Serendipity/crawl-tiktok-video
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

style: 统一代码格式并改进异常处理

Browse Source 
- 将多行字符串调整为符合PEP 8的格式
- 统一使用显式的异常捕获（except Exception）
- 改进线程的daemon设置方式
- 移除未使用的异常变量和导入
- 修复文件末尾的换行符问题
This commit is contained in:
LHY0125
2026-02-10 16:57:31 +08:00
parent 92619edcdb
commit bccffc006a
11 changed files with 71 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/__pycache__/downloader.cpython-310.pyc
BIN
View File
Binary file not shown.
src/__pycache__/utils.cpython-310.pyc
BIN
View File
Binary file not shown.
src/downloader.py
+10 -10
View File
@@ -1,6 +1,7 @@
import requests
import time
def download_file(url, filepath, referer=None, log_callback=None):
"""
[Data Layer] 文件下载执行器
@@ -9,7 +10,11 @@ def download_file(url, filepath, referer=None, log_callback=None):
try:
# 根据不同平台可能需要调整 Headers
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/120.0.0.0 Safari/537.36"
),
}
# 优先使用传入的 referer
@@ -17,20 +22,14 @@ def download_file(url, filepath, referer=None, log_callback=None):
headers["Referer"] = referer
else:
# 简单的 Referer 区分 (保留旧逻辑作为后备)
if (
"bilibili.com" in url
or "hdslb.com" in url
or "bilivideo.com" in url
):
if "bilibili.com" in url or "hdslb.com" in url or "bilivideo.com" in url:
headers["Referer"] = "https://www.bilibili.com/"
else:
headers["Referer"] = "https://www.douyin.com/"
for i in range(3):
try:
response = requests.get(
url, headers=headers, stream=True, timeout=20
)
response = requests.get(url, headers=headers, stream=True, timeout=20)
if response.status_code == 200:
with open(filepath, "wb") as f:
for chunk in response.iter_content(chunk_size=1024 * 1024):
@@ -41,7 +40,8 @@ def download_file(url, filepath, referer=None, log_callback=None):
if i == 2:
if log_callback:
log_callback(
f"下载请求失败: Status {response.status_code} | URL: {url[:30]}..."
f"下载请求失败: Status {response.status_code} "
f"| URL: {url[:30]}..."
)
except requests.exceptions.RequestException as e:
if i == 2:
src/tasks/__pycache__/bilibili.cpython-310.pyc
BIN
View File
Binary file not shown.
src/tasks/__pycache__/douyin.cpython-310.pyc
BIN
View File
Binary file not shown.
src/tasks/bilibili.py
+13 -5
View File
@@ -5,13 +5,17 @@ import json
import requests
import concurrent.futures
from datetime import datetime
from tkinter import messagebox
from DrissionPage import ChromiumPage, ChromiumOptions
from src.downloader import download_file
def run_bilibili_task(
target_url, target_count, save_root, browser_path, log_callback, finish_callback
target_url,
target_count,
save_root,
browser_path,
log_callback,
finish_callback=None,
):
"""
[Control Layer] B站核心业务流程
@@ -85,7 +89,7 @@ def run_bilibili_task(
next_btn.click()
no_new_data_count = 0
time.sleep(2)
except:
except Exception:
pass
else:
no_new_data_count = 0
@@ -146,7 +150,7 @@ def run_bilibili_task(
if dp:
try:
dp.close()
except:
except Exception:
pass
finally:
# 这里需要一种机制通知UI线程结束，或者由UI层处理
@@ -218,7 +222,11 @@ def get_bilibili_play_url(bvid):
"""
url = f"https://www.bilibili.com/video/{bvid}"
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
"User-Agent": (
"Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
"AppleWebKit/537.36 (KHTML, like Gecko) "
"Chrome/120.0.0.0 Safari/537.36"
),
"Referer": "https://www.bilibili.com/",
}
try:
src/tasks/douyin.py
+28 -10
View File
@@ -5,7 +5,15 @@ from datetime import datetime
from DrissionPage import ChromiumPage, ChromiumOptions
from src.downloader import download_file
def run_douyin_task(target_url, target_count, save_root, browser_path, log_callback, finish_callback):
def run_douyin_task(
target_url,
target_count,
save_root,
browser_path,
log_callback,
finish_callback,
):
"""
[Control Layer] 抖音核心业务流程
1. 启动浏览器
@@ -53,7 +61,7 @@ def run_douyin_task(target_url, target_count, save_root, browser_path, log_callb
):
collected_works.append(aweme)
found_new = True
except:
except Exception:
pass
log_callback(f"已获取作品信息: {len(collected_works)}/{target_count}")
@@ -99,7 +107,11 @@ def run_douyin_task(target_url, target_count, save_root, browser_path, log_callb
file_name_base = f"{date_str}({count_idx})"
download_tasks.append(
{"work": work, "index": index, "file_name_base": file_name_base}
{
"work": work,
"index": index,
"file_name_base": file_name_base,
}
)
# 使用线程池执行下载
@@ -115,7 +127,7 @@ def run_douyin_task(target_url, target_count, save_root, browser_path, log_callb
len(works_to_process),
save_root,
task["file_name_base"],
log_callback
log_callback,
)
)
@@ -133,12 +145,15 @@ def run_douyin_task(target_url, target_count, save_root, browser_path, log_callb
if dp:
try:
dp.close()
except:
except Exception:
pass
finally:
pass
def process_douyin_work(work, index, total_count, save_root, file_name_base, log_callback):
def process_douyin_work(
work, index, total_count, save_root, file_name_base, log_callback
):
"""
[Data Layer] 单个任务处理逻辑 (Worker)
判断作品类型(视频/图文)，生成路径并调用下载器
@@ -148,9 +163,11 @@ def process_douyin_work(work, index, total_count, save_root, file_name_base, log
if "images" in work and work["images"]:
is_video = False
log_callback(
f"[{index + 1}/{total_count}] {file_name_base} | {'视频' if is_video else '图文'} | 下载中..."
msg = (
f"[{index + 1}/{total_count}] {file_name_base} | "
f"{'视频' if is_video else '图文'} | 下载中..."
)
log_callback(msg)
if is_video:
video_url = work["video"]["play_addr"]["url_list"][0]
@@ -158,7 +175,7 @@ def process_douyin_work(work, index, total_count, save_root, file_name_base, log
if not os.path.exists(file_path):
if download_file(video_url, file_path, log_callback=log_callback):
log_callback(
f"[{index + 1}/{total_count}] {file_name_base} -> 下载完成"
f"[{index + 1}/{total_count}] {file_name_base} " "-> 下载完成"
)
else:
log_callback(
@@ -166,7 +183,8 @@ def process_douyin_work(work, index, total_count, save_root, file_name_base, log
)
else:
log_callback(
f"[{index + 1}/{total_count}] {file_name_base} -> 文件已存在，跳过"
f"[{index + 1}/{total_count}] {file_name_base} "
"-> 文件已存在，跳过"
)
else:
img_folder = os.path.join(save_root, file_name_base)
src/ui/__pycache__/app.cpython-310.pyc
BIN
View File
Binary file not shown.
src/ui/app.py
+9 -3
View File
@@ -123,12 +123,18 @@ class DouyinDownloaderApp:
frame_platform.pack(padx=10, pady=5, fill="x")
rb_douyin = tk.Radiobutton(
frame_platform, text="抖音", variable=self.platform_var, value="douyin"
frame_platform,
text="抖音",
variable=self.platform_var,
value="douyin",
)
rb_douyin.pack(side="left", padx=10)
rb_bilibili = tk.Radiobutton(
frame_platform, text="B站", variable=self.platform_var, value="bilibili"
frame_platform,
text="B站",
variable=self.platform_var,
value="bilibili",
)
rb_bilibili.pack(side="left", padx=10)
@@ -223,8 +229,8 @@ class DouyinDownloaderApp:
thread = threading.Thread(
target=self.run_task,
args=(url, int(count_str), save_path, browser_path, platform),
daemon=True,
)
thread.daemon = True
thread.start()
def run_task(self, target_url, target_count, save_root, browser_path, platform):
video_downloader.py
+6 -3
View File
@@ -2,10 +2,13 @@ import tkinter as tk
from src.ui.app import DouyinDownloaderApp
# 运行脚本 (使用 my_env 环境):
# D:\ProgramData\anaconda3\envs\my_env\python.exe "D:\Code\doing_exercises\programs\Video Downloader\video_downloader.py"
# D:\ProgramData\anaconda3\envs\my_env\python.exe video_downloader.py
#
# 打包成 exe (使用 my_env 环境):
# D:\ProgramData\anaconda3\envs\my_env\python.exe -m nuitka --standalone --mingw64 --show-memory --show-progress --output-dir=build_nuitka --enable-plugin=tk-inter --include-data-dir=ico=ico --windows-icon-from-ico=ico\video_downloader.ico --main=video_downloader.py
# D:\ProgramData\anaconda3\envs\my_env\python.exe -m nuitka --standalone ^
# --mingw64 --show-memory --show-progress --output-dir=build_nuitka ^
# --enable-plugin=tk-inter --include-data-dir=ico=ico ^
# --windows-icon-from-ico=ico\video_downloader.ico --main=video_downloader.py
# 主函数入口
if __name__ == "__main__":
@@ -13,7 +16,7 @@ if __name__ == "__main__":
root = tk.Tk()
app = DouyinDownloaderApp(root)
root.mainloop()
except Exception as e:
except Exception:
import traceback
with open("error_log.txt", "w") as f: