老司机教你用Python下载热门小说

tyrantlucifer

发布于 2022-03-23 14:47:09

5170

发布于 2022-03-23 14:47:09

文章被收录于专栏：Tyrant Lucifer

说起来Python，你能想到的是什么呢？大数据？Django？小程序？人工智能？爬虫？等等等等 Python作为一门入门简单适合于大众的编程语言，小至小学生，大至大学生，都在学习Python的编程知识，今天博主就给大家带来一篇关于Python的好玩例子---使用Python爬虫下载小说

需求分析

所谓爬虫，就是取模拟Http请求，然后将返回回来的页面数据进行处理分析，拿到我们想要的内容；今天带大家爬的是一家比较良心的小说网站--- https://www.dingdiann.com/，这个网站通过博主实测，不会封ip，不会限制你访问，不会有验证码，适合用来割韭菜，废话不多说，直接上源码。

技术要点:

BeautifulSoup4:解析标签
Requests:模拟http请求
Python3

脚本使用步骤:

安装 BeautifulSoup4

pip3 install beautifulsoup4

安装 requests

pip3 install requests

保存以下代码为 book.py

import re                                                                             import sys
 
import requests
 
import time
 
from bs4 import BeautifulSoup
 
from requests.packages.urllib3.exceptions import InsecureRequestWarning 
 
requests.packages.urllib3.disable_warnings(InsecureRequestWarning)
 


 
class BookSpider():
 
 '''爬取顶点小说网小说'''
 
 def __init__(self):
 


 
 self.headers = { 
 
 'Host':'www.dingdiann.com',
 
 'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',
 
 }
 
 self.chapter_url_list = list()
 
 self.chapter_name_list = list()
 
 self.book_info = dict()
 


 
 def get_book_url(self, book_name, author_name):
 
 '''获取要爬取书籍的详情页'''
 
        url = 'https://www.dingdiann.com/searchbook.php'
 
        data = {
 
 'keyword':book_name
 
 }
 
        result = requests.get(url, headers=self.headers, params=data, verify=False).text
 
        soup = BeautifulSoup(result, 'lxml')
 
        book_name_list = soup.find_all(name='span', attrs={'class':'s2'})
 
        book_author_list = soup.find_all(name='span', attrs={'class':'s4'})
 
        book_name_list.pop(0)
 
        book_author_list.pop(0)
 
 for candidate_name in book_name_list:
 
            book_info_list = list()
 
            name = str(candidate_name.a.string)
 
            book_url = str(candidate_name.a.get('href'))
 
            book_info_tuple = (name, book_url)
 
            book_info_list.append(book_info_tuple)
 
            author = str(book_author_list[0].string)
 
 if author in self.book_info.keys():
 
 self.book_info[author].append(book_info_tuple)
 
                book_author_list.pop(0)
 
 else:
 
 self.book_info[author] = book_info_list
 
                book_author_list.pop(0)
 
 if self.book_info[author_name]:
 
 for info in self.book_info[author_name]:
 
 if info[0] == book_name:
 
                    url = info[1]
 
 print('书籍已经找到,您要找的书籍为 ' + book_name + ':' + author_name) 
 
 print('3S 后将开始下载~~~')
 
                    time.sleep(3)
 
 return url
 
 else:
 
 print('抱歉,书籍未找到,请确认书籍作者及名称是否正确~~~')
 


 
 def get_book_info(self, url):
 
 '''获取书籍的章节列表和地址'''
 
        all_url = 'https://www.dingdiann.com' + url
 
        result = requests.get(all_url, headers=self.headers, verify=False).text
 
        soup = BeautifulSoup(result, 'lxml')
 
        div = soup.find_all(id='list')[0]
 
        chapter_list = div.dl.contents
 


 
 for text in chapter_list :
 
            text = str(text)
 
            content = re.findall('<a href="' + url + '(.*?)" style="">(.*?)</a>.*?', text)
 
 if content:
 
                chapter_url = all_url + content[0][0]
 
                chapter_name = content[0][1]
 
 self.chapter_url_list.append(chapter_url)
 
 self.chapter_name_list.append(chapter_name)
 


 
 for i in range(12):
 
 self.chapter_url_list.pop(0)
 
 self.chapter_name_list.pop(0)
 


 
 def get_chapter_content(self, name, url):
 
 '''获取小说每章内容''' 
 
 try:
 
            result = requests.get(url, headers=self.headers, verify=False).text
 
 except:
 
 print(name + "下载失败~~~")
 
 return False
 
 else:
 
            soup = BeautifulSoup(result, 'lxml')
 
            div = soup.find_all(id='content')[0]
 
            div = str(div)
 
            result = re.findall('<div id="content">(.*?)<script>', div, re.S)[0].strip()
 
            result = re.sub('<br/>', '\n', result)
 
 return result
 


 
 def save_book(self, book_name):
 
 '''保存小说'''
 
 for chapter_name in self.chapter_name_list:
 
 while True:
 
                chapter_content = self.get_chapter_content(chapter_name, self.chapter_url_list[0])
 
 if chapter_content:
 
 with open(book_name + ".txt", 'a') as f:
 
                        f.write(chapter_name)
 
                        f.write("\n")
 
                        f.write(chapter_content)
 
                        f.write("\n")
 
 self.chapter_url_list.pop(0)
 
 print(chapter_name + "已经下载完成")
 
 break
 


 
 def run(self, book_name, url):
 
 self.get_book_info(url)
 
 self.save_book(book_name)
 


 
def main(book_name, author_name):
 
    book = BookSpider()
 
    url = book.get_book_url(book_name, author_name)
 
    book.run(book_name, url)
 


 
if __name__ == "__main__":
 
    main(sys.argv[1], sys.argv[2])
    
    使用说明:脚本需要输入两个参数,参数1为 小说名称,参数2为 作者名称,之后便会将采集到的内容保存在本地,例如:
    
    python3 book.py 天珠变 唐家三少