Spaces:
Running
Running
Marcepelaez
commited on
Commit
•
befec25
1
Parent(s):
15ee190
app
Browse files
app.py
CHANGED
@@ -2,55 +2,163 @@ import streamlit as st
|
|
2 |
import requests
|
3 |
from bs4 import BeautifulSoup
|
4 |
import re
|
|
|
|
|
5 |
|
6 |
-
|
7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
try:
|
|
|
|
|
|
|
|
|
9 |
response = requests.get(url)
|
10 |
response.raise_for_status()
|
|
|
|
|
11 |
soup = BeautifulSoup(response.content, 'html.parser')
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
# Remove script, style, and other non-visible tags
|
14 |
-
for tag in soup(["script", "style", "meta", "link", "noscript", "header", "footer", "aside", "nav"
|
15 |
tag.extract()
|
16 |
-
|
17 |
# Get the header content
|
18 |
header_content = soup.find("header")
|
19 |
header_text = header_content.get_text() if header_content else ""
|
20 |
-
|
21 |
# Get the paragraph content
|
22 |
paragraph_content = soup.find_all("p")
|
23 |
paragraph_text = " ".join([p.get_text() for p in paragraph_content])
|
24 |
-
|
25 |
# Combine header and paragraph text
|
26 |
visible_text = f"{header_text}\n\n{paragraph_text}"
|
27 |
-
|
28 |
# Remove multiple whitespaces and newlines
|
29 |
visible_text = re.sub(r'\s+', ' ', visible_text)
|
30 |
return visible_text.strip()
|
|
|
31 |
except Exception as e:
|
32 |
st.error(f"Error occurred while scraping the data: {e}")
|
33 |
return None
|
34 |
|
35 |
-
# Streamlit UI
|
36 |
def main():
|
37 |
-
|
38 |
-
|
|
|
|
|
|
|
39 |
# Get the URL from the user
|
40 |
url_input = st.text_input("Enter the URL of the web page:", "")
|
41 |
-
|
42 |
-
|
|
|
|
|
|
|
43 |
if url_input:
|
44 |
# Extract visible text from the URL
|
45 |
-
|
46 |
-
|
47 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
st.subheader("Scraped Text:")
|
49 |
-
st.write(
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
else:
|
51 |
-
st.warning("Failed to scrape
|
52 |
else:
|
53 |
st.warning("Please enter a valid URL.")
|
54 |
|
55 |
if __name__ == "__main__":
|
56 |
-
main()
|
|
|
2 |
import requests
|
3 |
from bs4 import BeautifulSoup
|
4 |
import re
|
5 |
+
import os
|
6 |
+
from urllib.parse import urljoin
|
7 |
|
8 |
+
def download_images(url, max_images=10):
|
9 |
+
"""
|
10 |
+
Download images from the given URL
|
11 |
+
|
12 |
+
Args:
|
13 |
+
url (str): URL of the webpage
|
14 |
+
max_images (int): Maximum number of images to download
|
15 |
+
|
16 |
+
Returns:
|
17 |
+
tuple: List of downloaded image paths and total image count
|
18 |
+
"""
|
19 |
try:
|
20 |
+
# Create a directory to save images if it doesn't exist
|
21 |
+
os.makedirs('downloaded_images', exist_ok=True)
|
22 |
+
|
23 |
+
# Send a request to the URL
|
24 |
response = requests.get(url)
|
25 |
response.raise_for_status()
|
26 |
+
|
27 |
+
# Parse the HTML content
|
28 |
soup = BeautifulSoup(response.content, 'html.parser')
|
29 |
+
|
30 |
+
# Find all image tags
|
31 |
+
img_tags = soup.find_all('img', src=True)
|
32 |
+
|
33 |
+
# List to store downloaded image paths
|
34 |
+
downloaded_images = []
|
35 |
+
|
36 |
+
# Download images
|
37 |
+
for i, img in enumerate(img_tags[:max_images], 1):
|
38 |
+
# Get the image source URL
|
39 |
+
img_url = img['src']
|
40 |
+
|
41 |
+
# Handle relative URLs
|
42 |
+
if not img_url.startswith(('http://', 'https://')):
|
43 |
+
img_url = urljoin(url, img_url)
|
44 |
+
|
45 |
+
try:
|
46 |
+
# Download the image
|
47 |
+
img_response = requests.get(img_url)
|
48 |
+
img_response.raise_for_status()
|
49 |
+
|
50 |
+
# Generate a unique filename
|
51 |
+
filename = f'downloaded_images/image_{i}.{img_url.split(".")[-1].split("?")[0]}'
|
52 |
+
|
53 |
+
# Save the image
|
54 |
+
with open(filename, 'wb') as f:
|
55 |
+
f.write(img_response.content)
|
56 |
+
|
57 |
+
downloaded_images.append(filename)
|
58 |
+
|
59 |
+
except Exception as img_error:
|
60 |
+
st.warning(f"Could not download image {i}: {img_error}")
|
61 |
+
|
62 |
+
return downloaded_images, len(img_tags)
|
63 |
+
|
64 |
+
except Exception as e:
|
65 |
+
st.error(f"Error occurred while downloading images: {e}")
|
66 |
+
return [], 0
|
67 |
|
68 |
+
def scrape_visible_text_from_url(url):
|
69 |
+
"""
|
70 |
+
Scrape visible text from the given URL
|
71 |
+
|
72 |
+
Args:
|
73 |
+
url (str): URL of the webpage
|
74 |
+
|
75 |
+
Returns:
|
76 |
+
str: Extracted visible text
|
77 |
+
"""
|
78 |
+
try:
|
79 |
+
response = requests.get(url)
|
80 |
+
response.raise_for_status()
|
81 |
+
soup = BeautifulSoup(response.content, 'html.parser')
|
82 |
+
|
83 |
# Remove script, style, and other non-visible tags
|
84 |
+
for tag in soup(["script", "style", "meta", "link", "noscript", "header", "footer", "aside", "nav"]):
|
85 |
tag.extract()
|
86 |
+
|
87 |
# Get the header content
|
88 |
header_content = soup.find("header")
|
89 |
header_text = header_content.get_text() if header_content else ""
|
90 |
+
|
91 |
# Get the paragraph content
|
92 |
paragraph_content = soup.find_all("p")
|
93 |
paragraph_text = " ".join([p.get_text() for p in paragraph_content])
|
94 |
+
|
95 |
# Combine header and paragraph text
|
96 |
visible_text = f"{header_text}\n\n{paragraph_text}"
|
97 |
+
|
98 |
# Remove multiple whitespaces and newlines
|
99 |
visible_text = re.sub(r'\s+', ' ', visible_text)
|
100 |
return visible_text.strip()
|
101 |
+
|
102 |
except Exception as e:
|
103 |
st.error(f"Error occurred while scraping the data: {e}")
|
104 |
return None
|
105 |
|
|
|
106 |
def main():
|
107 |
+
"""
|
108 |
+
Main Streamlit application
|
109 |
+
"""
|
110 |
+
st.title("Web Data Scraper with Image Downloader")
|
111 |
+
|
112 |
# Get the URL from the user
|
113 |
url_input = st.text_input("Enter the URL of the web page:", "")
|
114 |
+
|
115 |
+
# Maximum images to download slider
|
116 |
+
max_images = st.slider("Maximum number of images to download", 1, 20, 10)
|
117 |
+
|
118 |
+
if st.button("Scrape Content"):
|
119 |
if url_input:
|
120 |
# Extract visible text from the URL
|
121 |
+
text_data = scrape_visible_text_from_url(url_input)
|
122 |
+
|
123 |
+
# Download images
|
124 |
+
downloaded_images, total_images = download_images(url_input, max_images)
|
125 |
+
|
126 |
+
if text_data:
|
127 |
+
st.success("Content successfully scraped!")
|
128 |
+
|
129 |
+
# Display text
|
130 |
st.subheader("Scraped Text:")
|
131 |
+
st.write(text_data)
|
132 |
+
|
133 |
+
# Display and manage images
|
134 |
+
st.subheader(f"Images (Downloaded {len(downloaded_images)} out of {total_images} total)")
|
135 |
+
|
136 |
+
# Create columns for images
|
137 |
+
if downloaded_images:
|
138 |
+
cols = st.columns(min(len(downloaded_images), 3))
|
139 |
+
for i, img_path in enumerate(downloaded_images):
|
140 |
+
with cols[i % 3]:
|
141 |
+
st.image(img_path, use_column_width=True)
|
142 |
+
|
143 |
+
# Provide download option for all images
|
144 |
+
with open('downloaded_images.zip', 'wb') as zipf:
|
145 |
+
import zipfile
|
146 |
+
with zipfile.ZipFile(zipf, 'w') as zip_file:
|
147 |
+
for img_path in downloaded_images:
|
148 |
+
zip_file.write(img_path, os.path.basename(img_path))
|
149 |
+
|
150 |
+
st.download_button(
|
151 |
+
label="Download All Images",
|
152 |
+
data=open('downloaded_images.zip', 'rb').read(),
|
153 |
+
file_name='downloaded_images.zip',
|
154 |
+
mime='application/zip'
|
155 |
+
)
|
156 |
+
else:
|
157 |
+
st.warning("No images found on the page.")
|
158 |
else:
|
159 |
+
st.warning("Failed to scrape content from the URL.")
|
160 |
else:
|
161 |
st.warning("Please enter a valid URL.")
|
162 |
|
163 |
if __name__ == "__main__":
|
164 |
+
main()
|