使用po模式读取豆瓣读书最受关注的书籍,取出标题、评分、评论、题材 按评分从小到大排序并输出到txt文件中

#coding=utf-8
from time import sleep
import unittest
from selenium import webdriver
from selenium.webdriver import Remote
from selenium.webdriver.common.by import By#元素定位
import sys

def browser():#启动浏览器驱动
    '''
    driver = Remote(command_executor='http://127.0.0.1:4444/wd/hub',
                                                desired_capabilities={'platform':'ANY',
                                                                      'browserName':'chrome',
                                                                      'version':'',
                                                                     })'''
    driver = webdriver.Ie()
    return driver

class MyTest(unittest.TestCase):#框架

    def setUp(self):
        print("开始执行用例!")
        self.driver = browser()
        self.driver.implicitly_wait(10)
        self.driver.maximize_window()

    def tearDown(self):
        self.driver.quit()
        print('用例执行结束!')
        
class Page(object):#基础类
    '''
    页面基础类,用于所有页面的继承
    '''
    bbs_url = 'https://book.douban.com/'
    
    def __init__(self,selenium_driver,base_url=bbs_url,parent=None):#初始化
        self.base_url = base_url
        self.driver = selenium_driver
        self.timeout = 30
        self.parent = parent
    
    def on_page(self):#断言url是否相等
        return self.driver.current_url == (self.base_url + self.url)
        
    def _open(self,url):
        url = self.base_url + url
        self.driver.get(url)
        assert self.on_page(),'获取的url和当前url不匹配.url:%s' % url
          
    def open(self):#打开浏览器  
        self._open(self.url)
    
    def find_element(self,*loc):#单个元素定位
        return self.driver.find_element(*loc)
    
    def find_elements(self,*loc):#多个元素定位
        return self.driver.find_elements(*loc)
    

class Douban_film(Page):#页面对象封装
    u'''豆瓣读书排序'''
    url = '/'
    #元素定位
    bbs_booknum_loc = (By.XPATH,'//li/div[2]/p[1]/span[2]')#评分
    bbs_bookname_loc = (By.XPATH,'//li/div[2]/h4/a')#书名
    bbs_bookauther_loc = (By.XPATH,'//li/div[2]/p[2]')#作者
    bbs_booktype_loc = (By.XPATH,'//li/div[2]/p[3]')#类型
    bbs_bookcomments_loc = (By.XPATH,'//li/div[2]/p[5]')#评论
    #元素封装
    def bbs_bookname(self):#豆瓣评分
        _input = self.driver.find_elements(*self.bbs_bookname_loc)# 选择页面上所有的tag name 为input 的元素
        bookname = []
        for i in _input:
            bookname.append(i.text)#取出值并添加到数组
        else:
            sleep(1)
        return bookname
                              
    def bbs_booknum(self):#豆瓣评分
        _input = self.driver.find_elements(*self.bbs_booknum_loc)# 选择页面上所有的tag name 为input 的元素
        booknum = []
        for i in _input:
            booknum.append(i.text)#取出值并添加到数组
        else:
            sleep(1)
        return booknum
        
    def bbs_bookauther(self):#作者
        _input = self.driver.find_elements(*self.bbs_bookauther_loc)# 选择页面上所有的tag name 为input 的元素
        bookauther = []
        for i in _input:
            bookauther.append(i.text)#取出值并添加到数组
        else:
            sleep(1)
        return bookauther

    def bbs_booktype(self):#类型
        _input = self.driver.find_elements(*self.bbs_booktype_loc)# 选择页面上所有的tag name 为input 的元素
        bookautype = []
        for i in _input:
            bookautype.append(i.text)#取出值并添加到数组
        else:
            sleep(1)
        return bookautype
        
    def bbs_bookcomments(self):#评论
        _input = self.driver.find_elements(*self.bbs_bookcomments_loc)# 选择页面上所有的tag name 为input 的元素
        bookaucomments = []
        for i in _input:
            bookaucomments.append(i.text)#取出值并添加到数组
        else:
            sleep(1)
        return bookaucomments
    
    def out_node(self):#排序
        list1 = self.bbs_booknum()
        list2 = self.bbs_bookname()
        list3 = self.bbs_bookauther()
        list4 = self.bbs_booktype()
        list5 = self.bbs_bookcomments()
        list = [[a,b,c,d,e] for a,b,c,d,e in zip(list1,list2,list3,list4,list5)]
        team = list[:]
        team.sort()
        print('从小到大排序:%s'%team)
        return team
    
    def writetxt(self):#写入txt文件
        a = self.out_node()
        f1 = open('b.txt','w',encoding='utf-8')#写入文件编码格式,不写的话有时候会导致解析错误   
        for i in a:#循环读取内嵌列表
            #if isinstance(i,list):#判断是否是一个列表
            print(i)#分别打印内嵌列表里的列表
            f1.writelines(i)#写入txt文件
            f1.write('\n')#写入文件时换行
        f1.close()
          
class test_Douban_film(MyTest):
    u'''豆瓣读书排序'''
    
    def test1(self):
        u'''豆瓣评分按降序排列并保存到txt文件'''
        p1 = Douban_film(self.driver)
        p1.open()
        p1.writetxt()

if __name__ == '__main__':
    unittest.main()

上一篇:Spark在处理数据的时候,会将数据都加载到内存再做处理吗?


下一篇:Servlet入门笔记