[Python] 纯文本查看 复制代码# -*- coding: UTF-8 -*-
from docx import Document #安装 pip install python-docx
import re
from selenium import webdriver
from mon.exceptions import NoSuchElementException
import time
# 凡是出现sleep的，都是因为网络等原因加载过慢，需要等一等
# 登录云盘
def login(driver,username,password):
orgin_url = '/'
driver.get(orgin_url)
try:
time.sleep(5)
elem_static = driver.find_element_by_id("TANGRAM__PSP_4__footerULoginBtn")
elem_static.click()
time.sleep(0.5)
elem_username = driver.find_element_by_id("TANGRAM__PSP_4__userName")
elem_username.clear()
elem_username.send_keys(username)
elem_userpas = driver.find_element_by_id("TANGRAM__PSP_4__password")
elem_userpas.clear()
elem_userpas.send_keys(password)
elem_submit = driver.find_element_by_id("TANGRAM__PSP_4__submit")
elem_submit.click()
time.sleep(5)
except NoSuchElementException:
pass
# 将加密分享的文件保存到自己云盘的目录下
def extract(driver,srcurl,srcpwd):
driver.get(srcurl)
try:
getpwd = driver.find_element_by_id("mwxxPOD") #("esDEV5")
getpwd.send_keys(srcpwd)
getButton = driver.find_element_by_link_text("提取文件")
getButton.click()
time.sleep(10)
# 目前有两种情况
# 一：分享文件是一压缩包
# 二：分享的是一路径
try:# 全选（情况二）
selectall = driver.find_element_by_class_name("zbyDdwb")
selectall.click()
except NoSuchElementException:
file_name = "no_zbyDdwb.png"
driver.save_screenshot(file_name)
driver.get_screenshot_as_file(file_name)
pass
savetodisk = driver.find_element_by_link_text("保存到网盘")
savetodisk.click()
time.sleep(5)
# AA 为指定的自己网盘保存路径
selectdir = driver.find_element_by_xpath("//span[@node-path='/AA']")
selectdir.click()
enter = driver.find_element_by_link_text("确定")
enter.click()
time.sleep(2)
except NoSuchElementException:
file_name = "no_such_element.png"
driver.get_screenshot_as_file(file_name)
pass
def read_docx(path):
fulltext=[]
list1=[]
listUrl=[]
listpwd=[]
#生成word对象，并指向word文件
doc=Document(path)
#读取对象的全部内容，不包括图片和表格
paras=doc.paragraphs
#将每行数据存入列表
for p in paras:
fulltext.append(p.text)
for i, element in enumerate(fulltext):
if element.find("https:")!=-1:
list1.append(i)
for j in range(len(list1)):
k =list1[j]
link = re.findall(r'.*(https.*)',fulltext[k].replace(u"\xa0",u"").replace(" ",""))
listUrl.append(link[0])
pwd = re.findall('[a-zA-Z0-9]{4}',fulltext[k+1])
listpwd.append(pwd[0])
#print(len(listUrl),len(listpwd))
return listUrl,listpwd
# 调用执行
def doWork():
# 存放链接的文件
path=r'文件地址***.docx'
listUrl,listpwd= read_docx(path)
driver = webdriver.Chrome(executable_path='D:\Program10\python37\chromedriver\chromedriver')
login(driver,"网盘帐户名***","密码***")
for index in range(len(listUrl)):
srcurl = listUrl[index]
srcpwd = listpwd[index]
extract(driver,srcurl,srcpwd)
driver.quit()
if __name__ == '__main__':
doWork()
