webscout 1.2.6__tar.gz → 1.2.9__tar.gz

{webscout-1.2.6 → webscout-1.2.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: webscout
-Version: 1.2.6
+Version: 1.2.9
 Summary: Search for words, documents, images, videos, news, maps and text translation using the Google, DuckDuckGo.com, yep.com, phind.com, you.com, etc Also containes AI models and now can transcribe yt videos
 Author: OEvortex
 Author-email: helpingai5@gmail.com
@@ -229,17 +229,23 @@ def extract_transcript(video_id):
     try:
         transcript_list = transcriber.list_transcripts(video_id)
         for transcript in transcript_list:
-            transcript_text_list = transcript.fetch()
+            transcript_data_list = transcript.fetch()
             lang = transcript.language
             transcript_text = ""
             if transcript.language_code == 'en':
-                for line in transcript_text_list:
-                    transcript_text += " " + line["text"]
+                for line in transcript_data_list:
+                    start_time = line['start']
+                    end_time = start_time + line['duration']
+                    formatted_line = f"{start_time:.2f} - {end_time:.2f}: {line['text']}\n"
+                    transcript_text += formatted_line
                 return transcript_text
             elif transcript.is_translatable:
                 english_transcript_list = transcript.translate('en').fetch()
                 for line in english_transcript_list:
-                    transcript_text += " " + line["text"]
+                    start_time = line['start']
+                    end_time = start_time + line['duration']
+                    formatted_line = f"{start_time:.2f} - {end_time:.2f}: {line['text']}\n"
+                    transcript_text += formatted_line
                 return transcript_text
         print("Transcript extraction failed. Please check the video URL.")
     except Exception as e:
@@ -351,11 +357,12 @@ import logging
 import sys
 from itertools import chain
 from random import shuffle
-
 import requests
 from webscout import AsyncWEBS
 
-# bypass curl-cffi NotImplementedError in windows https://curl-cffi.readthedocs.io/en/latest/faq/
+# If you have proxies, define them here
+proxies = None
+
 if sys.platform.lower().startswith("win"):
     asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
 
@@ -367,24 +374,21 @@ def get_words():
 
 async def aget_results(word):
     async with AsyncWEBS(proxies=proxies) as WEBS:
-        results = [r async for r in WEBS.text(word, max_results=None)]
+        results = await WEBS.text(word, max_results=None)
         return results
 
 async def main():
     words = get_words()
     shuffle(words)
-    tasks = []
-    for word in words[:10]:
-        tasks.append(aget_results(word))
+    tasks = [aget_results(word) for word in words[:10]]
     results = await asyncio.gather(*tasks)
     print(f"Done")
     for r in chain.from_iterable(results):
         print(r)
-    
 
-if __name__ == "__main__":
-    logging.basicConfig(level=logging.DEBUG)
-    asyncio.run(main())
+logging.basicConfig(level=logging.DEBUG)
+
+await main()
 ```
 It is important to note that the WEBS and AsyncWEBS classes should always be used as a context manager (with statement).
 This ensures proper resource management and cleanup, as the context manager will automatically handle opening and closing the HTTP client connection.
@@ -685,6 +689,6 @@ def chat(model_name, system_message="You are Jarvis"):# system prompt
     AI.chat()
 
 if __name__ == "__main__":
-    model_name = "mistralai/Mistral-7B-Instruct-v0.1" # name of the model you wish to use It supports ALL text generation models on deepinfra.com.
+    model_name = "mistralai/Mistral-7B-Instruct-v0.2" # name of the model you wish to use It supports ALL text generation models on deepinfra.com.
     chat(model_name)
 ```

{webscout-1.2.6 → webscout-1.2.9}/README.md

@@ -177,17 +177,23 @@ def extract_transcript(video_id):
     try:
         transcript_list = transcriber.list_transcripts(video_id)
         for transcript in transcript_list:
-            transcript_text_list = transcript.fetch()
+            transcript_data_list = transcript.fetch()
             lang = transcript.language
             transcript_text = ""
             if transcript.language_code == 'en':
-                for line in transcript_text_list:
-                    transcript_text += " " + line["text"]
+                for line in transcript_data_list:
+                    start_time = line['start']
+                    end_time = start_time + line['duration']
+                    formatted_line = f"{start_time:.2f} - {end_time:.2f}: {line['text']}\n"
+                    transcript_text += formatted_line
                 return transcript_text
             elif transcript.is_translatable:
                 english_transcript_list = transcript.translate('en').fetch()
                 for line in english_transcript_list:
-                    transcript_text += " " + line["text"]
+                    start_time = line['start']
+                    end_time = start_time + line['duration']
+                    formatted_line = f"{start_time:.2f} - {end_time:.2f}: {line['text']}\n"
+                    transcript_text += formatted_line
                 return transcript_text
         print("Transcript extraction failed. Please check the video URL.")
     except Exception as e:
@@ -299,11 +305,12 @@ import logging
 import sys
 from itertools import chain
 from random import shuffle
-
 import requests
 from webscout import AsyncWEBS
 
-# bypass curl-cffi NotImplementedError in windows https://curl-cffi.readthedocs.io/en/latest/faq/
+# If you have proxies, define them here
+proxies = None
+
 if sys.platform.lower().startswith("win"):
     asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
 
@@ -315,24 +322,21 @@ def get_words():
 
 async def aget_results(word):
     async with AsyncWEBS(proxies=proxies) as WEBS:
-        results = [r async for r in WEBS.text(word, max_results=None)]
+        results = await WEBS.text(word, max_results=None)
         return results
 
 async def main():
     words = get_words()
     shuffle(words)
-    tasks = []
-    for word in words[:10]:
-        tasks.append(aget_results(word))
+    tasks = [aget_results(word) for word in words[:10]]
     results = await asyncio.gather(*tasks)
     print(f"Done")
     for r in chain.from_iterable(results):
         print(r)
-    
 
-if __name__ == "__main__":
-    logging.basicConfig(level=logging.DEBUG)
-    asyncio.run(main())
+logging.basicConfig(level=logging.DEBUG)
+
+await main()
 ```
 It is important to note that the WEBS and AsyncWEBS classes should always be used as a context manager (with statement).
 This ensures proper resource management and cleanup, as the context manager will automatically handle opening and closing the HTTP client connection.
@@ -633,6 +637,6 @@ def chat(model_name, system_message="You are Jarvis"):# system prompt
     AI.chat()
 
 if __name__ == "__main__":
-    model_name = "mistralai/Mistral-7B-Instruct-v0.1" # name of the model you wish to use It supports ALL text generation models on deepinfra.com.
+    model_name = "mistralai/Mistral-7B-Instruct-v0.2" # name of the model you wish to use It supports ALL text generation models on deepinfra.com.
     chat(model_name)
 ```

{webscout-1.2.6 → webscout-1.2.9}/setup.py

@@ -1,15 +1,15 @@
 from setuptools import setup, find_packages
 
-version = None
-with open("webscout/version.py") as version_file:
-    exec(version_file.read())
+# version = None
+# with open("webscout/version.py") as version_file:
+#     exec(version_file.read())
 
 with open("README.md", encoding="utf-8") as f:
     README = f.read()
 
 setup(
     name="webscout",
-    version="1.2.6", 
+    version="1.2.9", 
     description="Search for words, documents, images, videos, news, maps and text translation using the Google, DuckDuckGo.com, yep.com, phind.com, you.com, etc Also containes AI models and now can transcribe yt videos",
     long_description=README,
     long_description_content_type="text/markdown",
@@ -54,6 +54,7 @@ setup(
         "tiktoken",
         "tldextract",
         "orjson",
+        # "appdirs"
     ],
     entry_points={
         "console_scripts": [

{webscout-1.2.6 → webscout-1.2.9}/webscout/__init__.py

@@ -9,7 +9,6 @@ from .webscout_search import WEBS
 from .webscout_search_async import AsyncWEBS
 from .version import __version__
 from .DWEBS import DeepWEBS
-from .AIutel import appdir
 from .transcriber import transcriber