生成有聲小說原理
文字是1500字內的生成微軟文檔說說
用代碼實現小說爬取正本
實現每章小說1450字
實現自動剪切后添加封面
實現自動上傳
用python代碼實現爬取小說，本案列以一本小說為實列代碼
點擊查看代碼
from bs4 import BeautifulSoup
import requests, sys
"""
類說明:下載《筆趣看》網小說《一念永恆》
Parameters:
無
Returns:
無
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 = [] # 存放章節名
self.urls = [] # 存放章節鏈接
self.nums = 0 # 章節數
"""
函數說明:獲取下載鏈接
Parameters:
無
Returns:
無
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:]) # 剔除不必要的章節，並統計章節數
for each in a[15:]:
self.names.append(each.string)
self.urls.append(self.server + each.get('href'))
"""
函數說明:獲取章節內容
Parameters:
target - 下載連接(string)
Returns:
texts - 章節內容(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
"""
函數說明:將爬取的文章內容寫入文件
Parameters:
name - 章節名稱(string)
path - 當前路徑下,小說保存名稱(string)
text - 章節內容(string)
Returns:
無
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('《一年永恆》開始下載：')
for i in range(dl.nums):
dl.writer(dl.names[i], '一念永恆.txt', dl.get_contents(dl.urls[i]))
sys.stdout.write(" 已下載:%.3f%%" % float(i / dl.nums) + '\r')
sys.stdout.flush()
print('《一年永恆》下載完成')
##本文爬取小說因為是單進程，所以下載速度比較忙 ##僅供學習參考
