Skip to content

Instantly share code, notes, and snippets.

@geobabbler
Created March 26, 2024 11:46
Show Gist options
  • Save geobabbler/151c3d226f1a5db242750c0a5b94286a to your computer and use it in GitHub Desktop.
Save geobabbler/151c3d226f1a5db242750c0a5b94286a to your computer and use it in GitHub Desktop.
Simple script to dump Wordpress posts to individual PDF files.
import pdfkit
import requests
'''
The current theme will be applied to outputs, so it is recommended to switch to a simple theme before exporting.
'''
#Generate PDF from individual post URL
def url_to_pdf(url, output_filename):
try:
# Fetch HTML content from the URL
response = requests.get(url)
response.raise_for_status() # Raises an HTTPError if the response was an unsuccessful status code
# Convert HTML to PDF and save it
pdfkit.from_string(response.text, output_filename)
print(f"PDF successfully saved as {output_filename}")
except requests.exceptions.RequestException as e:
#print(f"Error fetching the URL: {e}")
pass
except Exception as e:
#print(f"Error converting HTML to PDF: {e}")
pass
#Get all post URLs via Wordpress API
def list_all_posts(website_url):
posts_list = []
api_url = f"{website_url}/wp-json/wp/v2/posts"
page = 1
while True:
# Fetch a page of posts
response = requests.get(api_url, params={'per_page': 100, 'page': page})
# If the response status code is not 200, break the loop
if response.status_code != 200:
#print(f"Finished or encountered an error. HTTP status code: {response.status_code}")
break
posts = response.json()
# If the page is empty, break the loop
if not posts:
break
# Print URLs and titles of posts
for post in posts:
posts_list.append(post['link'])
#print(post['link'])
page += 1
return posts_list
# Usage
website_url = "https://blog.yoursite.org"
pl = list_all_posts(website_url)
#use an integer to generate unique file names.
ord = 0
for p in pl:
outfile = "p" + str(ord) + ".pdf"
url_to_pdf(p, outfile)
ord += 1
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment