Spaces:
Paused
Paused
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,118 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import gradio as gr
|
| 2 |
+
import requests
|
| 3 |
+
from bs4 import BeautifulSoup
|
| 4 |
+
import pdfkit
|
| 5 |
+
import os
|
| 6 |
+
import math
|
| 7 |
+
|
| 8 |
+
# Function to extract all links from a website
|
| 9 |
+
def extract_links(url):
|
| 10 |
+
try:
|
| 11 |
+
response = requests.get(url, headers={"User-Agent": "Mozilla/5.0"})
|
| 12 |
+
if response.status_code != 200:
|
| 13 |
+
return f"Error: Unable to fetch page (Status Code {response.status_code})", []
|
| 14 |
+
|
| 15 |
+
soup = BeautifulSoup(response.text, "html.parser")
|
| 16 |
+
base_url = "/".join(url.split("/")[:3]) # Extract base domain
|
| 17 |
+
|
| 18 |
+
links = []
|
| 19 |
+
for a_tag in soup.find_all("a", href=True):
|
| 20 |
+
href = a_tag["href"]
|
| 21 |
+
if not href.startswith("http"): # Convert relative links to absolute
|
| 22 |
+
href = base_url + href if href.startswith("/") else base_url + "/" + href
|
| 23 |
+
|
| 24 |
+
links.append(href)
|
| 25 |
+
|
| 26 |
+
links = list(set(links)) # Remove duplicates
|
| 27 |
+
if not links:
|
| 28 |
+
return "No links found on the website.", []
|
| 29 |
+
|
| 30 |
+
return f"✅ {len(links)} links found! Select which ones to convert into PDFs:", links
|
| 31 |
+
|
| 32 |
+
except Exception as e:
|
| 33 |
+
return f"Error: {str(e)}", []
|
| 34 |
+
|
| 35 |
+
# Function to clean unwanted content (like headers, footers, etc.)
|
| 36 |
+
def clean_content(soup):
|
| 37 |
+
# Remove common unwanted elements
|
| 38 |
+
for tag in soup.find_all(["header", "footer", "nav", "aside", "script", "style"]):
|
| 39 |
+
tag.decompose() # Remove the tag completely
|
| 40 |
+
|
| 41 |
+
# You can also remove specific classes or IDs if necessary, for example:
|
| 42 |
+
# for tag in soup.find_all(attrs={"class": "footer"}):
|
| 43 |
+
# tag.decompose()
|
| 44 |
+
|
| 45 |
+
# Get the cleaned text from the remaining content
|
| 46 |
+
return soup.get_text(separator="\n", strip=True)
|
| 47 |
+
|
| 48 |
+
# Function to scrape selected links and generate PDFs
|
| 49 |
+
def scrape_and_generate_pdfs(selected_links):
|
| 50 |
+
try:
|
| 51 |
+
if not selected_links:
|
| 52 |
+
return "No links selected.", None
|
| 53 |
+
|
| 54 |
+
pdf_files = []
|
| 55 |
+
batch_size = 4 # Each PDF contains up to 4 links
|
| 56 |
+
|
| 57 |
+
# Process selected links in batches of 4
|
| 58 |
+
for i in range(0, len(selected_links), batch_size):
|
| 59 |
+
batch_links = selected_links[i:i + batch_size]
|
| 60 |
+
all_text = ""
|
| 61 |
+
|
| 62 |
+
# Scrape text content from each selected link
|
| 63 |
+
for link in batch_links:
|
| 64 |
+
try:
|
| 65 |
+
response = requests.get(link, headers={"User-Agent": "Mozilla/5.0"})
|
| 66 |
+
if response.status_code == 200:
|
| 67 |
+
soup = BeautifulSoup(response.text, "html.parser")
|
| 68 |
+
page_text = clean_content(soup)
|
| 69 |
+
all_text += f"--- Content from: {link} ---\n\n" + page_text + "\n\n"
|
| 70 |
+
except:
|
| 71 |
+
all_text += f"Failed to fetch content from {link}\n\n"
|
| 72 |
+
|
| 73 |
+
if all_text:
|
| 74 |
+
pdf_filename = f"output_{(i//batch_size) + 1}.pdf"
|
| 75 |
+
|
| 76 |
+
# Save as temporary HTML file
|
| 77 |
+
html_path = f"temp_{i}.html"
|
| 78 |
+
with open(html_path, "w", encoding="utf-8") as f:
|
| 79 |
+
f.write(f"<html><body><pre>{all_text}</pre></body></html>")
|
| 80 |
+
|
| 81 |
+
# Convert HTML to PDF
|
| 82 |
+
pdfkit.from_file(html_path, pdf_filename)
|
| 83 |
+
os.remove(html_path)
|
| 84 |
+
|
| 85 |
+
pdf_files.append(pdf_filename)
|
| 86 |
+
|
| 87 |
+
return pdf_files # Return list of generated PDFs
|
| 88 |
+
|
| 89 |
+
except Exception as e:
|
| 90 |
+
return f"Error: {str(e)}", None
|
| 91 |
+
|
| 92 |
+
# Gradio UI with link selection
|
| 93 |
+
def show_links_and_generate_pdfs(url):
|
| 94 |
+
message, links = extract_links(url)
|
| 95 |
+
if not links:
|
| 96 |
+
return message, gr.update(choices=[], value=[])
|
| 97 |
+
|
| 98 |
+
return message, gr.update(choices=links, value=[])
|
| 99 |
+
|
| 100 |
+
iface = gr.Blocks()
|
| 101 |
+
|
| 102 |
+
with iface:
|
| 103 |
+
gr.Markdown("### 🌐 Web Scraper & PDF Generator")
|
| 104 |
+
gr.Markdown("Enter a website URL to extract internal links, then select which links to convert into PDFs (4 links per PDF).")
|
| 105 |
+
|
| 106 |
+
url_input = gr.Textbox(label="Enter Website URL")
|
| 107 |
+
extract_btn = gr.Button("Extract Links")
|
| 108 |
+
|
| 109 |
+
message_output = gr.Markdown("")
|
| 110 |
+
link_selector = gr.CheckboxGroup([], label="Select Links to Convert", interactive=True)
|
| 111 |
+
generate_btn = gr.Button("Generate PDFs")
|
| 112 |
+
|
| 113 |
+
pdf_output = gr.File(label="Download Generated PDFs")
|
| 114 |
+
|
| 115 |
+
extract_btn.click(show_links_and_generate_pdfs, inputs=url_input, outputs=[message_output, link_selector])
|
| 116 |
+
generate_btn.click(scrape_and_generate_pdfs, inputs=link_selector, outputs=pdf_output)
|
| 117 |
+
|
| 118 |
+
iface.launch()
|