Export public scribehow scribe as word file

scribehow-scrap-export.py

import requests
import json
from bs4 import BeautifulSoup
from docx import Document
from docx.shared import Inches,RGBColor,Pt
from requests.adapters import HTTPAdapter
from requests.packages.urllib3.util.retry import Retry
from fpdf import FPDF
import tkinter as tk
from tkinter import simpledialog
import sys

def get_user_input():
    root = tk.Tk()
    root.withdraw()
    url = simpledialog.askstring("Input", "Enter the URL of the ScribeHow page:")
    choice = simpledialog.askstring("Input", "Choose file format (word/pdf):")
    return url, choice.lower().strip()

def print_progress(message):
    print(message)
    sys.stdout.flush()

def scrape_scribehow(url):
    content_data = {}
    
    headers = {"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"}
    session = requests.Session()
    retries = Retry(total=5, backoff_factor=1, status_forcelist=[500, 502, 503, 504])
    session.mount('https://', HTTPAdapter(max_retries=retries))
    
    try:
        print_progress("Fetching webpage...")
        response = session.get(url, headers=headers, timeout=10)
        response.raise_for_status()
    except requests.exceptions.RequestException as e:
        return {"error": f"Failed to fetch the webpage: {e}"}
    
    soup = BeautifulSoup(response.text, 'html.parser')
    
    heading = soup.find('h1')
    if heading:
        content_data['title'] = heading.text.strip()
    
    desc = soup.find('span')
    if desc:
        content_data['description'] = desc.text.strip()
    
    main_div = soup.find('div', class_='flex w-full flex-col items-center')
    if main_div:
        content_data['steps'] = []
        for div in main_div.find_all('div', recursive=False):
            step = div.find('div', class_="bg-opacity-0")
            if step:
                step_no_elem = step.find('span', class_="text-lg")
                step_text_elem = step.find('span', class_="action-description")
                if step_no_elem and step_text_elem:
                    step_no = step_no_elem.text.strip()
                    step_text = step_text_elem.text.strip()
                    image = div.find('img')
                    image_src = image['src'] if image else None
                    content_data['steps'].append({
                        'step': f"Step {step_no}: {step_text}",
                        'img': image_src
                    })
    
    return content_data

def save_to_word(data, filename='scraped_data.docx'):
    print_progress("Saving data to Word file...")
    doc = Document()
    
    if 'title' in data:
        title = doc.add_heading(data['title'], level=1)
        title.runs[0].font.size = Pt(24)
        title.runs[0].font.underline = True
        title.runs[0].font.color.rgb = RGBColor(0, 0, 0)

    
    if 'description' in data:
        doc.add_paragraph(data['description'])

    
    if 'steps' in data:
        headers = {"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"}
        session = requests.Session()
        retries = Retry(total=5, backoff_factor=1, status_forcelist=[500, 502, 503, 504])
        session.mount('https://', HTTPAdapter(max_retries=retries))
        
        for step in data['steps']:
            stepp = doc.add_heading(step['step'], level=2)
            stepp.runs[0].font.color.rgb = RGBColor(0, 0, 0)

            if step['img']:
                try:
                    response = session.get(step['img'], headers=headers, timeout=10)
                    response.raise_for_status()
                    image_path = "temp_image.jpg"
                    with open(image_path, 'wb') as img_file:
                        img_file.write(response.content)
                    doc.add_picture(image_path, width=Inches(6))
                except requests.exceptions.RequestException as e:
                    print_progress(f"Failed to download image: {e}")
    
    doc.save(filename)
    print_progress("Word file saved successfully.")

def save_to_pdf(data, filename='scraped_data.pdf'):
    print_progress("Saving data to PDF file...")
    pdf = FPDF()
    pdf.set_auto_page_break(auto=True, margin=15)
    pdf.add_page()
    pdf.set_font("Arial", style='B', size=16)
    
    if 'title' in data:
        pdf.cell(200, 10, data['title'], ln=True, align='C')
    
    pdf.ln(10)
    pdf.set_font("Arial", size=12)
    
    if 'description' in data:
        pdf.multi_cell(0, 10, data['description'])
    
    if 'steps' in data:
        headers = {"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"}
        session = requests.Session()
        retries = Retry(total=5, backoff_factor=1, status_forcelist=[500, 502, 503, 504])
        session.mount('https://', HTTPAdapter(max_retries=retries))
        
        for step in data['steps']:
            pdf.ln(5)
            pdf.set_font("Arial", style='B', size=12)
            pdf.cell(0, 10, step['step'], ln=True)
            pdf.set_font("Arial", size=12)
            if step['img']:
                try:
                    response = session.get(step['img'], headers=headers, timeout=10)
                    response.raise_for_status()
                    image_path = "temp_image.jpg"
                    with open(image_path, 'wb') as img_file:
                        img_file.write(response.content)
                    pdf.image(image_path, x=10, w=100)
                except requests.exceptions.RequestException as e:
                    print_progress(f"Failed to download image: {e}")
    
    pdf.output(filename)
    print_progress("PDF file saved successfully.")

# User interaction
url, choice = get_user_input()
print_progress("Scraping...")
data = scrape_scribehow(url)
if "error" not in data:
    if choice == "word":
        save_to_word(data)
    elif choice == "pdf":
        save_to_pdf(data)
    else:
        print_progress("Invalid choice. Please choose either 'word' or 'pdf'.")
else:
    print_progress(data["error"])