【某趣阁】小说下载，纯python脚本，无需selenium等自动化
### 脚本说明某趣阁小说下载，纯python脚本，无需selenium等自动化工具
命令行支持小说搜索，和下载
### 只需要request和bs4依赖
```shell
pip install requests bs4 -i https://pypi.tuna.tsinghua.edu.cn/simple
```
### 完整代码
```python
#!/usr/bin/env python
# -*- coding: utf-8 -*-
# @file : main.py
import time
import urllib.parse
import requests
import copy
import os
from bs4 import BeautifulSoup
HEADERS = {
"authority": "www.biqg.cc",
"accept": "application/json",
"accept-language": "zh,en;q=0.9,zh-CN;q=0.8",
"cache-control": "no-cache",
"pragma": "no-cache",
"sec-fetch-dest": "empty",
"sec-fetch-mode": "cors",
"sec-fetch-site": "same-origin",
"user-agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 16_6 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/16.6 Mobile/15E148 Safari/604.1",
"x-requested-with": "XMLHttpRequest",
}
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
DOWNLOAD_PATH = os.path.join(BASE_DIR, "result")
def get_hm_cookie(url):
session = requests.Session()
session.get(url=url, headers=HEADERS, timeout=10)
return session
def search(key_word):
new_header = copy.deepcopy(HEADERS)
new_header["referer"] = urllib.parse.quote(
f"https://www.biqg.cc/s?q={key_word}", safe="/&=:?"
)
hm_url = urllib.parse.quote(
f"https://www.biqg.cc/user/hm.html?q={key_word}", safe="/&=:?"
)
session = get_hm_cookie(hm_url)
params = {
"q": f"{key_word}",
}
try:
response = session.get(
"https://www.biqg.cc/user/search.html",
params=params,
headers=new_header,
timeout=10,
)
except Exception as e:
print(f"搜索{key_word}时失败，错误信息:{e}")
return [], session
data = response.json()
return data, session
def download_by_tag(tag, href, result_path, session):
title = f"{tag.text}"
url = f"https://www.biqg.cc{href}"
print(f"开始下载第{title} url: {url}")
result_file_name = os.path.join(result_path, f"{title}.txt")
with open(result_file_name, "w+", encoding="utf-8") as f:
content_response = session.get(url, headers=HEADERS)
content_soup = BeautifulSoup(content_response.content, "html.parser")
text = content_soup.find(id="chaptercontent")
for i in text.get_text().split(" "):
f.write(f"{i}\n")
time.sleep(0.2)
def download_txt(download_url, path_name, session):
"""
下载小说
:param download_url: 下载链接
:param path_name: 存储文件名
:return:
"""
result_path = os.path.join(DOWNLOAD_PATH, path_name)
if not os.path.exists(result_path):
os.makedirs(result_path, exist_ok=True)
try:
response = session.get(download_url, headers=HEADERS, timeout=10)
soup = BeautifulSoup(response.content, "html.parser")
down_load_url = soup.select("div dl dd a")
for tag in down_load_url:
href = tag["href"]
if href == "javascript:dd_show()":
hide_dd = soup.select("span dd a")
for hide_tag in hide_dd:
href = hide_tag["href"]
download_by_tag(hide_tag, href, result_path, session)
else:
download_by_tag(tag, href, result_path, session)
except Exception as e:
import traceback
print(traceback.format_exc())
print(f"下载{download_url}失败，错误信息:{e}")
def run():
while True:
keyword = input("请输入搜索的小说名or输入q退出:")
if keyword.replace(" ", "").lower() == "q":
break
if not keyword:
continue
data_list, session = search(keyword)
if not data_list or data_list == 1:
print("请重试.......")
continue
for i in range(len(data_list)):
item = data_list
articlename = item.get("articlename")
author = item.get("author")
print(f"编号：{i} 书名：{articlename}----->{author}")
while True:
try:
num_book = int(input("请输入需要下载的编号:"))
except Exception:
print("请输入正确的编号")
continue
try:
item = data_list
except Exception:
print("编号超出了预期，请请重新输入")
continue
break
url_list = f"https://www.biqg.cc{item.get('url_list')}"
print(f"开始下载{url_list}")
path_name = f"{item.get('articlename', '')}___{item.get('author', '')}"
download_txt(url_list, path_name, session)
if __name__ == "__main__":
run()
```
### 运行
```shell
python main.py
# 输入小说名
# 选择要下载的编号
# 等待下载就行了
```
### 常见问题
1、会存在偶尔失败问题，犹豫网络问题导致，失败后重新运行就行
### 运行截图
哇，学习！ 这个可以哦 谢谢 感谢分享！ 很厉害啊 可以看小说了 pip 现在不好用 卡的要死 {:1_893:} 感谢分享！真的刚需了这个 感谢分享，mark 书虫狂喜 这个老牛了，谢谢分享！