1

我刚开始学习Python。我想写一个蜘蛛程序来在网上找些笑话。当我运行程序时它警告：'AttributeError：'Spi​​der_Model'对象没有属性'pages'。而且我在网上找到的解决方案不起作用。这是代码。请看一下。

import urllib.request as  request
import re
#import _thread
import time

class Spider_Model:

def __int__(self):
    self.page = 1
    self.pages = []
    self.enable = False

# Download all the jokes and save it to the list
def GetPage(self, page):
    myUrl = 'https://www.qiushibaike.com/hot/' + str(page)
    user_agent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_3) \
                  AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
    headers = {'User_Agent' : user_agent}
    req = request.Request(myUrl, headers = headers)
    myResponse = request.urlopen(req)
    myPage = myResponse.read()

    # The role of decode is to convert other encoded strings into unicode string
    unicodePage = myPage.decode('utf-8')
    myItems = re.findall('<span>(.*?)</span>', unicodePage, re.s)
    items = []
    for item in myItems:
        items.append(item[0].repalce("\n", ""), item[1].replace("\n", ""))
    return items

# Download new jokes
def LoadPage(self):
    # If users doesn't enter quit, keep download
    while self.enable:
        # If the pages array less than 2
        if len(self.pages) < 2:
            try:
                 myPage = self.GetPage(str(self.page))
                 self.page += 1
                 self.pages.append(myPage)
            except:
                 print('Connection failed')
        else:
            time.sleep(1)

def ShowPage(self, nowPage, page):
    for items in nowPage:
        print('No.%d Page:'% page, items[0], items[1])
        myInput = input()
        if myInput == 'quit':
            self.enable = False
            break

def Start(self):
    self.enable = True
    page = 0
    print('Loading...')
    # _thread.start_new_thread(self.LoadPage(), ())
    while self.enable:
        if len(self.pages) > 0:
            nowPage = self.pages[0]
            page += 1
            del self.pages[0]
            self.ShowPage(nowPage, page)


print('Hit Enter:')
input(' ')
myModel = Spider_Model()
myModel.Start()

在此处输入图像描述

4

0 回答 0