Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,29 +1,18 @@
|
|
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 |
-
|
13 |
-
|
14 |
-
return None
|
15 |
|
16 |
def extract_tiktok_id(url):
|
17 |
"""استخراج معرف فيديو تيكتوك من الرابط"""
|
18 |
-
|
19 |
-
|
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"""
|
@@ -32,55 +21,54 @@ def get_hashtags_from_text(text):
|
|
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 |
-
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
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 |
-
|
78 |
-
|
79 |
-
|
80 |
-
|
81 |
-
|
82 |
-
|
83 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
|
85 |
except Exception as e:
|
86 |
return f"حدث خطأ: {str(e)}", "", ""
|
@@ -93,8 +81,8 @@ def gradio_interface():
|
|
93 |
|
94 |
with gr.Row():
|
95 |
url_input = gr.Textbox(
|
96 |
-
label="🔗 أدخل رابط
|
97 |
-
placeholder="https
|
98 |
)
|
99 |
|
100 |
with gr.Row():
|
@@ -131,4 +119,4 @@ def gradio_interface():
|
|
131 |
|
132 |
if __name__ == "__main__":
|
133 |
demo = gradio_interface()
|
134 |
-
demo.launch()
|
|
|
1 |
import gradio as gr
|
|
|
2 |
from bs4 import BeautifulSoup
|
3 |
import requests
|
4 |
import re
|
5 |
from urllib.parse import urlparse
|
|
|
|
|
6 |
|
7 |
def extract_youtube_id(url):
|
8 |
"""استخراج معرف فيديو يوتيوب من الرابط"""
|
9 |
+
match = re.search(r'(?:v=|\/)([0-9A-Za-z_-]{11}).*', url)
|
10 |
+
return match.group(1) if match else None
|
|
|
11 |
|
12 |
def extract_tiktok_id(url):
|
13 |
"""استخراج معرف فيديو تيكتوك من الرابط"""
|
14 |
+
match = re.search(r'video/(\d+)', url)
|
15 |
+
return match.group(1) if match else None
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
|
17 |
def get_hashtags_from_text(text):
|
18 |
"""استخراج الهاشتاغات من النص"""
|
|
|
21 |
def extract_from_url(url):
|
22 |
"""استخراج البيانات من الرابط"""
|
23 |
domain = urlparse(url).netloc
|
|
|
24 |
headers = {
|
25 |
'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'
|
26 |
}
|
27 |
|
28 |
try:
|
29 |
+
# استخراج البيانات من YouTube
|
30 |
if 'youtube.com' in domain or 'youtu.be' in domain:
|
31 |
video_id = extract_youtube_id(url)
|
32 |
if not video_id:
|
33 |
return "رابط يوتيوب غير صالح", "", ""
|
|
|
|
|
|
|
34 |
|
35 |
+
response = requests.get(url, headers=headers)
|
36 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
37 |
+
|
38 |
+
# استخراج العنوان
|
39 |
+
title_element = soup.find('h1', {'id': 'title'})
|
40 |
+
title = title_element.text.strip() if title_element else "العنوان غير متوفر"
|
41 |
+
|
42 |
+
# استخراج الوصف
|
43 |
+
description_element = soup.find('div', {'id': 'description'})
|
44 |
+
description = description_element.text.strip() if description_element else "الوصف غير متوفر"
|
45 |
+
|
46 |
+
# استخراج الهاشتاغات
|
47 |
+
hashtags = get_hashtags_from_text(description)
|
48 |
+
|
49 |
+
return title, description, "\n".join(hashtags)
|
50 |
+
|
51 |
+
# استخراج البيانات من TikTok
|
52 |
elif 'tiktok.com' in domain:
|
53 |
video_id = extract_tiktok_id(url)
|
54 |
if not video_id:
|
55 |
return "رابط تيكتوك غير صالح", "", ""
|
56 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
response = requests.get(url, headers=headers)
|
58 |
+
soup = BeautifulSoup(response.text, 'html.parser')
|
59 |
+
|
60 |
+
# استخراج العنوان
|
61 |
+
title_element = soup.find('h1')
|
62 |
+
title = title_element.text.strip() if title_element else "العنوان غير متوفر"
|
63 |
+
|
64 |
+
# استخراج الوصف
|
65 |
+
description = title # الوصف موجود داخل نفس العنصر <h1>
|
66 |
+
|
67 |
+
# استخراج الهاشتاغات
|
68 |
+
hashtags_elements = soup.find_all('a', {'class': re.compile(r'.*hashtag.*')})
|
69 |
+
hashtags = [tag.text.strip() for tag in hashtags_elements]
|
70 |
+
|
71 |
+
return title, description, "\n".join(hashtags)
|
72 |
|
73 |
except Exception as e:
|
74 |
return f"حدث خطأ: {str(e)}", "", ""
|
|
|
81 |
|
82 |
with gr.Row():
|
83 |
url_input = gr.Textbox(
|
84 |
+
label="🔗 أدخل رابط يوتيوب/تيكتوك",
|
85 |
+
placeholder="https://.../video/..."
|
86 |
)
|
87 |
|
88 |
with gr.Row():
|
|
|
119 |
|
120 |
if __name__ == "__main__":
|
121 |
demo = gradio_interface()
|
122 |
+
demo.launch()
|