def _crawl(detail_link: str, driver: WebDriver) -> Info:
driver.get(detail_link)
time.sleep(5)
accordeon = driver.find_elements_by_class_name('accordeon')
try:
driver.find_element_by_class_name(
'moove-gdpr-infobar-allow-all').click(
) # get rid of cookie banner blocking all clicks on this website
except:
pass
info = _get_all_present_fields(accordeon, driver)
return _convert(info)
def batchAccept(browser: WebDriver):
# 批量受理
u = 'http://10.204.14.35/eoms4/sheetBpp/myWaitingDealSheetQueryty.action?baseSchema=WF4_EL_TTM_TTH_EQU&var_pagesize=100'
browser.get(u)
total_ele = 'form#form1 span.pagenumber'
total_element = browser.find_element(By.CSS_SELECTOR, total_ele)
total = re.search(r'共([0-9]+)条数据', total_element.text).group(1)
if total < 1:
return
todo_list = browser.find_elements(By.CSS_SELECTOR, 'table#tab tr')[1:]
data = []
i = 0
for x in range(0, int(total)):
title = todo_list[2 * x + 1].text
if title.find('[数据网]') != -1:
checkbox = todo_list[2 * x].find_element(By.NAME, 'checkid')
checkbox.click()
# batchAccept_btn = browser.find_element(By.CSS_SELECTOR, 'li.page_active_button')
browser.execute_script('batchAccept();')
def _crawl_detail_page(driver: WebDriver) -> List[DetailPageInfo]:
detail_pages_infos = []
for idx in range(1, 315):
driver.get(URL)
rows: List[WebElement] = _get_table_rows(driver)
for row in rows:
cols = row.find_elements_by_tag_name('td')
row_idx: int = extract_idx(cols[0])
if row_idx == idx:
link_element = cols[0].find_element_by_tag_name('a')
link_element.click()
detail_page_info = _extract_detail_info(driver, idx)
detail_pages_infos.append(detail_page_info)
break
_clean_detail_pages(detail_pages_infos)
return detail_pages_infos
def jumpToEOMS(browser: WebDriver, keyword='') -> list:
eoms_url = 'http://uip.ln.cmcc/_layouts/Document/BridgeToSPControl.aspx?skipcode=emoss'
browser.get(eoms_url)
# 故障处理工单(设备)：
todo_list_url = 'http://10.204.14.35/eoms4/sheetBpp/myWaitingDealSheetQueryGlobalTemplate.action?baseSchema=WF4_EL_TTM_TTH_EQU&var_pagesize=100'
browser.get(todo_list_url)
total_ele = 'form#form1 span.pagenumber'
total_element = browser.find_element(By.CSS_SELECTOR, total_ele)
total = re.search(r'共([0-9]+)条数据', total_element.text).group(1)
# oo = $('table#tab tr')
# Array.prototype.shift.apply(oo)
todo_list = browser.find_elements(By.CSS_SELECTOR, 'table#tab tr')[1:]
def get_url(title_ele):
onclick = title_ele.find_element_by_tag_name('a').get_attribute(
'onclick')
args = re.findall(r'\'(.*?)\'', onclick)
# browser.execute_script('')
url = 'http://10.204.14.35/eoms4/sheet/openWaittingSheet.action?baseSchema={}&taskid={}&baseId={}&entryId=&version=&processType={}'
url = url.format(args[0], args[2], args[1], args[3])
# url = 'http://10.204.14.31:8001/bpp/ultrabpp/view.action?baseSchema={}&baseId={}&taskid={}&processType={}'
# url = url.format(args[0], args[1], args[2], args[3])
return url
data = []
# 待处理工单统计
i = 0
for x in range(0, int(total)):
title = todo_list[2 * x + 1]
if title.text.find(keyword) != -1:
data.append({})
data[i]['title'] = title.text[21:]
content = todo_list[2 * x].find_elements_by_tag_name('td')
data[i]['end_time'] = datep(content[4].text)
data[i]['find_time'] = datep(content[5].text)
data[i]['status'] = content[6].text
data[i]['url'] = get_url(title)
i += 1
# 上清除时间的工单统计
data2 = []
# 未上清除时间统计
data3 = []
j = 0
for x in range(i):
browser.get(data[x]['url'])
data[x]['clear_time'] = browser.find_element_by_id(
'INC_Alarm_ClearTime').get_attribute('value')
title_match = re.search(r'([A-Z\-0-9]+) 上报 (.+)', data[x]['title'])
try:
data[x]['device'] = title_match.group(1)
data[x]['event'] = title_match.group(2)
except:
pass
if data[x]['clear_time'] != '':
data2.append(data[x])
j += 1
else:
data3.append(data[x])
# TODO 详细推送
msg_title = '{}故障工单 {} 个，已上清除 {} 个。'
msg_title = msg_title.format(keyword, len(data), len(data2))
find_time2, find_time3 = [], []
if data2 != []:
for x in data2:
find_time2.append(datef(x['find_time']))
if data3 != []:
for x in data3:
find_time3.append(datef(x['find_time']))
msg_text = '### {}\n\n**已上清除建单时间分别为**：\n\n{}\n\n**未上清除建单时间分别为**：\n\n{}\n\n> 推送时间：{}'
t2, t3 = '\n\n'.join(find_time2), '\n\n'.join(find_time3)
msg_text = msg_text.format(msg_title, t2, t3, datef())
send_msg(msg_markdown(msg_title, msg_text, True))
browser.get(eoms_url)
return data, data2, data3
def cleanUpCookiesAndLaunchIE(self):
caps = DesiredCapabilities.INTERNETEXPLORER
ie = WebDriver()
ie.delete_all_cookies()
ie.get("http://www.yahoo.com")
return ie
def cleanUpCookiesAndLaunchIE(self):
caps = DesiredCapabilities.INTERNETEXPLORER
ie = WebDriver()
ie.delete_all_cookies()
ie.get("http://www.yahoo.com")
return ie