File size: 2,409 Bytes
c565645 1f87fff f97eb77 1f87fff f97eb77 1f87fff f97eb77 bbe2d12 1f87fff f97eb77 1f87fff c565645 1f87fff f97eb77 1f87fff c565645 f97eb77 c565645 1f87fff f97eb77 1f87fff c565645 1f87fff |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 |
import gradio as gr
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api._errors import TranscriptsDisabled, NoTranscriptFound
import textwrap
import requests
from fp.fp import FreeProxy
import random
# Configure session with proxies
def configure_session():
try:
proxy = FreeProxy(rand=True, timeout=1).get()
proxies = {
"http": proxy,
"https": proxy
}
session = requests.Session()
session.proxies = proxies
session.headers.update({
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64)"
})
return session
except:
return None
def fetch_transcript(video_url):
try:
if not video_url:
return "Missing video URL", []
# Handle different YouTube formats
if "watch?v=" in video_url:
video_id = video_url.split("watch?v=")[-1].split("&")[0]
elif "youtu.be/" in video_url:
video_id = video_url.split("youtu.be/")[-1].split("?")[0]
elif "/shorts/" in video_url:
video_id = video_url.split("/shorts/")[-1].split("?")[0]
else:
return "Invalid YouTube URL format", []
# Create a new session with proxy for each request
session = configure_session()
if session:
transcript = YouTubeTranscriptApi.get_transcript(video_id, proxies=session.proxies)
else:
transcript = YouTubeTranscriptApi.get_transcript(video_id)
full_text = " ".join([entry["text"] for entry in transcript])
chunks = textwrap.wrap(full_text, width=4000, break_long_words=False)
return f"Word count: {len(full_text.split())}", chunks
except (TranscriptsDisabled, NoTranscriptFound) as e:
return str(e), []
except Exception as e:
proxy_used = session.proxies['http'] if session and hasattr(session, 'proxies') else 'None'
return f"Error: {str(e)} (Proxy: {proxy_used})", []
iface = gr.Interface(
fn=fetch_transcript,
inputs=gr.Textbox(label="YouTube URL", placeholder="Paste YouTube URL here..."),
outputs=[
gr.Textbox(label="Status"),
gr.Textbox(label="Transcript Chunks", lines=10)
],
title="YouTube Transcript Fetcher with Proxy Rotation",
description="Fetches transcripts using rotating proxies to avoid rate limits"
)
iface.launch() |