基本配置:
- Python版本:3.6
- 相关模块:
from bs4 import BeautifulSoup
import requests, sys
'''
遇到不懂的问题?Python学习交流群:1136201545满足你的需求,资料都已经上传群文件,可以自行下载!
'''
下载《17K》网小说
class downloader(object):
def __init__(self):
"""
:rtype: object
"""
self.server = 'http://www.17k.com' # 网站地址
self.target = 'http://www.17k.com/list/2731559.html' # 目录URL地址
self.names = [] #存放章节名
self.urls = [] #存放章节链接
self.nums = 0 #章节数
获取下载链接
def get_downloader_url(self):
req = requests.get(self.target) # 获取URL地址内容
req.encoding = 'utf-8' # 转码
html = req.text # 保存get到的内容
div_bf = BeautifulSoup(html, 'html.parser') # 使用BeautifulSoup进行解析
div = div_bf.find_all('div', class_='Main List') # 查询符合条件的内容
a_bf = BeautifulSoup(str(div[0]),'html.parser')#重新解析
a = a_bf.find_all('a')#查找元素为'a'的内容
self.nums = len(a[11:])
for each in a[11:]:
self.names.append(each.string)#把章节名称添加到变量
self.urls.append(self.server + each.get('href'))#把章节URL地址添加到变量
获取章节内容
def get_contents(self,target):
req = requests.get(target)#获取URL地址内容
req.encoding = 'utf-8'#解码
html = req.text
bf = BeautifulSoup(html, 'html.parser')#解析
texts = bf.find_all('div', class_='readAreaBox content')#使用查找章节正文
texts = texts[0].text.replace('\xa0' * 8, '\n\n')#使用replace方法,剔除空格,替换为回车进行分段
return texts
将爬取的文章内容写入文件
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_downloader_url()
print('《正道潜龙》开始下载:')
for i in range(dl.nums):
dl.writer(str(dl.names[i]), '正道潜龙.txt', dl.get_contents(dl.urls[i]))
sys.stdout.write(" 已下载:%.3f%%" % float(i/dl.nums) + '\r')
sys.stdout.flush()
print('《正道潜龙》下载完成')