聪哥哥教你学Python之爬取金庸系列的小说

话不多说，代码贴起:

# -*- coding: utf-8 -*-
import urllib.request  
from bs4 import BeautifulSoup

#获取每本书的章节内容
def get_chapter(url):
    # 获取网页的源代码
    html = urllib.request.urlopen(url)  
    content = html.read().decode('utf8')
    html.close()
    # 将网页源代码解析成HTML格式
    soup = BeautifulSoup(content, "lxml")
    title = soup.find('h1').text    #获取章节的标题
    text = soup.find('div', id='htmlContent')    #获取章节的内容
    #处理章节的内容，使得格式更加整洁、清晰
    content = text.get_text('\n','br/').replace('\n', '\n    ')
    content = content.replace('　　', '\n　　')
    return title, '    '+content

def main():
    # 书本列表
    books = ['射雕英雄传','天龙八部','鹿鼎记','神雕侠侣','笑傲江湖','碧血剑','倚天屠龙记',\
             '飞狐外传','书剑恩仇录','连城诀','侠客行','越女剑','鸳鸯刀','白马啸西风',\
             '雪山飞狐']
    order = [1,2,3,4,5,6,7,8,10,11,12,14,15,13,9]  #order of books to scrapy
    #list to store each book's scrapying range
    page_range = [1,43,94,145,185,225,248,289,309,329,341,362,363,364,375,385]

    for i,book in enumerate(books):
        for num in range(page_range[i],page_range[i+1]):
            url = "http://jinyong.zuopinj.com/%s/%s.html"%(order[i],num)
            # 错误处理机制
            try:
                title, chapter = get_chapter(url)
                with open('D://book/%s.txt'%book, 'a', encoding='gb18030') as f:
                    print(book+':'+title+'-->写入成功！')
                    f.write(title+'\n\n\n')
                    f.write(chapter+'\n\n\n')
            except Exception as e:
                print(e) 
    print('全部写入完毕!')

main()

最终的结果是这样的:

 

将对应的书写入对应的txt，打开阅读，确实有点体验不好，但是聪哥哥金点子，给你提建议:

通过如下网站，可将txt转为pdf

http://www.pdfdo.com/txt-to-pdf.aspx

所以最后的结果是:

 

转为pdf后，阅读体验更好了。希望这篇文章能给广大的小伙伴们帮助。