refactor(book): 重构图书服务以提高稳定性和可维护性
- 添加 Path 模块导入并定义允许的内容类型常量 - 改进设置查询逻辑并添加异常处理 - 将请求头配置改为使用 session 对象管理 - 为文件名合法性检查方法添加类型注解和文档字符串 - 更新内容类型检查使用类常量替代硬编码值 - 使用 session 对象替代直接 requests 调用 - 添加响应状态码检查确保请求成功 - 简化重定向处理逻辑并优化文件下载流程 - 移除重复的私有方法实现
This commit is contained in:
@@ -1,5 +1,6 @@
|
||||
import os
|
||||
import requests
|
||||
from pathlib import Path
|
||||
from bs4 import BeautifulSoup
|
||||
from app.extensions import db
|
||||
from tenacity import retry, stop_after_attempt, RetryError
|
||||
@@ -8,27 +9,49 @@ from app.models import Setting
|
||||
|
||||
|
||||
class BookService:
|
||||
ALLOWED_CONTENT_TYPES = ['"application/octet-stream"', "application/octet-stream", "text/plain",
|
||||
"application/zip"]
|
||||
|
||||
def __init__(self):
|
||||
self.setting = Setting.query.filter_by(name="book_download").first().to_dict()
|
||||
self.setting["targetDate"] = timestamp_to_datetime(
|
||||
datetime_to_timestamp(self.setting["targetDate"]) - 24 * 60 * 60)
|
||||
setting_record = Setting.query.filter_by(name="book_download").first()
|
||||
if not setting_record:
|
||||
raise RuntimeError("Setting 'book_download' not found in database")
|
||||
self.setting = setting_record.to_dict()
|
||||
|
||||
# 目标日期减一天
|
||||
target_ts = datetime_to_timestamp(self.setting["targetDate"]) - 24 * 60 * 60
|
||||
self.setting["targetDate"] = timestamp_to_datetime(target_ts)
|
||||
|
||||
app_dir = os.path.dirname(os.path.dirname(__file__))
|
||||
self.download_path = os.path.join(os.path.dirname(app_dir), "download") # 下载目录
|
||||
self.today_timestamp = get_today_timestamp()
|
||||
self.one_date_loading = False
|
||||
self.headers = {
|
||||
self.session = requests.session()
|
||||
self.session.headers.update({
|
||||
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36",
|
||||
"cookie": "cPNj_2132_saltkey=CeJLs8Ed; "
|
||||
"cPNj_2132_auth=44bdzFfx4TYjBMhuKf4AZdi2JM%2BXZ0Okxd0JEl1Hmwbz%2Fr3WiX0sLmATmolWkLlRgorFz%2BULizz5o6G%2FJ3YGWYPF0xw; "
|
||||
}
|
||||
})
|
||||
self.session.timeout = 30
|
||||
|
||||
def legitimate_naming(self, name): # 合法命名
|
||||
name = name.replace(":", "：")
|
||||
name = name.replace("<", "《")
|
||||
name = name.replace(">", "》")
|
||||
name = name.replace("/", " ")
|
||||
name = name.replace("\\", " ")
|
||||
name = name.replace("?", "？")
|
||||
# ------------------------------------------------------------
|
||||
# 数据库辅助方法
|
||||
# ------------------------------------------------------------
|
||||
def _update_setting(self, **kwargs):
|
||||
Setting.query.filter_by(name="book_download").update(kwargs)
|
||||
db.session.commit()
|
||||
for key, value in kwargs.items():
|
||||
self.setting[key] = value
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# 文件与目录处理
|
||||
# ------------------------------------------------------------
|
||||
@staticmethod
|
||||
def legitimate_naming(name: str) -> str:
|
||||
"""将文件名中的非法字符替换为合法字符"""
|
||||
replacements = {":": "：", "<": "《", ">": "》", "/": " ", "\\": " ", "?": "？"}
|
||||
for old, new in replacements.items():
|
||||
name = name.replace(old, new)
|
||||
return name
|
||||
|
||||
def create_folder(self, target_dir, name): # 创建文件夹
|
||||
@@ -40,12 +63,12 @@ class BookService:
|
||||
print(f"文件夹：{name} 已存在")
|
||||
|
||||
def isDownloadTarget(self, soup): # 是否是可以下载的文件
|
||||
return soup.headers.get('Content-Type') in ['"application/octet-stream"', "application/octet-stream",
|
||||
"text/plain", "application/zip"]
|
||||
return soup.headers.get('Content-Type') in self.ALLOWED_CONTENT_TYPES
|
||||
|
||||
def post_page(self, name, url): # 帖子页面
|
||||
print(f"详情页面 {self.setting["baseUrl"]}{url}")
|
||||
response = requests.get(f"{self.setting["baseUrl"]}{url}", headers=self.headers)
|
||||
response = self.session.get(f"{self.setting["baseUrl"]}{url}")
|
||||
response.raise_for_status()
|
||||
print(f"详情页面状态码：{str(response.status_code)}")
|
||||
soup = BeautifulSoup(response.text, 'lxml')
|
||||
resource_boxs = soup.select('ignore_js_op')
|
||||
@@ -67,11 +90,8 @@ class BookService:
|
||||
|
||||
@retry(stop=stop_after_attempt(3))
|
||||
def download_file(self, file_url, dir_name, file_name): # 下载文件
|
||||
file_res = requests.get(file_url, headers=self.headers, stream=True, allow_redirects=False)
|
||||
if file_res.status_code in (301, 302, 307, 308): # 非200状态码，重新请求
|
||||
file_url = file_res.headers["location"]
|
||||
print(f'跳转页面了：{file_url}')
|
||||
file_res = requests.get(file_url, headers={"referer": file_url}, stream=True)
|
||||
file_res = self.session.get(file_url, stream=True)
|
||||
file_res.raise_for_status()
|
||||
print(f"下载状态码：{file_res.status_code} {file_url}")
|
||||
print(dir_name + "/" + file_name)
|
||||
if self.isDownloadTarget(file_res):
|
||||
@@ -93,7 +113,8 @@ class BookService:
|
||||
return None
|
||||
# yield f"data: 当前页面 {page}\n\n"
|
||||
url = f"{self.setting["baseUrl"]}forum.php?mod={self.setting["mod"]}&fid={self.setting["fid"]}&page={page}" # 版块页面地址
|
||||
response = requests.get(url, headers=self.headers) # 请求
|
||||
response = self.session.get(url) # 请求
|
||||
response.raise_for_status()
|
||||
soup = BeautifulSoup(response.text, 'lxml') # 解析
|
||||
total_page_element = soup.select_one("a.bm_h") # 获取总页数元素
|
||||
if total_page_element is not None: # 总页数元素存在 则更新总页数
|
||||
@@ -162,9 +183,3 @@ class BookService:
|
||||
target_page = self.setting["totalPage"] - self.setting["targetCountdownPage"] # 目标页
|
||||
yield from self.section_page(target_page) # 前往目标页
|
||||
yield f"event: close\ndata: 已完成\n\n"
|
||||
|
||||
def _update_setting(self, **kwargs):
|
||||
Setting.query.filter_by(name="book_download").update(kwargs)
|
||||
db.session.commit()
|
||||
for key, value in kwargs.items():
|
||||
self.setting[key] = value
|
||||
|
||||
Reference in New Issue
Block a user