python3练手：爬糗事百科

python3 练手：爬糗事百科

参考原文地址：
https://blog.csdn.net/pleasecallmewhy/article/details/8932310
https://cuiqingcai.com/990.html

糗事百科地址：https://www.qiushibaike.com/hot/page/1/

每页显示25则糗事，糗事内容在〈div class = ‘content’〉…〈/div〉内
目标：爬取糗事内容并在每按一次回车时显示一则糗事，当按下"q"键时结束
分析：设置标志开关flag，根据输入判断是否显示。
flag为真，判断存储列表stories是否为空：
为空：加载页面，解析页面，添加内容至stroies
非空：显示一则内容
flag为假：退出
注意：只解析一个结果item与解析多个结果不同
多个结果可用item[0]，item[1]…
单个结果引用item[0]无内容
代码：

import urllib
import urllib.request
import re
class QSBK:
    def __init__(self):
        self.headers = {'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'}
        self.pageindex = 1
        self.flag = True
        self.stories = []

    def get_html(self,url):
        try:
            myreq = urllib.request.Request(url,headers = self.headers)
            myrespoonse = urllib.request.urlopen(myreq)
            html = myrespoonse.read().decode('utf-8')
            return html
        except urllib.request.URLError as e:
            if(hasattr(e,'reason')):
                print('未连接，原因：' + e.reason + '\n')

    def parse_html(self,html):
        patterns = re.compile('.*?(.*?)',re.S)
        items = re.findall(patterns,html)
        for item in items:
            replacebr = re.compile('
')
            modifytext = re.sub(replacebr,'\n',item)
            self.stories.append(modifytext.strip())

    def load_page(self):
        download_url = 'https://www.qiushibaike.com/hot/page/' + str(self.pageindex)
        html = self.get_html(download_url)
        self.parse_html(html)

    def getonestory(self):
        story = self.stories[0]
        print(story)
        del self.stories[0]

    def start(self):
        self.load_page()
        print(len(self.stories))
        self.pageindex += 1
        print('糗事百科：\n')
        print('按回车键加载内容，按‘q’键结束：\n')
        i = 1
        while(self.flag):
            exityesorno = input()
            if (exityesorno == 'q'):
                self.flag = False
            else:
                if(len(self.stories) > 0):
                    print("第" + str(i) + "则糗事：")
                    self.getonestory()
                    i += 1
                else:
                    self.load_page()
                    self.pageindex += 1
                    print("第" + str(i) + "则糗事：")
                    self.getonestory()
                    i += 1
                    
spider = QSBK()
spider.start()