options.add_argument('ignore-certificate-errors')

# 設(shè)置默認(rèn)地址
prefs = {'download.default_directory': r'D:\desktop\test_download'}
options.add_experimental_option('prefs', prefs)

# 導(dǎo)入所需要的庫
import time
import json
import warnings
from selenium import webdriver
from sqlalchemy import create_engine
from selenium.webdriver.common.by import By
from selenium.webdriver.chrome.service import Service
from selenium.webdriver.support.wait import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
# 運(yùn)行時(shí)terminal里面會(huì)出現(xiàn)好多警告,剔除警告
warnings.filterwarnings('ignore')
class Download():
	def __init__(self, url, year, path, chrome, username, password, elements):
		self.year = year
		self.url = url
		self.path = path
		self.chrome = chrome
		self.username = username
		self.password = password
		self.elements = elements
	# 瀏覽器設(shè)置
	def web_sets(self):
		self.options = webdriver.ChromeOptions()
		# 因?yàn)槲沂褂玫氖枪雀铻g覽器
		self.c_service = Service(f'{self.chrome}')
		self.c_service.command_line_args()
		# 設(shè)置后端服務(wù)器開始，因?yàn)闀?huì)在后臺(tái)產(chǎn)生好多服務(wù),為了后面的關(guān)閉
		self.c_service.start()
		# 提供默認(rèn)下載地址
		self.prefs = {'download.default_directory': f'{self.path}'}
		self.options.add_experimental_option('prefs', self.prefs)
		# 設(shè)置忽略安全證書所帶來的錯(cuò)誤
		self.options.add_argument('ignore-certificate-errors')
		# 一些小的設(shè)置
		self.options.add_experimental_option('excludeSwitches', ["enable-automation"])
		self.options.add_argument('--np-sanbox')
		self.options.add_argument('--disable-dev-shm-usage')
		# 加屬性避免bug
		self.options.add_argument('disable-gpu')
		# 添加無頭模式
		self.options.add_argument('headless')
		self.br = webdriver.Chrome(f'{self.chrome}', chrome_options=self.options)
		self.br.implicitly_wait(3)
	def loginPage(self):
		"""
		因?yàn)槲沂菍⑺性乇４嬖趈son文件里面，這樣就不需要因?yàn)閒ind_element而占用好多列
		也為代碼節(jié)省地方
		這里需要強(qiáng)調(diào)的時(shí)find_element(By.XPATH)是最新selenium的使用方法,之前的使用會(huì)報(bào)錯(cuò)
		"""
		self.br.get(self.url)
		time.sleep(4)
		self.br.find_element(By.XPATH, f'{self.elements[keys[2]]}').send_keys(self.username)
		time.sleep(2)
		self.br.find_element(By.XPATH, f'{self.elements[keys[3]]}').send_keys(self.password)
		time.sleep(2)
		self.br.find_element(By.XPATH, f'{self.elements[keys[4]]}').click()
		time.sleep(2)
	# 設(shè)置跳轉(zhuǎn)到最后頁面
	def skipPage(self, url):
		self.br.get(url)
		time.sleep(2)

	# 下載文件
	def download_excel(self):
		# 獲取所有ul下面的li標(biāo)簽個(gè)數(shù)
		ul2 = self.br.find_element(By.XPATH, f'{self.elements[keys[6]]}')
		# 獲取li標(biāo)簽數(shù)目
		lis2 = ul2.find_elements(By.XPATH, 'li')
		time.sleep(1)
		# 循環(huán)li標(biāo)簽
		for j in range(len(lis2)):
			# 因?yàn)閘i的elements都是從1開始,python列表是從0開始,所以要+1
			j+=1
			# 獲取li標(biāo)簽的text
			name = self.br.find_element(By.XPATH, f'{self.elements[keys[7]][1]}'%j).get_attribute('title')
			print(f'li標(biāo)簽name: {name}')
			if '日?qǐng)?bào)' in name:
				print(f'第二遍過濾name: {name}')
				li_test = self.br.find_element(By.XPATH, f'{self.elements[keys[8]]}'%j)
				self.br.execute_script('arguments[0].click();',li_test)
				time.sleep(0.5)
				self.br.find_element(By.XPATH, f'{self.elements[keys[9]]}').click()
				time.sleep(0.5)
				li_test2 = self.br.find_element(By.XPATH, f'{self.elements[keys[8]]}'%j)
				time.sleep(1)
				# 設(shè)置點(diǎn)擊覆蓋，以防止報(bào)錯(cuò)
				# 因?yàn)橐恢币M點(diǎn)擊選擇文件,然后進(jìn)行下載文件,防止點(diǎn)擊覆蓋
				self.br.execute_script("arguments[0].click();", li_test2)
				time.sleep(8)
		time.sleep(10)
		time.sleep(12)
		# 退出瀏覽器,推出后臺(tái)服務(wù)
		# c_service.stop()對(duì)應(yīng)之前的c_service.stop()
		self.br.quit();self.c_service.stop()

xpath: //*[@id="main"]/div[2]/div/div[3]/div[1]/as-dataview/div[2]/ul
full_xpath: /html/body/div[2]/div[1]/div[2]/div/div[1]/div[2]/div/div[3]/div[1]/as-dataview/div[2]/ul

if __name__ == '__main__':
	jsonFile = r'JsonFile\elements.json'
	with open(jsonFile, 'r') as f:
		row_data = json.load(f)
	# 獲取所有json的鍵
	keys = list(row_data.keys())
	# 讀取賬號(hào)和密碼
	filename = row_data[keys[0]]
	# 獲取賬號(hào)和密碼txt
	with open(filename, 'r') as f:
		data = f.read()
	data1 = data.split('\n')
	url = 'url'
	# chromedriver.exe
	chrome = r'chromedriver.exe'
	username = data1[0]
	password = data1[1]
	path = row_data[keys[1]]
	year = time.gmtime().tm_year
	start = Download(url, year, path, chrome, username, password, row_data)
	start.web_sets()
	start.loginWeb()
	e = row_data[keys[5]]
	start.skipPage(e)
	start.download_excel()
	time.sleep(15)