Python爬取小说（requests和BeautifulSoup）

最新推荐文章于 2024-02-23 11:58:17 发布

zxxxlh123

最新推荐文章于 2024-02-23 11:58:17 发布

阅读量479

点赞数

分类专栏：自动化办公文章标签： python beautifulsoup 开发语言

本文链接：https://blog.csdn.net/zxxxlh123/article/details/133682981

版权

自动化办公专栏收录该内容

6 篇文章 0 订阅

订阅专栏

1.用requests和BeautifulSoup爬取起点中文网小说(https://www.qidian.com/free/all/)

在这里插入图片描述

2.选择一篇小说(https://www.qidian.com/book/1037297523/）

在这里插入图片描述

3.查看小说的卷章和每章对应的章节

在这里插入图片描述

4.Chrome浏览器，使用F12，打开开发者模式，查看章节对应代码细节

在这里插入图片描述

5.查看卷章结构，并创建文件夹

#卷章结构
volums_names = [a.text.strip() for a in soup.find_all('h3', class_='volume-name')]

在这里插入图片描述

#创建文件夹存卷章
def create_folders(base_path, folder_names):
    for folder_name in folder_names:
        try:
            # 使用os.makedirs()创建文件夹，如果它不存在
            older_path = os.path.join(base_path, folder_name)
            os.makedirs(folder_name)
            print("文件夹 {}'创建成功!".format(folder_name))
        except OSError as e:
            print("创建文件夹 {}失败!!!".format(folder_name))

在这里插入图片描述

6.章节结构

chapter_names = [a.text.strip() for a in soup.find_all('a', class_='chapter-name')]

在这里插入图片描述

7.章节内容所在页面URL，缺少https:

data_cids = [a['data-cid'] for a in soup.find_all('a', class_='chapter-name')]

在这里插入图片描述

8.提取章节内容

def getchacontents(chapter_id,headers):
    response = requests.get('https:' + chapter_id, headers = headers)
    pattern = r'<p>(.*?)</p>'
    matches = re.findall(pattern, response.text, re.DOTALL)
    result = '\n'.join(matches)# 使用换行符拼接文本
    return result

在这里插入图片描述

9.获取章节内容写入txt文件，并将文件存入对应的卷章文件夹

#将章节内容写入文件，存入对应的文件夹
 def save2file(filepath, filename , content):
    filename = filename.replace(“/”,“-”)#文件名称不可出现-
    try:
        if not os.path.exists(filepath):
            os.makedirs(filepath)
         #文件存储地址
        file_path = os.path.join(filepath, filename + '.txt')
        #爬取内容写入文件
        with open(file_path,'a',encoding ='utf-8') as f:
                f.write(content +'\n')
                f.close()
        print('{}写入成功'.format(filename))
    except Exception as e:
        print('{}写入失败!!!'.format(filename))

在这里插入图片描述

10.整体代码

import requests
import json
import os
import re
from bs4 import BeautifulSoup
import random
#提取章节内容
def getchacontents(chapter_id,headers):
    response = requests.get('https:' + chapter_id, headers = headers)
    pattern = r'<p>(.*?)</p>'
    matches = re.findall(pattern, response.text, re.DOTALL)
    result = '\n'.join(matches)# 使用换行符拼接文本
    return result
#创建文件夹存卷章
def create_folders(base_path, folder_names):
    for folder_name in folder_names:
        try:
            # 使用os.makedirs()创建文件夹，如果它不存在
            older_path = os.path.join(base_path, folder_name)
            os.makedirs(folder_name)
            print("文件夹 {}'创建成功!".format(folder_name))
        except OSError as e:
            print("创建文件夹 {}失败!!!".format(folder_name))
 #将章节内容写入文件，存入对应的文件夹
 def save2file(filepath, filename , content):
    filename = filename.replace("/","-")
    try:
        if not os.path.exists(filepath):
            os.makedirs(filepath)
        #user_home = os.path.expanduser("~")
        file_path = os.path.join(filepath, filename + '.txt')
        #file_path = os.path.join(filepath,filename +'.txt')
        with open(file_path,'a',encoding ='utf-8') as f:
                f.write(content +'\n')
                f.close()
        print('{}写入成功'.format(filename))
    except Exception as e:
        print('{}写入失败!!!'.format(filename))
#防止被禁，随机返回list_中某个User_Agent设置值
def get_User_Agent():
    list_ = ['Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/113.0.0.0 Safari/537.36',\
'Mozilla/5.0 (Windows NT 10.0;Win64;x64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36',\
'Mozilla/5.0 (Windows NT 6.3;Win64;x64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',\
'Mozilla/5.0 (Windows NT 6.2;Win64;x64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',\
 'Mozilla/5.0 (Windows NT 6.1;Win64;x64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',\
'Mozilla/5.0 (Windows NT 6.3;WOW64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/401.0.2225.0 Safari/537.36',\
'Mozilla/5.0 (Windows NT 6.2;WOW64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/401.0.2225.0 Safari/537.36',\
'Mozilla/5.0 (Windows NT 6.1;WOW64) \
AppleWebKit/537.36 (KHTML, like Gecko) Chrome/401.0.2225.0 Safari/537.36']
    return list_[random.randint(0,len(list_)-1]
def main():
    headers = {'User-Agent':get_User_Agent()}
    response = requests.get('https://www.qidian.com/book/1037297523/',headers = headers)
    # 使用BeautifulSoup解析HTML
    soup = BeautifulSoup(response.text, 'html.parser')
    # 查找所有章节名称和章节对应网页
    volums_names = [a.text.strip() for a in soup.find_all('h3', class_='volume-name')]
    chapter_names = [a.text.strip() for a in soup.find_all('a', class_='chapter-name')]
    data_cids = [a['data-cid'] for a in soup.find_all('a', class_='chapter-name')] 
     # 指定要创建文件夹的基本路径
    base_path = '/Users/xinxin/Desktop'
    create_folders(base_path ,volums_names)

    i = 0; j = 0;m = 0
    for chapter_name in chapter_names:
        result = getchacontents(data_cids[chapter_names.index(chapter_name)], headers)
        save2file(base_path + '/' +volums_names[j] , chapter_name, result)
        i += 1;m += 1
        print(' -----写入{}已完成{}/{}----'.format(volums_names[j],m,volums_names[j][6:8]))
        if i == volums_names[0][6:8]:
            j += 1;m = 0
        elif i == volums_names[0][6:8] + volums_names[0][6:8]:
            j += 1;m =1
        
    print("小说爬取完毕")

if __name__=='__main__':
    main()