Auto restart and errror handling when fetching open llm leaderboard

app.py

@@ -6,6 +6,9 @@ from tqdm import tqdm
 from bs4 import BeautifulSoup
 from huggingface_hub import HfApi, list_models, list_datasets, list_spaces
 import gradio as gr
+from apscheduler.schedulers.background import BackgroundScheduler
+import datetime
+
 
 api = HfApi()
 
@@ -26,26 +29,32 @@ def get_sum(df_for_sum_function):
   return {"Downloads": sum_downloads, "Likes": sum_likes}
 
 def get_openllm_leaderboard():
-    url = 'https://huggingfaceh4-open-llm-leaderboard.hf.space/'
-    response = requests.get(url)
-    soup = BeautifulSoup(response.content, 'html.parser')
-    script_elements = soup.find_all('script')
-    data = json.loads(str(script_elements[1])[31:-10])
-
-    component_index = 19
-
-    result_list = []
-    i = 0
-    while True:
-        try:
-            normal_name = data['components'][component_index]['props']['value']['data'][i][-1]
-            result_list.append(normal_name)
-            i += 1
-        except (IndexError, AttributeError):
-            return result_list
+    try:
+      url = 'https://huggingfaceh4-open-llm-leaderboard.hf.space/'
+      response = requests.get(url)
+      soup = BeautifulSoup(response.content, 'html.parser')
+      script_elements = soup.find_all('script')
+      data = json.loads(str(script_elements[1])[31:-10])
+
+      component_index = 19
+
+      result_list = []
+      i = 0
+      while True:
+          try:
+              normal_name = data['components'][component_index]['props']['value']['data'][i][-1]
+              result_list.append(normal_name)
+              i += 1
+          except (IndexError, AttributeError):
+              return result_list
+    except Exception as e:
+      print("Error on open llm leaderboard: ", e)
+      return []
 
 
 def get_ranking(model_list, target_org):
+    if model_list == []:
+        return "Error on Leaderboard"
     for index, model in enumerate(model_list):
       if model.split("/")[0].lower() == target_org.lower():
           return [index+1, model]
@@ -208,10 +217,14 @@ def get_ranking_trend(json_data, org_name):
     else:
       return {"id": "Not Found", "rank": "Not Found"}
 
+def restart_space():
+    api.restart_space(repo_id="TFLai/organization-leaderboard", token=HF_TOKEN)
+
+
 with open("org_names.txt", "r") as f:
   org_names_in_list = [i.rstrip("\n") for i in f.readlines()]
 
-
+datetime = str(datetime.datetime.now().strftime("%Y-%m-%d %H:%M"))
 INTRODUCTION_TEXT = f"""
 🎯 The Organization Leaderboard aims to track organization rankings. This space is inspired by the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
 
@@ -232,6 +245,10 @@ INTRODUCTION_TEXT = f"""
 **🌐 Note:** In the model's dataframe, there are some columns related to the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard). This data is also retrieved through web scraping.
 
 **🌐 Note:** In trending models, first 300 models/datasets/spaces is being retrieved from huggingface.
+
+## Last Update
+
+⌛ This space is last updated in **{datetime}**.
 """
 
 with gr.Blocks() as demo:
@@ -268,4 +285,8 @@ with gr.Blocks() as demo:
           headers = ["🔢 Serial Number", "🏢 Organization Name", "👍 Total Likes", "🚀 Number of Spaces", "📈 Average Likes per Space", "❤️ Most Liked Space", "👍 Most Like Count", "🔥 Trending Space", "👑 Best Rank at Trending Spaces"]
           gr.Dataframe(spaces_df.head(200), headers=headers, interactive=False,  datatype=["str", "markdown", "str", "str", "str", "markdown", "str", "markdown", "str"])
 
+
+
+scheduler = BackgroundScheduler()
+scheduler.add_job(restart_space, "interval", seconds=21600)
 demo.launch()