Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import gradio as gr
|
2 |
+
from collections import Counter
|
3 |
+
from bs4 import BeautifulSoup
|
4 |
+
import requests
|
5 |
+
import re
|
6 |
+
from urllib.parse import urlparse
|
7 |
+
import json
|
8 |
+
from youtube_transcript_api import YouTubeTranscriptApi
|
9 |
+
|
10 |
+
def extract_youtube_id(url):
|
11 |
+
"""استخراج معرف فيديو يوتيوب من الرابط"""
|
12 |
+
if match := re.search(r'(?:v=|\/)([0-9A-Za-z_-]{11}).*', url):
|
13 |
+
return match.group(1)
|
14 |
+
return None
|
15 |
+
|
16 |
+
def extract_tiktok_id(url):
|
17 |
+
"""استخراج معرف فيديو تيكتوك من الرابط"""
|
18 |
+
if match := re.search(r'video/(\d+)', url):
|
19 |
+
return match.group(1)
|
20 |
+
return None
|
21 |
+
|
22 |
+
def extract_instagram_shortcode(url):
|
23 |
+
"""استخراج معرف منشور انستغرام من الرابط"""
|
24 |
+
if match := re.search(r'/(p|reel)/([A-Za-z0-9_-]+)', url):
|
25 |
+
return match.group(2)
|
26 |
+
return None
|
27 |
+
|
28 |
+
def get_hashtags_from_text(text):
|
29 |
+
"""استخراج الهاشتاغات من النص"""
|
30 |
+
return re.findall(r'#\w+', text)
|
31 |
+
|
32 |
+
def extract_from_url(url):
|
33 |
+
"""استخراج البيانات من الرابط"""
|
34 |
+
domain = urlparse(url).netloc
|
35 |
+
|
36 |
+
headers = {
|
37 |
+
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36'
|
38 |
+
}
|
39 |
+
|
40 |
+
try:
|
41 |
+
if 'youtube.com' in domain or 'youtu.be' in domain:
|
42 |
+
video_id = extract_youtube_id(url)
|
43 |
+
if not video_id:
|
44 |
+
return "رابط يوتيوب غير صالح", "", ""
|
45 |
+
|
46 |
+
api_url = f"https://www.youtube.com/watch?v={video_id}"
|
47 |
+
response = requests.get(api_url, headers=headers)
|
48 |
+
|
49 |
+
if 'watch-title' in response.text:
|
50 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
51 |
+
title = soup.find('meta', property='og:title')['content']
|
52 |
+
description = soup.find('meta', property='og:description')['content']
|
53 |
+
hashtags = get_hashtags_from_text(description)
|
54 |
+
|
55 |
+
return title, description, "\n".join(hashtags)
|
56 |
+
|
57 |
+
elif 'tiktok.com' in domain:
|
58 |
+
video_id = extract_tiktok_id(url)
|
59 |
+
if not video_id:
|
60 |
+
return "رابط تيكتوك غير صالح", "", ""
|
61 |
+
|
62 |
+
response = requests.get(url, headers=headers)
|
63 |
+
if response.status_code == 200:
|
64 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
65 |
+
title = soup.find('meta', property='og:title')['content']
|
66 |
+
description = soup.find('meta', property='og:description')['content']
|
67 |
+
hashtags = get_hashtags_from_text(description)
|
68 |
+
|
69 |
+
return title, description, "\n".join(hashtags)
|
70 |
+
|
71 |
+
elif 'instagram.com' in domain:
|
72 |
+
shortcode = extract_instagram_shortcode(url)
|
73 |
+
if not shortcode:
|
74 |
+
return "رابط انستغرام غير صالح", "", ""
|
75 |
+
|
76 |
+
response = requests.get(url, headers=headers)
|
77 |
+
if response.status_code == 200:
|
78 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
79 |
+
title = soup.find('meta', property='og:title')['content']
|
80 |
+
description = soup.find('meta', property='og:description')['content']
|
81 |
+
hashtags = get_hashtags_from_text(description)
|
82 |
+
|
83 |
+
return title, description, "\n".join(hashtags)
|
84 |
+
|
85 |
+
except Exception as e:
|
86 |
+
return f"حدث خطأ: {str(e)}", "", ""
|
87 |
+
|
88 |
+
return "لم يتم العثور على بيانات", "", ""
|
89 |
+
|
90 |
+
def gradio_interface():
|
91 |
+
with gr.Blocks() as demo:
|
92 |
+
gr.Markdown("## 📱 محلل روابط وسائل التواصل الاجتماعي")
|
93 |
+
|
94 |
+
with gr.Row():
|
95 |
+
url_input = gr.Textbox(
|
96 |
+
label="🔗 أدخل رابط يوتيوب/تيكتوك/انستغرام",
|
97 |
+
placeholder="https://..."
|
98 |
+
)
|
99 |
+
|
100 |
+
with gr.Row():
|
101 |
+
analyze_btn = gr.Button("تحليل الرابط", variant="primary")
|
102 |
+
|
103 |
+
with gr.Row():
|
104 |
+
title_output = gr.Textbox(
|
105 |
+
label="📝 العنوان",
|
106 |
+
lines=2,
|
107 |
+
interactive=False
|
108 |
+
)
|
109 |
+
|
110 |
+
with gr.Row():
|
111 |
+
description_output = gr.Textbox(
|
112 |
+
label="📄 الوصف",
|
113 |
+
lines=5,
|
114 |
+
interactive=False
|
115 |
+
)
|
116 |
+
|
117 |
+
with gr.Row():
|
118 |
+
hashtags_output = gr.Textbox(
|
119 |
+
label="🏷️ الهاشتاغات",
|
120 |
+
lines=5,
|
121 |
+
interactive=False
|
122 |
+
)
|
123 |
+
|
124 |
+
analyze_btn.click(
|
125 |
+
fn=extract_from_url,
|
126 |
+
inputs=[url_input],
|
127 |
+
outputs=[title_output, description_output, hashtags_output]
|
128 |
+
)
|
129 |
+
|
130 |
+
return demo
|
131 |
+
|
132 |
+
if __name__ == "__main__":
|
133 |
+
demo = gradio_interface()
|
134 |
+
demo.launch()
|