第三方库需求: Faker
安装方法:终端输入pip3 install faker
不安装将相关代码删除自行添加假UA也可使用。
使用方法:下载源码直接运行即可。
功能介绍:一键搜索+下载,下载的txt文件会自动查重,已经存在的不会重复下载浪费时间和存储空间。
文件下载位置:程序执行同目录下会自动创建小说 文件夹,每次下载小说都会在里面添加一个以小说书名命名的文件夹,内容分章存储。
源代码
# -*- coding: utf-8 -*-
"""
Project Name: novel
Author: ARtcgb
Email:artcgb@ebay.onmicrosoft.com
Date: 2021/4/24
"""
import os
import requests
from faker import Faker
from bs4 import BeautifulSoup
f = Faker()
headers = {'user-agent': f.user_agent()}
while True:
search_url = "https://www.mibaoge.com/search.php?q=" + input("输入要查找的书名:")
requests_url = requests.get(search_url, headers=headers)
soup_url = BeautifulSoup(requests_url.text, "lxml")
search_list = soup_url.find_all("a", cpos="title")
if search_list:
count = 1
for soup in search_list:
print(count, soup.text.replace("\n", ""))
count += 1
break
else:
print("未搜索到相关结果")
choose = int(input("请输入所选查找结果前面的数字:")) - 1
title = soup_url.find_all("a", cpos="title")[choose].text.replace("\n", "")
title_url = soup_url.find_all("a", cpos="title")[choose]["href"]
url = "https://www.mibaoge.com" + title_url
requests_url = requests.get(url, headers=headers)
soup_url = BeautifulSoup(requests_url.text, "lxml")
menu_list = soup_url.find("div", id="list").find_all("a")
url_list = []
chapter_list = []
for menu in menu_list:
url_list.append(menu['href'])
chapter_list.append(menu.text)
print("共找到", len(url_list), "个章节")
a = os.path.exists("./小说")
b = os.path.exists("./小说/" + title)
if a and b:
print("文件夹已存在,PASS")
elif a:
os.mkdir("./小说/" + title)
print("文件夹建立成功")
else:
os.mkdir("./小说")
os.mkdir("./小说/" + title)
print("文件夹建立成功")
url_count = 0
for url in url_list:
a = os.path.exists("./小说/" + title + "/" + chapter_list[url_count] + ".txt")
url_count += 1
if a:
try:
print(chapter_list[url_count], "已存在,PASS")
except IndexError:
print("全部章节验证完毕")
continue
requests_url = requests.get("https://www.mibaoge.com/" + url, headers=headers)
soup = BeautifulSoup(requests_url.text, "lxml")
chapter = soup.find("h1").text
content = str(soup.find("div", id="content")).replace("<!--go-->", "").replace("<!--over-->", "") \
.replace("<br/>", "\n").replace("<div id=\"content\">", "").replace("</div>", "")
with open("./小说/" + title + "/" + chapter + ".txt", "w") as f:
f.write(content)
print(chapter, "写入成功")
print(title, "写入成功")
|