Upload 4 files

.gitattributes

@@ -1,35 +1,37 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+test.py

app.py

@@ -0,0 +1,230 @@
+import json
+import time
+import requests
+import schedule
+import gradio as gr
+import pandas as pd
+from tqdm import tqdm
+from bs4 import BeautifulSoup
+from urllib.parse import urlparse
+
+TIMEOUT = 15
+DELAY = 1
+
+
+def get_studios(username: str):
+    # 请求负载
+    payload = {
+        "PageNumber": 1,
+        "PageSize": 1000,
+        "Name": "",
+        "SortBy": "gmt_modified",
+        "Order": "desc",
+    }
+    try:
+        # 发送PUT请求
+        response = requests.put(
+            f"https://www.modelscope.cn/api/v1/studios/{username}/list",
+            data=json.dumps(payload),
+            headers={
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
+            },
+            timeout=TIMEOUT,
+        )
+        # 检查请求是否成功
+        response.raise_for_status()
+        # 解析JSON响应
+        spaces: list = response.json()["Data"]["Studios"]
+        if spaces:
+            studios = []
+            for space in spaces:
+                studios.append(
+                    f"https://www.modelscope.cn/studios/{username}/{space['Name']}"
+                )
+
+            return studios
+
+    except requests.exceptions.HTTPError as errh:
+        print(f"HTTP错误发生: {errh}")
+    except requests.exceptions.ConnectionError as errc:
+        print(f"连接错误发生: {errc}")
+    except requests.exceptions.Timeout as errt:
+        print(f"请求超时: {errt}, retrying...")
+        time.sleep(DELAY)
+        return get_studios(username)
+
+    except requests.exceptions.RequestException as err:
+        print(f"请求发生错误: {err}")
+
+    return []
+
+
+def get_spaces(username: str):
+    try:
+        # 发送GET请求
+        response = requests.get(
+            "https://huggingface.co/spaces-json",
+            params={"sort": "trending", "search": username},
+            headers={
+                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537"
+            },
+            timeout=TIMEOUT,
+        )
+        # 检查请求是否成功
+        response.raise_for_status()
+        # 解析JSON响应
+        spaces: list = response.json()["spaces"]
+        studios = []
+        for space in spaces:
+            if space["author"] == username:
+                studios.append(f"https://huggingface.co/spaces/{space['id']}")
+
+        return studios
+
+    except requests.exceptions.HTTPError as errh:
+        print(f"HTTP错误发生: {errh}")
+
+    except requests.exceptions.Timeout as errt:
+        print(f"请求超时: {errt}, retrying...")
+        time.sleep(DELAY)
+        return get_spaces(username)
+
+    except requests.exceptions.RequestException as err:
+        print(f"请求发生错误: {err}")
+
+    return []
+
+
+def activate_space(url: str):
+    success = "success"
+    try:
+        # 发送GET请求获取页面内容
+        response = requests.get(url, timeout=TIMEOUT)
+        response.raise_for_status()  # 确保请求成功
+        web_page_content = response.text
+
+        # 使用BeautifulSoup解析页面
+        soup = BeautifulSoup(web_page_content, "html.parser")
+
+        # 寻找class为btn-lg的按钮
+        button = soup.find("button", class_="btn-lg")
+        if not button:
+            # print("未找到class为'btn-lg'的按钮。")
+            return success
+
+        # 获取表单的action属性和method属性
+        form = button.find_parent("form")
+        if not form:
+            return "按钮未在表单内找到。"
+
+        form_action = form.get("action")
+        form_method = form.get("method", "GET").upper()  # 默认为GET
+        host = "https://" + urlparse(url).hostname
+        if not host in form_action:
+            form_action = host + form_action
+
+        # 提取表单数据
+        form_data = {
+            input_tag.get("name"): input_tag.get("value")
+            for input_tag in form.find_all("input")
+            if input_tag.has_attr("name")
+        }
+
+        # 发送请求提交表单
+        if form_method == "POST":
+            response = requests.post(form_action, data=form_data)
+        else:
+            response = requests.get(form_action, params=form_data)
+
+        # 打印响应内容
+        print("提交表单后的页面内容:")
+        print(response.text)
+
+    except requests.exceptions.Timeout as errt:
+        print(f"请求超时: {errt}, retrying...")
+        time.sleep(DELAY)
+        return activate_space(url)
+
+    except requests.RequestException as e:
+        success = f"{e}"
+
+    except Exception as e:
+        success = f"{e}"
+
+    return success
+
+
+def activate(hf_users: str, ms_users: str):
+    hf_usernames = hf_users.split(";")
+    ms_usernames = ms_users.split(";")
+    spaces = []
+    for user in tqdm(hf_usernames, desc="Collecting spaces..."):
+        username = user.strip()
+        if username:
+            spaces += get_spaces(username)
+            time.sleep(DELAY)
+
+    for user in tqdm(ms_usernames, desc="Collecting studios..."):
+        username = user.strip()
+        if username:
+            spaces += get_studios(username)
+            time.sleep(DELAY)
+
+    output = []
+    for space in tqdm(spaces, desc="Activating spaces..."):
+        output.append({"space": space, "status": activate_space(space)})
+        time.sleep(DELAY)
+
+    print("Activation complete!")
+    return pd.DataFrame(output)
+
+
+def monitor(hf_users: str, ms_users: str, trigger_time="12:30"):
+    if schedule.get_jobs():
+        return
+
+    print(f"监控开启中...每日触发时间：{trigger_time}")
+    schedule.every().day.at(trigger_time).do(lambda: activate(hf_users, ms_users))
+    while True:
+        schedule.run_pending()
+        time.sleep(DELAY)
+
+
+def list_tasks():
+    jobs = schedule.get_jobs()
+    if jobs:
+        return f"{jobs}".replace("[", "").replace("]", "")
+
+    return "None"
+
+
+with gr.Blocks() as iface:
+    gr.Interface(
+        title="Start keeping all spaces active daily",
+        fn=monitor,
+        inputs=[
+            gr.Textbox(label="HuggingFace", placeholder="Usernames joint by ;"),
+            gr.Textbox(label="ModelScope", placeholder="Usernames joint by ;"),
+        ],
+        outputs=None,
+        allow_flagging=False,
+    )
+    gr.Interface(
+        title="See current task status",
+        fn=list_tasks,
+        inputs=None,
+        outputs=gr.Textbox(label="Current task details"),
+        allow_flagging=False,
+    )
+    gr.Interface(
+        title="Test activation for all spaces once",
+        fn=activate,
+        inputs=[
+            gr.Textbox(label="HuggingFace", placeholder="Usernames joint by ;"),
+            gr.Textbox(label="ModelScope", placeholder="Usernames joint by ;"),
+        ],
+        outputs=gr.Dataframe(label="Activated spaces"),
+        allow_flagging=False,
+    )
+
+iface.launch()

requirements.txt

@@ -0,0 +1,4 @@
+requests
+beautifulsoup4
+tqdm
+schedule