Spaces:
Running
Running
Marcepelaez
commited on
Commit
•
1bf2dc7
1
Parent(s):
38f7ded
app
Browse files
app.py
CHANGED
@@ -5,105 +5,130 @@ import re
|
|
5 |
import os
|
6 |
from urllib.parse import urljoin
|
7 |
|
8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
|
10 |
def main():
|
11 |
"""
|
12 |
Main Streamlit application
|
13 |
"""
|
14 |
-
# Set page config
|
15 |
st.set_page_config(page_title="Web Content Scraper", page_icon=":mag:", layout="wide")
|
16 |
-
|
17 |
-
# Theme selector
|
18 |
theme = st.sidebar.radio("Seleccionar Tema:", ["Oscuro", "Claro"])
|
19 |
-
|
20 |
-
# Apply selected theme
|
21 |
apply_theme(theme)
|
22 |
-
|
23 |
st.title("Web Content Scraper")
|
24 |
-
|
25 |
-
# Get the URL from the user
|
26 |
url_input = st.text_input("Enter the URL of the web page:", "")
|
27 |
-
|
28 |
-
# Option to choose display mode
|
29 |
-
display_mode = st.radio("Display Mode:",
|
30 |
-
["Full HTML", "Plain Text", "Side-by-Side"])
|
31 |
-
|
32 |
-
# Slider for maximum images (1-40)
|
33 |
max_images = st.slider("Maximum number of images to download", 1, 40, 10)
|
34 |
|
35 |
if st.button("Scrape Content"):
|
36 |
if url_input:
|
37 |
-
# Scrape the content
|
38 |
scraped_content = scrape_web_content(url_input, max_images, theme)
|
39 |
-
|
40 |
if scraped_content:
|
41 |
st.success("Content successfully scraped!")
|
42 |
-
|
43 |
-
# Display content based on selected mode
|
44 |
-
if display_mode == "Full HTML":
|
45 |
-
# Display full HTML with preserved formatting
|
46 |
-
st.markdown("### Formatted Web Content")
|
47 |
-
st.components.v1.html(scraped_content['html'], height=600, scrolling=True)
|
48 |
-
|
49 |
-
elif display_mode == "Plain Text":
|
50 |
-
# Display plain text
|
51 |
-
st.markdown("### Plain Text Content")
|
52 |
-
# Text area to show scraped content
|
53 |
-
text_area = st.text_area("Scraped Text:", scraped_content['plain_text'], height=400)
|
54 |
-
# Add a button to copy all text
|
55 |
-
st.download_button(
|
56 |
-
label="Copy All Text",
|
57 |
-
data=scraped_content['plain_text'],
|
58 |
-
file_name="scraped_text.txt",
|
59 |
-
mime="text/plain",
|
60 |
-
help="Click to copy all extracted text"
|
61 |
-
)
|
62 |
-
|
63 |
-
else: # Side-by-Side
|
64 |
-
# Split the screen to show HTML and plain text
|
65 |
-
col1, col2 = st.columns(2)
|
66 |
-
|
67 |
-
with col1:
|
68 |
-
st.markdown("### Formatted HTML")
|
69 |
-
st.components.v1.html(scraped_content['html'], height=600, scrolling=True)
|
70 |
-
|
71 |
-
with col2:
|
72 |
-
st.markdown("### Plain Text")
|
73 |
-
text_area = st.text_area("Scraped Text:", scraped_content['plain_text'], height=600)
|
74 |
-
st.download_button(
|
75 |
-
label="Copy All Text",
|
76 |
-
data=scraped_content['plain_text'],
|
77 |
-
file_name="scraped_text.txt",
|
78 |
-
mime="text/plain",
|
79 |
-
help="Click to copy all extracted text"
|
80 |
-
)
|
81 |
-
|
82 |
-
# Display images
|
83 |
-
if scraped_content['images']:
|
84 |
-
st.subheader(f"Downloaded Images ({len(scraped_content['images'])} of {max_images})")
|
85 |
-
|
86 |
-
# Create a grid of image columns
|
87 |
-
cols = st.columns(4) # 4 columns for better layout with more images
|
88 |
-
for i, img_path in enumerate(scraped_content['images']):
|
89 |
-
with cols[i % 4]:
|
90 |
-
st.image(img_path, use_column_width=True)
|
91 |
-
|
92 |
-
# Zip and download option for images
|
93 |
-
with open('downloaded_images.zip', 'wb') as zipf:
|
94 |
-
import zipfile
|
95 |
-
with zipfile.ZipFile(zipf, 'w') as zip_file:
|
96 |
-
for img_path in scraped_content['images']:
|
97 |
-
zip_file.write(img_path, os.path.basename(img_path))
|
98 |
-
|
99 |
-
st.download_button(
|
100 |
-
label="Download All Images",
|
101 |
-
data=open('downloaded_images.zip', 'rb').read(),
|
102 |
-
file_name='downloaded_images.zip',
|
103 |
-
mime='application/zip'
|
104 |
-
)
|
105 |
-
else:
|
106 |
-
st.warning("Failed to scrape content from the URL.")
|
107 |
else:
|
108 |
st.warning("Please enter a valid URL.")
|
109 |
|
|
|
5 |
import os
|
6 |
from urllib.parse import urljoin
|
7 |
|
8 |
+
def apply_theme(theme):
|
9 |
+
"""
|
10 |
+
Apply custom CSS based on the selected theme
|
11 |
+
"""
|
12 |
+
if theme == "Claro":
|
13 |
+
st.markdown("""
|
14 |
+
<style>
|
15 |
+
body {
|
16 |
+
color: black;
|
17 |
+
background-color: white;
|
18 |
+
}
|
19 |
+
.stTextInput > div > div > input {
|
20 |
+
color: black;
|
21 |
+
background-color: white;
|
22 |
+
}
|
23 |
+
.stMarkdown {
|
24 |
+
color: black;
|
25 |
+
}
|
26 |
+
/* Light theme for HTML content */
|
27 |
+
.light-theme {
|
28 |
+
background-color: white !important;
|
29 |
+
color: black !important;
|
30 |
+
}
|
31 |
+
.light-theme a {
|
32 |
+
color: #0066cc !important;
|
33 |
+
}
|
34 |
+
.light-theme h1, .light-theme h2, .light-theme h3,
|
35 |
+
.light-theme h4, .light-theme h5, .light-theme h6 {
|
36 |
+
color: #333 !important;
|
37 |
+
}
|
38 |
+
</style>
|
39 |
+
""", unsafe_allow_html=True)
|
40 |
+
return """
|
41 |
+
<div style="background-color: white; color: black; padding: 20px;">
|
42 |
+
<style>
|
43 |
+
body { background-color: white !important; color: black !important; }
|
44 |
+
a { color: #0066cc; }
|
45 |
+
h1, h2, h3, h4, h5, h6 { color: #333; }
|
46 |
+
</style>
|
47 |
+
"""
|
48 |
+
else:
|
49 |
+
st.markdown("""
|
50 |
+
<style>
|
51 |
+
body {
|
52 |
+
color: white;
|
53 |
+
background-color: #0E1117;
|
54 |
+
}
|
55 |
+
.stTextInput > div > div > input {
|
56 |
+
color: white;
|
57 |
+
background-color: #262730;
|
58 |
+
}
|
59 |
+
.stMarkdown {
|
60 |
+
color: white;
|
61 |
+
}
|
62 |
+
</style>
|
63 |
+
""", unsafe_allow_html=True)
|
64 |
+
return ""
|
65 |
+
|
66 |
+
def scrape_web_content(url, max_images, theme):
|
67 |
+
"""
|
68 |
+
Scrape the web content while preserving its original formatting
|
69 |
+
"""
|
70 |
+
try:
|
71 |
+
response = requests.get(url)
|
72 |
+
response.raise_for_status()
|
73 |
+
|
74 |
+
soup = BeautifulSoup(response.content, 'html.parser')
|
75 |
+
os.makedirs('downloaded_images', exist_ok=True)
|
76 |
+
|
77 |
+
downloaded_images = []
|
78 |
+
img_tags = soup.find_all('img', src=True)
|
79 |
+
for i, img in enumerate(img_tags[:max_images], 1):
|
80 |
+
try:
|
81 |
+
img_url = img['src']
|
82 |
+
if not img_url.startswith(('http://', 'https://')):
|
83 |
+
img_url = urljoin(url, img_url)
|
84 |
+
|
85 |
+
img_response = requests.get(img_url)
|
86 |
+
img_response.raise_for_status()
|
87 |
+
|
88 |
+
filename = f'downloaded_images/image_{i}.{img_url.split(".")[-1].split("?")[0]}'
|
89 |
+
with open(filename, 'wb') as f:
|
90 |
+
f.write(img_response.content)
|
91 |
+
|
92 |
+
img['src'] = filename
|
93 |
+
downloaded_images.append(filename)
|
94 |
+
except Exception as img_error:
|
95 |
+
st.warning(f"Could not download image {i}: {img_error}")
|
96 |
+
|
97 |
+
for tag in soup(["script", "style", "meta", "link", "noscript"]):
|
98 |
+
tag.decompose()
|
99 |
+
|
100 |
+
theme_prefix = apply_theme(theme) if theme == "Claro" else ""
|
101 |
+
formatted_html = theme_prefix + str(soup)
|
102 |
+
plain_text = soup.get_text(separator='\n', strip=True)
|
103 |
+
|
104 |
+
return {
|
105 |
+
'html': formatted_html,
|
106 |
+
'plain_text': plain_text,
|
107 |
+
'images': downloaded_images
|
108 |
+
}
|
109 |
+
|
110 |
+
except Exception as e:
|
111 |
+
st.error(f"Error occurred while scraping the content: {e}")
|
112 |
+
return None
|
113 |
|
114 |
def main():
|
115 |
"""
|
116 |
Main Streamlit application
|
117 |
"""
|
|
|
118 |
st.set_page_config(page_title="Web Content Scraper", page_icon=":mag:", layout="wide")
|
|
|
|
|
119 |
theme = st.sidebar.radio("Seleccionar Tema:", ["Oscuro", "Claro"])
|
|
|
|
|
120 |
apply_theme(theme)
|
|
|
121 |
st.title("Web Content Scraper")
|
|
|
|
|
122 |
url_input = st.text_input("Enter the URL of the web page:", "")
|
123 |
+
display_mode = st.radio("Display Mode:", ["Full HTML", "Plain Text", "Side-by-Side"])
|
|
|
|
|
|
|
|
|
|
|
124 |
max_images = st.slider("Maximum number of images to download", 1, 40, 10)
|
125 |
|
126 |
if st.button("Scrape Content"):
|
127 |
if url_input:
|
|
|
128 |
scraped_content = scrape_web_content(url_input, max_images, theme)
|
|
|
129 |
if scraped_content:
|
130 |
st.success("Content successfully scraped!")
|
131 |
+
# Resto del código para mostrar contenido...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
132 |
else:
|
133 |
st.warning("Please enter a valid URL.")
|
134 |
|