爬虫的有声小说制作（用python）

Question

做一个爬取小说的网站
网站要先注册，登录
网站要有搜索引擎，输入小说名就可以下载整本小说，依章节分序下载到txt
经过前面几步，可以将文本小说转化成语音小说，并保存到本地的音频文件中（如：点击一个章节，这章就可转成语音）
转成语音后，在网站上读，可以暂停
美化网站，以上都要在网站上进行，使用python，提供源代码，要求可以运行成功
（没有诚意就不要回答了）

Answer 1

import requests
import re
from urllib.parse import urljoin
import urllib3
from lxml import etree
urllib3.disable_warnings()#解决warning

class Tingshu_bao_spider:
    def do_get_request(self,url):
        """
        发送网络请求，获取网页源代码
        :param url:
        :return:
        """
        headers={"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.81 Safari/537.36",
                 "Referer":url}
        try:
            r=requests.get(url,headers=headers,timeout=6)
            if r.status_code==200:
                r.encoding=r.apparent_encoding
                html=r.text
                return html
            else:
                return  False
        except:
            return False

    def get_novel_detail(self,sound_link):
        """
        获取小说详情
        :param sound_link:
        :return:
        """
        novel_detail_item={}
        html=self.do_get_request(sound_link)
        if html:
            res=etree.HTML(html)
            name=res.xpath('//div[@class="book-cell"]/h1[@class="book-title"]/text()')
            if name:
                novel_detail_item['novel_name']=name[0].split("有声小说简介：")[0]
            else:
                novel_detail_item['novel_name']="未知"
            cover=res.xpath('//div[@class="book"]/img[@class="book-cover"]/@src')
            if cover:
                novel_detail_item['novel_cover']=urljoin(sound_link,cover[0])
            else:
                novel_detail_item['novel_cover']="未知"
            datas=res.xpath('//div[@class="book-rand-a"]//text()')
            if datas:
                novel_detail_item['novel_type'] = datas[1]
                novel_detail_item['novel_status'] = datas[3]
                novel_detail_item['novel_update_time'] = datas[-1]

            else:
                novel_detail_item['novel_type']="未知"
                novel_detail_item['novel_status'] = "未知"
                novel_detail_item['novel_update_time'] = "未知"
            #作者
            data2 = res.xpath('//div[@class="book-des"]/p/a/text()')
            if data2:
                novel_detail_item['novel_author'] = data2[0]
                novel_detail_item['novel_anchor'] = data2[-1]
            else:
                novel_detail_item['novel_author']="未知"
                novel_detail_item['novel_anchor']="未知"

            introduce = res.xpath('//div[@class="book-des"]/text()')
            if introduce:
                novel_detail_item['novel_introduce'] = introduce[0]
            else:
                novel_detail_item['novel_introduce']="未知"
            selector=res.xpath('//div[@id="playlist"]/ul/li')
            play_list=[]
            for data in selector:
                play_item={}
                novel_play_name=data.xpath("./a/@title")
                if novel_play_name:
                    play_item["play_name"]=novel_play_name[0]
                else:
                    play_item["play_name"]="NULL"
                novel_play_link = data.xpath("./a/@href")
                if novel_play_name:
                    play_item["play_link"] = urljoin(sound_link,novel_play_link[0])
                else:
                    play_item["play_link"]="NULL"
                play_list.append(play_item)
            novel_detail_item['play_list']=play_list
            return novel_detail_item
        else:
            return False

    def get_audio_play_link(self,detail_intro_link):
        """
        获取小说播放链接地址
        :param detail_intro_link:
        :return:
        """
        html=self.do_get_request(detail_intro_link)
        if html:
            base_url="https://t3344t.tingchina.com/"
            aim_asciis=re.findall("FonHen_JieMa\('(.*?)'",html)
            if aim_asciis:
                sp = aim_asciis[0].split("*")
                res = ""
                for s in sp:
                    if s != "":
                        if "-" in s:
                            res += chr((int(~int(s.replace("-", '')) & 0xffff) + 1))
                        else:
                            res += chr(int(s))
                aim_suffix = "/" + res.split('&')[0].split('/', 1)[-1]
                play_url=urljoin(base_url,aim_suffix)
                return play_url
            else:
                return False
        else:
            return False

if __name__ == '__main__':
    t=Tingshu_bao_spider()
    aim_url='http://m.tingshubao.com/book/2267.html'
    print(t.get_novel_detail(aim_url))
    print(t.get_audio_play_link('http://m.tingshubao.com/video/?2267-0-0.html'))

参考：

Python3网络爬虫--爬取有声小说（附源码）_有声小说源码_懷淰メ的博客-CSDN博客 在第二个class为book的div标签中能得到小说简介、作者、播音。本次分析了一个有声小说网站，重点在于分析其小说详情页、音频播放地址，加密方式判断。思路、代码方面有什么不足欢迎各位大佬指正、批评！_有声小说源码 https://blog.csdn.net/a1397852386/article/details/122085836