python看小说-CSDN博客

本文链接：https://blog.csdn.net/ultramand/article/details/127590450

import requests
import re
import parsel
import os  # 文件操作模块
from time import sleep



list_url='https://www.23wx.cc/du/54/54202/'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.81 Safari/537.36 SE 2.X MetaSr 1.0'
}
response = requests.get(list_url,headers = headers)

response.encoding = 'gbk'



href = re.findall('<a href="(.*?)">.*?</a></dd>',response.text)  #存在response.text里
# print(href)
name = re.findall('<meta name="og:novel:book_name" content="(.*?)" />',response.text)[0] #小说名字
print(name)
#提取herf列表里的每个元素
i = 0
max = 100

for index in href:
   
    index_url = 'https://www.23wx.cc/du/54/54202/'+index
    # print(index_url)
    response = requests.get(index_url)
    response.encoding = 'gbk'
    #print(response.text)

    selector = parsel.Selector(response.text) # response.text 字符串数据  转成可解析的对象
    title = selector.css('#wrapper > div.content_read > div > div.bookname > h1::text').get() 
    #print(title)
    content_list = selector.css('#content::text').getall() 
    
    content = ''.join(content_list)
    #print(content)
    # 自动创建路径

    filename = f'{name}\\'
    if not os.path.exists(filename):
        os.mkdir(filename)

    with open(f'{filename}\\{title}.txt',mode="a",encoding='utf-8') as f:  # 保存到文件
        f.writelines(title)
        f.writelines(content)
        i+=1
    print("正在保存：\t",title,i)
    for i in (range(max)):
        print("█", end="", flush=True)
        sleep(0.1)