python生成有声小说模拟真人发音 python生成有声小说模拟真人发

生成有声小说原理文字是1500字内的生成微软文档说说用代码实现小说爬取正本实现每章小说1450字实现自动剪切后添加封面实现自动上传用python代码实现爬取小说，本案列以一本小说为实列代码

点击查看代码

from bs4 import BeautifulSoup import requests, sys""" 类说明:下载《笔趣看》网小说《一念永恒》 Parameters: 无 Returns: 无 Modify: """class downloader(object):def __init__(self): self.server = 'http://www.biqukan.com/' self.target = 'http://www.biqukan.com/1_1094/' self.headers = { "User_Agent": "User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36", } self.names = []# 存放章节名 self.urls = []# 存放章节链接 self.nums = 0# 章节数""" 函数说明:获取下载链接 Parameters: 无 Returns: 无 Modify: """def get_download_url(self): req = requests.get(url=self.target, headers=self.headers) html = req.content.decode("gbk") div_bf = BeautifulSoup(html, features="lxml") div = div_bf.find_all('div', class_='listmain') a_bf = BeautifulSoup(str(div[0]), features="lxml") a = a_bf.find_all('a') self.nums = len(a[15:])# 剔除不必要的章节，并统计章节数 for each in a[15:]: self.names.append(each.string) self.urls.append(self.server + each.get('href'))""" 函数说明:获取章节内容 Parameters: target - 下载连接(string) Returns: texts - 章节内容(string) Modify: """def get_contents(self, target): req = requests.get(url=target, headers=self.headers) html = req.content.decode("gbk") bf = BeautifulSoup(html, features="lxml") texts = bf.find_all('div', class_='showtxt') texts = texts[0].text.replace('\xa0' * 8, '\n\n') return texts""" 函数说明:将爬取的文章内容写入文件 Parameters: name - 章节名称(string) path - 当前路径下,小说保存名称(string) text - 章节内容(string) Returns: 无 Modify """def writer(self, name, path, text): write_flag = True with open(path, 'a', encoding='utf-8') as f: f.write(name + '\n') f.writelines(text) f.write('\n\n')if __name__ == "__main__": dl = downloader() dl.get_download_url() print('《一年永恒》开始下载：') for i in range(dl.nums): dl.writer(dl.names[i], '一念永恒.txt', dl.get_contents(dl.urls[i])) sys.stdout.write("已下载:%.3f%%" % float(i / dl.nums) + '\r') sys.stdout.flush() print('《一年永恒》下载完成')

##本文爬取小说因为是单进程，所以下载速度比较忙 ##仅供学习参考