爬虫案例—根据四大名著书名抓取并存储为文本文件

爬虫案例—根据四大名著书名抓取并存储为文本文件

诗词名句网：https://www.shicimingju.com

目标：输入四大名著的书名，抓取名著的全部内容，包括书名，作者，年代及各章节内容

诗词名句网主页如下图：

今天的案例是抓取古籍板块下的四大名著，如下图：

案例源码如下：

import time
import requests
from bs4 import BeautifulSoup
import random

headers = {
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36', }


# 获取响应页面,并返回实例化soup
def get_soup(html_url):
    res = requests.get(html_url, headers=headers)
    res.encoding = res.apparent_encoding
    html = res.content.decode()
    soup = BeautifulSoup(html, 'lxml')
    return soup


# 返回名著的书名及对应的网址字典
def get_book_url(page_url):
    book_url_dic = {}
    soup = get_soup(page_url)

    div_tag = soup.find(class_="card booknark_card")

    title_lst = div_tag.ul.find_all(name='li')

    for title in title_lst:
        book_url_dic[title.a.text.strip('《》')] = 'https://www.shicimingju.com' + title.a['href']
    return book_url_dic


# 输出每一章节内容
def get_chapter_content(chapter_url):
    chapter_content_lst = []
    chapter_soup = get_soup(chapter_url)
    div_chapter = chapter_soup.find(class_='card bookmark-list')
    chapter_content = div_chapter.find_all('p')
    for p_content in chapter_content:
        chapter_content_lst.append(p_content.text)

    time.sleep(random.randint(1, 3))
    return chapter_content_lst


  # 主程序
if __name__ == '__main__':
  
    # 古籍板块链接
    gj_url = 'https://www.shicimingju.com/book'
    url_dic = get_book_url(gj_url)
    mz_name = input('请输入四大名著名称： ')
    mz_url = url_dic[mz_name]

    soup = get_soup(mz_url)
    abbr_tag = soup.find(class_="card bookmark-list")
    book_name = abbr_tag.h1.text
    f = open(f'{book_name}.txt', 'a', encoding='utf-8')
    f.write('书名：'+book_name+'\n')
    print('名著名称：', book_name, end='\n')
    p_lst = abbr_tag.find_all('p')
    for p in p_lst:
        f.write(p.text+'\n')

    mulu_lst = soup.find_all(class_="book-mulu")
    book_ul = mulu_lst[0].ul
    book_li = book_ul.find_all(name='li')
    for bl in book_li:
        print('\t\t', bl.text)
        chapter_url = 'https://www.shicimingju.com' + bl.a['href']
        f.write(bl.text+'\n')
        f.write(''.join(get_chapter_content(chapter_url))+'\n')

    f.close()