1.代码:

# -*- coding:UTF- -*-
from bs4 import BeautifulSoup
import requests, sys """
类说明:下载文字
Parameters:

Returns:

Modify:
--
""" class downloader(object): def __init__(self):
self.server = 'http://www.biqukan.com/'
self.target = 'http://www.biqukan.com/1_1094/'
self.names = [] # 存放章节名
self.urls = [] # 存放章节链接
self.nums = # 章节数 """
函数说明:获取下载链接
Parameters:

Returns:

Modify:
--
""" def get_download_url(self):
req = requests.get(url=self.target)
html = req.text
div_bf = BeautifulSoup(html)
div = div_bf.find_all('div', class_='listmain')
a_bf = BeautifulSoup(str(div[]))
a = a_bf.find_all('a')
self.nums = len(a[:]) # 剔除不必要的章节,并统计章节数
for each in a[:]:
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)
html = req.text
bf = BeautifulSoup(html)
texts = bf.find_all('div', class_='showtxt')
texts = texts[].text.replace('\xa0' * , '\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:

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')
05-11 13:50