学习笔记20190309

from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.common.exceptions import NoSuchElementException
import time
###################常量设置
TIME_FOR_LOGIN=60###################预留n秒用于扫码登录 
READING_STEP=10###################分10次读完一篇文章
TIME_FOR_READING=18###################n秒阅读完一篇文章十分之一
TIME_FOR_AJAX=10##########################预留三秒用于异步加载
HOME_PAGE=''
PAPER_COUNT=6##############文章数6
VIDEO_COUNT=6#############视频数6
TIME_FOR_VIDEO=300#30秒后开始计时
TIME_FOR_NEWS=30

#创建浏览器
browser=webdriver.Chrome()
####################################阅读文章任务
browser.get(HOME_PAGE)
#等待手工扫码登录
#time.sleep(TIME_FOR_LOGIN)
for i in range(1,TIME_FOR_LOGIN+1):#
     print('已等待扫码：'+str(i)+'秒……')
     time.sleep(1)
n=0
#先读取已观看记录
has_read=dict()
read=open('观看记录.txt','r')
for line in read:
     n+=1
     has_read[line]=''
read.close()

n=0
read=open('观看记录.txt','a')


#再读取文章列表
paper=dict()
f=open('文章URL.txt','r')
for line in f:
     n+=1
     paper[line]=''
f.close()
readingIndex=0 
for url in paper:
     #print(url)
     if url not in has_read and  readingIndex<PAPER_COUNT :
          readingIndex=readingIndex+1
          #阅读 计时
          browser.get(url)
          read.write(url)#追加记录
          for i in range(1,READING_STEP+1):#
               js="window.scrollTo("+str((i-1)/READING_STEP)+"*document.body.scrollHeight,"+str(i/READING_STEP)+"*document.body.scrollHeight)"
               print('第 '+str(readingIndex)+' 篇文章浏览进度：'+str(i/READING_STEP*100)+'% ')
               browser.execute_script(js)
               #time.sleep(TIME_FOR_READING)
               for i in range(1,TIME_FOR_READING+1):
                    print('正在阅读第'+str(readingIndex)+'篇文章，已观看：'+str(i//60)+'分'+str(i % 60)+'秒')
                    time.sleep(1)

#再读取视频记录
news=dict()
f=open('视频URL.txt','r')
for line in f:
     n+=1
     news[line]=''
f.close()

readingIndex=1 
for url in news:
     #print('视频'+url)
     if url not in has_read and  readingIndex<=VIDEO_COUNT :
         #阅读 计时
          browser.get(url)
          print('请稍后，正在判断视频')
          #time.sleep(TIME_FOR_AJAX)
          for i in range(1,TIME_FOR_AJAX+1):#
               print('请稍后，正在判断视频：'+str(i)+'秒……')
               time.sleep(1)
          try:
               isnews=True
               e=browser.find_element(By.ID,'C2k4pjg7itcs00')#Cgi6ap0m271c00
          except NoSuchElementException:
               isnews=False
               print('这个不是新闻联播')
          
          if isnews==False:
               print('正在观看第'+str(readingIndex)+'个视频')
               try:
                    btn=browser.find_element_by_class_name('outter')
                    btn.click()
                    read.write(url)#追加记录
                    time.sleep(TIME_FOR_AJAX)
                    for i in range(1,TIME_FOR_VIDEO+1):
                         print('正在观看第'+str(readingIndex)+'个视频，已观看：'+str(i//60)+'分'+str(i % 60)+'秒')
                         time.sleep(1)
                    readingIndex=readingIndex+1
               except NoSuchElementException:
                    print("这不是视频网页")
#观看新闻联播
readingIndex=0
for url in news:
     #print(url)
     if url not in has_read and  readingIndex<1 :
         #阅读 计时
          browser.get(url)
          #time.sleep(TIME_FOR_AJAX)
          for i in range(1,TIME_FOR_AJAX+1):#
               print('请稍后，正在判断新闻：'+str(i)+'秒……')
               time.sleep(1)
          try:
               isnews=True
               e=browser.find_element(By.ID,'C2k4pjg7itcs00')#Cgi6ap0m271c00  'Cgi6ap0m271c00
          except NoSuchElementException:
               isnews=False   
          if isnews==True:
               readingIndex+=1
               #browser.get(url)
               #browser.refresh()
               read.write(url)#追加记录
               btn=browser.find_element_by_class_name('outter')
               btn.click()
               time.sleep(TIME_FOR_AJAX)
               for i in range(1,TIME_FOR_NEWS+1):
                    print('正在观看新闻联播，已观看：'+str(i//60)+'分'+str(i % 60)+'秒')
                    time.sleep(1)
read.close()