File size: 8,106 Bytes
36dbdcd
 
 
 
befec25
 
36dbdcd
1bf2dc7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4680d28
 
 
 
 
 
 
 
1bf2dc7
 
4680d28
1bf2dc7
 
 
4680d28
1bf2dc7
4680d28
 
1bf2dc7
 
4680d28
1bf2dc7
 
 
 
4680d28
1bf2dc7
4680d28
 
1bf2dc7
 
 
4680d28
1bf2dc7
 
 
4680d28
1bf2dc7
4680d28
 
1bf2dc7
 
 
4680d28
1bf2dc7
 
4680d28
1bf2dc7
 
 
4680d28
1bf2dc7
 
 
4680d28
1bf2dc7
4680d28
 
1bf2dc7
4680d28
 
1bf2dc7
 
 
 
 
 
 
 
 
 
 
36dbdcd
 
befec25
 
 
4680d28
0f3572b
4680d28
 
0f3572b
4680d28
 
0f3572b
4680d28
0f3572b
4680d28
 
36dbdcd
4680d28
 
 
 
 
 
0f3572b
 
befec25
36dbdcd
4680d28
6ef7dfb
4680d28
2df3230
befec25
4680d28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36dbdcd
 
 
 
4680d28
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
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
import streamlit as st
import requests
from bs4 import BeautifulSoup
import re
import os
from urllib.parse import urljoin

def apply_theme(theme):
    """
    Apply custom CSS based on the selected theme
    """
    if theme == "Claro":
        st.markdown("""
        <style>
        body {
            color: black;
            background-color: white;
        }
        .stTextInput > div > div > input {
            color: black;
            background-color: white;
        }
        .stMarkdown {
            color: black;
        }
        /* Light theme for HTML content */
        .light-theme {
            background-color: white !important;
            color: black !important;
        }
        .light-theme a {
            color: #0066cc !important;
        }
        .light-theme h1, .light-theme h2, .light-theme h3, 
        .light-theme h4, .light-theme h5, .light-theme h6 {
            color: #333 !important;
        }
        </style>
        """, unsafe_allow_html=True)
        return """
        <div style="background-color: white; color: black; padding: 20px;">
        <style>
            body { background-color: white !important; color: black !important; }
            a { color: #0066cc; }
            h1, h2, h3, h4, h5, h6 { color: #333; }
        </style>
        """
    else:
        st.markdown("""
        <style>
        body {
            color: white;
            background-color: #0E1117;
        }
        .stTextInput > div > div > input {
            color: white;
            background-color: #262730;
        }
        .stMarkdown {
            color: white;
        }
        </style>
        """, unsafe_allow_html=True)
        return ""

def scrape_web_content(url, max_images, theme):
    """
    Scrape the web content while preserving its original formatting
    
    Args:
        url (str): URL of the webpage
        max_images (int): Maximum number of images to download
        theme (str): Selected theme (Claro/Oscuro)
    
    Returns:
        dict: Extracted content with text, HTML, and images
    """
    try:
        # Send a request to the URL
        response = requests.get(url)
        response.raise_for_status()
        
        # Parse the HTML content
        soup = BeautifulSoup(response.content, 'html.parser')
        
        # Create a directory to save images if it doesn't exist
        os.makedirs('downloaded_images', exist_ok=True)
        
        # Download images
        downloaded_images = []
        img_tags = soup.find_all('img', src=True)
        for i, img in enumerate(img_tags[:max_images], 1):
            try:
                # Get the image source URL
                img_url = img['src']
                
                # Handle relative URLs
                if not img_url.startswith(('http://', 'https://')):
                    img_url = urljoin(url, img_url)
                
                # Download the image
                img_response = requests.get(img_url)
                img_response.raise_for_status()
                
                # Generate a unique filename
                filename = f'downloaded_images/image_{i}.{img_url.split(".")[-1].split("?")[0]}'
                
                # Save the image
                with open(filename, 'wb') as f:
                    f.write(img_response.content)
                
                # Update the image tag in the soup to point to local file
                img['src'] = filename
                downloaded_images.append(filename)
            
            except Exception as img_error:
                st.warning(f"Could not download image {i}: {img_error}")
        
        # Remove unwanted tags
        for tag in soup(["script", "style", "meta", "link", "noscript"]):
            tag.decompose()
        
        # Apply light theme styling if selected
        theme_prefix = apply_theme(theme) if theme == "Claro" else ""
        
        # Convert remaining soup to HTML string with theme prefix
        formatted_html = theme_prefix + str(soup)
        
        # Extract plain text for preview
        plain_text = soup.get_text(separator='\n', strip=True)
        
        return {
            'html': formatted_html,
            'plain_text': plain_text,
            'images': downloaded_images
        }
    
    except Exception as e:
        st.error(f"Error occurred while scraping the content: {e}")
        return None

def main():
    """
    Main Streamlit application
    """
    # Set page config
    st.set_page_config(page_title="Web Content Scraper", page_icon=":mag:", layout="wide")
    
    # Theme selector
    theme = st.sidebar.radio("Seleccionar Tema:", ["Oscuro", "Claro"])
    
    # Apply selected theme
    apply_theme(theme)
    
    st.title("Web Content Scraper")
    
    # Get the URL from the user
    url_input = st.text_input("Enter the URL of the web page:", "")
    
    # Option to choose display mode
    display_mode = st.radio("Display Mode:", 
                             ["Full HTML", "Plain Text", "Side-by-Side"])
    
    # Slider for maximum images (1-40)
    max_images = st.slider("Maximum number of images to download", 1, 40, 10)
    
    if st.button("Scrape Content"):
        if url_input:
            # Scrape the content
            scraped_content = scrape_web_content(url_input, max_images, theme)
            
            if scraped_content:
                st.success("Content successfully scraped!")
                
                # Display content based on selected mode
                if display_mode == "Full HTML":
                    # Display full HTML with preserved formatting
                    st.markdown("### Formatted Web Content")
                    st.components.v1.html(scraped_content['html'], height=600, scrolling=True)
                
                elif display_mode == "Plain Text":
                    # Display plain text
                    st.markdown("### Plain Text Content")
                    st.text_area("Scraped Text:", scraped_content['plain_text'], height=400)
                
                else:  # Side-by-Side
                    # Split the screen to show HTML and plain text
                    col1, col2 = st.columns(2)
                    
                    with col1:
                        st.markdown("### Formatted HTML")
                        st.components.v1.html(scraped_content['html'], height=600, scrolling=True)
                    
                    with col2:
                        st.markdown("### Plain Text")
                        st.text_area("Scraped Text:", scraped_content['plain_text'], height=600)
                
                # Display images
                if scraped_content['images']:
                    st.subheader(f"Downloaded Images ({len(scraped_content['images'])} of {max_images})")
                    
                    # Create a grid of image columns
                    cols = st.columns(4)  # 4 columns for better layout with more images
                    for i, img_path in enumerate(scraped_content['images']):
                        with cols[i % 4]:
                            st.image(img_path, use_column_width=True)
                    
                    # Zip and download option for images
                    with open('downloaded_images.zip', 'wb') as zipf:
                        import zipfile
                        with zipfile.ZipFile(zipf, 'w') as zip_file:
                            for img_path in scraped_content['images']:
                                zip_file.write(img_path, os.path.basename(img_path))
                    
                    st.download_button(
                        label="Download All Images",
                        data=open('downloaded_images.zip', 'rb').read(),
                        file_name='downloaded_images.zip',
                        mime='application/zip'
                    )
            else:
                st.warning("Failed to scrape content from the URL.")
        else:
            st.warning("Please enter a valid URL.")

if __name__ == "__main__":
    main()