对象并赋值为actions变量
actions = ActionChains(browser)
# 调用执行拖拽动作
actions.drag_and_drop(source, target)
actions.perform()
def auth_slide(self):
def get_distance(img1, img2):
"""计算滑动距离"""
threshold = 60
# 忽略可动滑块部分
start_x = 57
for i in range(start_x, img1.size[0]):
for j in range(img1.size[1]):
rgb1 = img1.load()[i, j]
rgb2 = img2.load()[i, j]
res1 = abs(rgb1[0] - rgb2[0])
res2 = abs(rgb1[1] - rgb2[1])
res3 = abs(rgb1[2] - rgb2[2])
if not (res1 < threshold and res2 < threshold
and res3 < threshold):
return i - 7 # 经过测试，误差为大概为7
def get_tracks(distance):
"""
制造滑动轨迹
策略：匀加速再匀减速，超过一些，再回调，左右小幅度震荡
"""
v = 0
current = 0
t = 0.2
tracks = []
if not distance:
return tracks
# 正向滑动
while current < distance + 10:
if current < distance * 2 / 3:
a = 2
else:
a = -3
s = v * t + 0.5 * a * (t**2)
current += s
tracks.append(round(s))
v = v + a * t
# 往回滑动
current = 0
while current < 13:
if current < distance * 2 / 3:
a = 2
else:
a = -3
s = v * t + 0.5 * a * (t**2)
current += s
tracks.append(-round(s))
v = v + a * t
# 最后修正
tracks.extend([2, 2, -3, 2])
return tracks
# 1. 截取完整图片
if self.get_full_img:
time.sleep(2) # 等待图片加载完毕
img_before = self.get_img()
else:
img_before = self._img_before
# 2. 点击出现缺口图片
slider_btn = self.driver.find_element_by_class_name(
"geetest_slider_button")
slider_btn.click()
# 3. 截取缺口图片
time.sleep(2) # 等待图片加载完毕
img_after = self.get_img()
# 4. 生成移动轨迹
tracks = get_tracks(get_distance(img_before, img_after))
# 5. 模拟滑动
slider_btn = self.driver.find_element_by_class_name(
"geetest_slider_button")
ActionChains(self.driver).click_and_hold(slider_btn).perform()
for track in tracks:
ActionChains(self.driver).move_by_offset(xoffset=track,
yoffset=0).perform()
# 6. 释放鼠标
time.sleep(0.5) # 0.5秒后释放鼠标
ActionChains(self.driver).release().perform()
# 7. 验证是否成功
time.sleep(2)
div_tag = self.driver.find_element_by_class_name(
"geetest_fullpage_click")
if "display: block" in div_tag.get_attribute("style"):
'''判断模块对话框是否存在，如果存在就说明没有验证成功，"display: block"，重新去验证'''
self.get_full_img = False
setattr(self, "_img_before", img_before)
return self.auth_slide()
else:
# 如果验证成功"display: none"
time.sleep(1000)
return True
def __init__(self, driver):
self.driver = driver
# self.action = webdriver.ActionChains(driver)
self.action = ActionChains(driver)
self.configManager = ConfigManager()
def test_web_regressions(browser, basic_html):
html_dir, dvcs = basic_html
bad_commit_hash = dvcs.get_hash('master~9')
browser.set_window_size(1200, 900)
with tools.preview(html_dir) as base_url:
get_with_retry(browser, base_url)
regressions_btn = browser.find_element_by_link_text('Regressions')
regressions_btn.click()
# Check that the expected links appear in the table
regression_1 = browser.find_element_by_link_text('params_examples.track_find_test(1)')
regression_2 = browser.find_element_by_link_text('params_examples.track_find_test(2)')
bad_hash_link = browser.find_element_by_link_text(bad_commit_hash[:8])
href = regression_1.get_attribute('href')
assert '/#params_examples.track_find_test?' in href
assert 'commits=' in href
# Sort the tables vs. benchmark name (PhantomJS doesn't allow doing it via actionchains)
browser.execute_script("$('thead th').eq(0).stupidsort('asc')")
WebDriverWait(browser, WAIT_TIME).until(EC.text_to_be_present_in_element(
('xpath', '//table[1]/tbody/tr[1]/td[1]'), 'params_examples.track_find_test(1)'
))
# Check the contents of the table
table_rows = browser.find_elements_by_xpath('//table[1]/tbody/tr')
assert len(table_rows) == 2
cols1 = [td.text for td in table_rows[0].find_elements_by_xpath('td')]
cols2 = [td.text for td in table_rows[1].find_elements_by_xpath('td')]
assert cols1[0] == 'params_examples.track_find_test(1)'
assert cols2[0] == 'params_examples.track_find_test(2)'
assert re.match(r'^\d\d\d\d-\d\d-\d\d \d\d:\d\d$', cols1[1])
assert re.match(r'^\d\d\d\d-\d\d-\d\d \d\d:\d\d$', cols2[1])
assert cols1[2:] == [bad_commit_hash[:8], '2.00x', '1.00', '2.00', 'Ignore']
assert cols2[2:] == [bad_commit_hash[:8], '2.00x', '1.00', '2.00', 'Ignore']
# Check that the ignore buttons work as expected
buttons = [button for button in browser.find_elements_by_xpath('//button')
if button.text == 'Ignore']
buttons[0].click()
# The button should disappear, together with the link
WebDriverWait(browser, WAIT_TIME).until_not(EC.visibility_of(buttons[0]))
WebDriverWait(browser, WAIT_TIME).until_not(EC.visibility_of(regression_1))
table_rows = browser.find_elements_by_xpath('//table[1]/tbody/tr')
assert len(table_rows) == 1
# There's a second button for showing the links, clicking
# which makes the elements reappear
show_button = [button for button in browser.find_elements_by_xpath('//button')
if button.text == 'Show ignored regressions...'][0]
show_button.click()
regression_1 = browser.find_element_by_link_text('params_examples.track_find_test(1)')
WebDriverWait(browser, WAIT_TIME).until(EC.visibility_of(regression_1))
table_rows = browser.find_elements_by_xpath('//table[2]/tbody/tr')
assert len(table_rows) == 1
# There's a config sample element
pre_div = browser.find_element_by_xpath('//pre')
assert "params_examples\\\\.track_find_test\\\\(1\\\\)" in pre_div.text
# There's an unignore button that moves the element back to the main table
unignore_button = [button for button in browser.find_elements_by_xpath('//button')
if button.text == 'Unignore'][0]
unignore_button.click()
browser.find_elements_by_xpath('//table[1]/tbody/tr[2]') # wait until the table has two rows
table_rows = browser.find_elements_by_xpath('//table[1]/tbody/tr')
assert len(table_rows) == 2
# Check that a plot of some sort appears on mouseover. The
# page needs to be scrolled first so that the mouseover popup
# has enough space to appear.
regression_1 = browser.find_element_by_link_text('params_examples.track_find_test(1)')
y = regression_1.location['y']
browser.execute_script('window.scrollTo(0, {0})'.format(y - 200))
chain = ActionChains(browser)
chain.move_to_element(regression_1)
chain.perform()
popover = browser.find_element_by_css_selector('div.popover-content')
flotplot = browser.find_element_by_css_selector('canvas.flot-base')
def bot():
# set paths for webdriver + initialize
options = Options()
options.add_argument('--incognito')
options.binary_location = 'C:/Program Files (x86)/Google/Chrome/Application/chrome.exe'
driver = webdriver.Chrome(ChromeDriverManager().install(), options=options)
driver.maximize_window()
driver.get(
'https://www.linkedin.com/login?fromSignIn=true&trk=guest_homepage-basic_nav-header-signin'
)
time.sleep(1)
# enter login info
user = driver.find_element_by_xpath(
'/html/body/div/main/div[2]/form/div[1]/input')
user.send_keys('EMAIL')
pswd = driver.find_element_by_xpath(
'/html/body/div/main/div[2]/form/div[2]/input')
pswd.send_keys('PASSWORD')
# submit form, try catch because it was having issues finding the button by a single absolute path
try:
driver.find_element_by_xpath(
'/html/body/div/main/div[2]/form/div[4]').click()
except Exception:
try:
driver.find_element_by_xpath(
'/html/body/div/main/div[2]/form/div[3]/button').click()
except Exception:
driver.find_element_by_xpath(
'//*[@id="app__container"]/main/div[2]/form/div[4]/button'
).click()
try:
driver.find_element_by_link_text('Sign in').click()
except Exception:
quit()
time.sleep(1)
# try catch for mobile authentication, seems unnecessary as of now
try:
driver.find_element_by_xpath(
'/html/body/div/div[1]/section/div[2]/div/article/footer/div/div/button'
).click()
except Exception:
print('No auth needed')
driver.find_element_by_xpath(
'/html/body/div[7]/header/div[2]/nav/ul/li[2]/a/span').click()
time.sleep(5)
driver.find_element_by_xpath(
'/html/body/div[7]/div[3]/div/div/div/div/div/aside/div/div/div[1]/section/div/div[1]/a'
).click()
time.sleep(3)
# need a way to both A: scroll through every single connection B: search for specific line in header of title
# NEED CRITERIA AND MESSAGE TO SEND
li_count = 11
while True:
try:
title = driver.find_element_by_xpath(
'/html/body/div[7]/div[3]/div/div/div/div/div/div/div/div/section/ul/li['
+ str(li_count) + ']/div[1]/a/span[4]')
actions = ActionChains(driver)
actions.move_to_element(title).perform()
temp = title.text
# if li_count < 123:
# li_count += 1
# continue
if "Booz Allen" in temp and (
"Lead Associate" in temp or "Senior Associate" in temp
or "Sr. Associate" in temp) and (
"Vice President" not in temp
or "Program Manager" not in temp
): # and criteria in temp: #need criteria from pamela
name = driver.find_element_by_xpath(
'/html/body/div[7]/div[3]/div/div/div/div/div/div/div/div/section/ul/li['
+ str(li_count) + ']/div[1]/a/span[2]')
name = str(name.text)
print(name)
name = name.split(' ')
name = name[0]
driver.find_element_by_xpath(
'/html/body/div[7]/div[3]/div/div/div/div/div/div/div/div/section/ul/li['
+ str(li_count) +
']/div[2]/div[1]/button/span[1]').click()
msgb = driver.find_element_by_xpath(
'/html/body/div[7]/aside/div[2]/div[1]/form/div[3]/div/div[1]/div[1]'
)
time.sleep(2)
msgb.send_keys(
name +
'- Glad to connect here. Advantech proudly continues to receive accolades from BAH VPs and PMs as your Technical & Professional Services HUBZone teammate for over 14 years, having supported BAH on 40+ national contracts, which is the reason our organization mirrors Booz Allen.\nPlease take a look at us at: http://advantech-gs.com.\n\nWe help Booz win by adding the hard to meet HUBZone goals; as you know, HUBZones in the professional service sector are very rare, so we are proud to provide competence and excellence in services, a differentiation that adds value to your team!\n\nWe\'re very proud of our reputation providing successful staff and contract management to support BAH, and I\'ve linked a reference here for you, if you\'d like to see what others at BAH have to say.\nhttps://www.linkedin.com/posts/advantech-gs-enterprises-inc_activity-6719290412378537984-2u8g\n\nPlease let me know what other information we can provide, or if you\'d like to have a quick call re: how else we can help you.\n\nMy email address is [email protected], and my cell number is 858.705.3069.\n\nThank you for your continued support!\nVery respectfully,\nJack Fraser, President & CEO\n'
)
time.sleep(2)
driver.find_element_by_xpath(
'/html/body/div[7]/aside/div[2]/div[1]/form/footer/div[2]/div[1]/button'
).click()
time.sleep(2)
driver.find_element_by_xpath(
'/html/body/div[7]/aside/div[2]/header/section[2]/button[2]'
).click()
li_count += 1
else:
li_count += 1
except Exception:
print('failed to find title')
li_count += 1
continue
def shubiao_zhixiang_xpath(self,shuxing):
try:
article = geturl.llq.find_element_by_xpath(shuxing)
ActionChains(geturl.llq).move_to_element(article).perform()
except:
geturl.error(1)
from selenium import webdriver from selenium.webdriver.common.by import By from init import Init from selenium.webdriver import ActionChains import time driver = webdriver.Chrome(executable_path=Init.driver) driver.get(Init.url9) driver.implicitly_wait(10) driver.maximize_window() username = '******' password = '******' login = '******' driver.find_element(By.XPATH, username).clear() driver.find_element(By.XPATH, password).clear() driver.find_element(By.XPATH, username).send_keys(Init.username) driver.find_element(By.XPATH, password).send_keys(Init.password) driver.find_element(By.XPATH, login).click() header = driver.find_element(By.XPATH, '//*[@id="main"]/div[1]/span/div/div') actions = ActionChains(driver) actions.context_click(header).perform()
def joongonara(keyword):
url = 'https://m.joongna.com/search-list/product?searchword={}&dateFilter=7'.format(
keyword)
options = webdriver.ChromeOptions()
# options.add_argument("user-agent={}".format(UserAgent().chrome))
options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36"
)
options.add_argument("headless")
driver = webdriver.Chrome(options=options)
driver.get(url)
tag = driver.find_element_by_xpath(
'//*[@id="root"]/div[1]/div[2]/div[1]/div/button')
action = ActionChains(driver)
while True:
try:
action.move_to_element(tag).perform()
driver.find_element_by_xpath(
'//*[@id="root"]/div[1]/div[2]/div[1]/div/button/span').click(
)
time.sleep(2)
except:
break
links = driver.find_elements_by_css_selector('.pd_h20 div > div > a')
print("loaded {} items!!!".format(len(links)))
df = []
n = 1
for link in links:
link = link.get_attribute('href')
options = webdriver.ChromeOptions()
options.add_argument("headless")
# options.add_argument("user-agent={}".format(UserAgent().chrome))
options.add_argument(
"user-agent=Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36"
)
driver = webdriver.Chrome(options=options)
driver.get(link)
time.sleep(1)
try:
title = driver.find_element_by_css_selector('.pd20 > p').text
view_count = driver.find_element_by_css_selector(
'p .c_orange').text
desc = driver.find_elements_by_css_selector(
'.ProductDetailComponent_tag__1sc7f.mb8')[0].text
price = driver.find_element_by_css_selector('.pd20 strong').text
except:
print("err", end=" ")
driver.quit()
continue
try:
region = driver.find_elements_by_css_selector(
'button .f15')[0].text
except:
region = None
df.append({
'title': title,
'price': price,
'region': region,
'view_counts': view_count,
'desc': desc,
'link': link,
'market': '중고나라',
'keyword': keyword
})
driver.quit()
print(n, end=" ")
n += 1
driver.quit()
today = datetime.now()
delta = timedelta(days=1)
today_1 = today - delta
config = configparser.ConfigParser()
config.read('/home/ubuntu/masterpiece/mongo.ini')
mongodb_ip = config["mongo"]
client = pymongo.MongoClient(mongodb_ip["ip_address"])
db = client.joongo
collection = db["D{}".format(today.strftime('%y%m%d'))]
collection.insert(df)
client.joongo.drop_collection("D{}".format(today_1.strftime('%y%m%d')))
print("Done Crawling and Insert into Mongodb")
return pd.DataFrame(df)
def hover(self, element):
ActionChains(self.driver).move_to_element(element).perform()
element = driver.find_element_by_css_selector(
"#fcxH9b > div.WpDbMd > c-wiz:nth-child(5) > div > c-wiz > div > div > c-wiz > c-wiz:nth-child(1) > c-wiz > div > div.Z3lOXb > div.W9yFB > a"
)
element.click()
'''페이지에 들어가자마자 50위 수집'''
#순위를 수집하는 코드
firstElementList = driver.find_elements_by_css_selector(
"#fcxH9b > div.WpDbMd > c-wiz:nth-child(6) > div > c-wiz > div > c-wiz > c-wiz > c-wiz > div > div.ZmHEEd > div"
)
#수집한 순위의 마지막 요소를 선택
LastElement = firstElementList[-1]
#마지막 요소로 스크롤을 이동시켜라
ActionChains(driver).move_to_element(LastElement).perform()
#스크롤을 내리고 3초 쉬게 한다 요소가 불러올시간을 주기위함
'''스크롤을 내림으로써 새롭게 생긴 태그를 다시한번 불러온다'''
for i in range(1, 4):
time.sleep(3)
elementList = driver.find_elements_by_css_selector(
"#fcxH9b > div.WpDbMd > c-wiz:nth-child(6) > div > c-wiz > div > c-wiz > c-wiz > c-wiz > div > div.ZmHEEd > c-wiz"
)
LastElement = elementList[-1]
ActionChains(driver).move_to_element(LastElement).perform()
#firstElementList -1 ~50까지 앱 요소
#elementList - 51~200위 까지 앱 요소
elementList = firstElementList + elementList
def double_click(context, element):
ActionChains(context.driver).double_click(element).perform()
from selenium import webdriver
from selenium.webdriver import ActionChains
import time
driver = webdriver.Chrome()
driver.get("https://www.qcc.com")
driver.maximize_window()
# 弹出框
driver.find_element_by_xpath(
"//*[@id='addfavorModal']/div/div/div[1]/img[1]").click()
# 登录
driver.find_element_by_link_text("登录 | 注册").click()
time.sleep(5)
# 获取模块
ele = driver.find_element_by_xpath("//*[@id='nc_1_n1z']")
# actionchain
ac = ActionChains(driver)
ac.click_and_hold(ele).move_by_offset(348, 0).perform()
time.sleep(3)
driver.quit()
def extract_user_info(driver, review):
user_dict = {}
#find the user profile and set up the click action;
try:
reviewer_prof = review.find_element_by_xpath(
'.//div[contains(@class,"memberOverlayLink")]')
Click = ActionChains(driver).click(reviewer_prof)
#if that fails, it's probably because the user has no account (probably deleted?)
except:
user_dict['username'] = '******'
return user_dict
#click on the profile and wait until it loads
profile_wait = WebDriverWait(driver, 3)
try:
Click.perform()
profile = profile_wait.until(
EC.presence_of_element_located(
(By.XPATH, '//div[@class="memberOverlayRedesign g10n"]')))
except:
user_dict['username'] = None
return user_dict
#extract user info
#username
reviewer_link = driver.find_element_by_xpath(
'//div[@class="memberOverlayRedesign g10n"]/a').get_attribute('href')
reviewer_username = re.sub('.*members/', '', reviewer_link)
#demos
reviewer_demos = driver.find_elements_by_xpath(
'//ul[@class="memberdescriptionReviewEnhancements"]/*')
reviewer_demos = [element.text for element in reviewer_demos]
reviewer_demos = ";".join(reviewer_demos)
#reviewer rating histogram
histogram_rows = driver.find_elements_by_xpath(
'//div[@class="chartRowReviewEnhancements"]')
review_hist = []
for row in histogram_rows:
n_reviews = row.find_element_by_xpath('./span[3]').text
review_hist += [n_reviews]
review_hist = ";".join(review_hist)
#reviewer helpful votes
try:
helpvotes = driver.find_element_by_xpath(
'//div[@class="memberOverlayRedesign g10n"]//*[contains(text(), "Helpful votes")]'
).text
except:
helpvotes = None
#reviewer cities visited
try:
n_cities_visited = driver.find_element_by_xpath(
'//div[@class="memberOverlayRedesign g10n"]//*[contains(text(), "Cities visited")]'
).text
except:
n_cities_visited = None
#reviewer tags
tags = driver.find_elements_by_xpath(
'//a[@class="memberTagReviewEnhancements"]')
tags = [tag.text for tag in tags]
tags = ";".join(tags)
#build dict item
user_dict['username'] = reviewer_username
user_dict['demos'] = reviewer_demos
user_dict['review_hist'] = review_hist
user_dict['helpvotes'] = helpvotes
user_dict['n_cities_visited'] = n_cities_visited
user_dict['tags'] = tags
user_dict['time_accessed'] = str(datetime.datetime.now())
#close the user profile -- make sure it's closed before moving on
close_profile_button = driver.find_element_by_xpath(
'//span[@class="ui_overlay ui_popover arrow_left "]/div[@class="ui_close_x"]'
)
close_profile_button.click()
profile_wait.until_not(
EC.presence_of_element_located(
(By.XPATH, '//span[@class="ui_overlay ui_popover arrow_left "]')))
return user_dict
# 2.获取用户名和密码的输入框，和登录按钮
username = dirver.find_element_by_name('username')
password = dirver.find_element_by_xpath(".//*[@id='loginForm']/input[2]")
login_button = dirver.find_element_by_xpath("//input[@type='submit']")
# 3.使用send_keys方法输入用户名和密码，使用click方法模拟点击登录
username.send_keys("qiye")
password.send_keys("qiye_pass")
login_button.click()
# 轮流点击选项卡
#select = dirver.find_element_by_xpath("//form/select")
#all_options = select.find_elements_by_tag_name("option")
#for option in all_options:
# print("Value is: %s"% option.get_attribute("value"))
# option.click()
# 根据索引/文字/value值来获取选项卡
from selenium.webdriver.support.ui import Select
#select = Select(dirver.find_element_by_xpath('//form/select '))
#select.select_by_index(1)
#select.select_by_visible_text("用户名")
#select.select_by_value("name")
# 元素拖拽
element = dirver.find_element_by_name("source")
target = dirver.find_element_by_name("target")
from selenium.webdriver import ActionChains
action_chains = ActionChains(dirver)
action_chains.drag_and_drop(element,target).perform()
