从“顶点小说”下载完整小说——python爬虫

 1 # -*- coding:utf-8 -*-
 2 import requests
 3 from lxml import etree
 4 
 5 novel_name = ''  #全局变量，存放小说名称
 6 headers = {
 7         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'}
 8 
 9 def get_url(name):
10     '''
11         通过百度获取小说在顶点小说中的网址
12         name:小说名
13     '''
14     #site: booktxt.net + 小说名 指定为该网站搜索
15     baidu = 'https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=1&tn=baidu&wd=site%3A%20booktxt.net%20'+name
16 
17     #获取该小说在顶点小说中的网址
18     r = requests.get(baidu, headers=headers)
19     html = etree.HTML(r.content)
20     try:
21         #提取网址链接，若不存在则退出程序
22         url = html.xpath('//*[@id="1"]/h3/a/@href')[0]
23         url =requests.get(url, headers=headers).url
24     except:
25         print("该小说不存在！")
26         exit(0)
27     if url[-4:] == 'html': #搜索结果为某一章节，结果无效
28         print("该小说不存在！")
29         exit(0)
30     get_chapter(url) #获取小说章节
31 
32 def get_chapter(url):
33     '''
34     获取搜索到的小说名，并询问是否下载
35 
36     :param url: 小说的链接
37     '''
38     global novel_name
39 
40     r = requests.get(url=url,headers=headers)
41     coding = r.apparent_encoding #获取网页编码格式
42 
43     html = etree.HTML(r.content, parser=etree.HTMLParser(encoding=coding))
44 
45     novel_name = html.xpath('//*[@id="info"]/h1/text()')[0]
46     print('小说名：'+novel_name+'n是否下载？是/否n')
47     flag = input()
48     if flag=='否':
49         print('退出系统')
50         exit(0)
51 
52     list = html.xpath('//*[@id="list"]/dl/dd[position()>8]') #获取章节列表
53     for item in list:
54         chapter_name = item.xpath('./a')[0].text #每一章的名称
55         print(chapter_name)
56         link = item.xpath('./a/@href')[0] #每章的网址链接
57         full_link = url+link #每章的完整地址
58         print(full_link)
59         get_text(chapter_name,full_link)
60 
61 def get_text(name,link):
62     '''
63     获取每章的内容并写入至txt文件中
64     :param name: 小说章节名
65     :param link: 章节链接
66     :return:
67     '''
68 
69     r = requests.get(url=link, headers=headers)
70     coding = r.apparent_encoding
71     r = r.content
72 
73     html = etree.HTML(r, parser=etree.HTMLParser(encoding=coding))
74     #获取一章内容，并以空格为界分割成字符串列表
75     text = html.xpath('string(//*[@id="content"])').split()
76     #print(text)
77     #创建小说名.txt文件
78     with open('{}.txt'.format(novel_name),'a+',encoding='utf-8') as f:
79         f.write('t'*3+name+'n') #章节名
80         for i in range(len(text)):
81             f.write(' '*4+text[i]+'n')
82 
83 if __name__ == '__main__':
86     novel_name = input('请输入小说名称：')
88     get_url(novel_name)