[Text URL extract] Extract text and URL from copied web-page link. #espanso #python

URL_extract.yml

  - trigger: :test
    replace: '{{Clipb}} {{Output}}'  
    vars:
      - name: Clipb
        type: clipboard
      - name: Output
        type: script
        params:
          args:
            - python
            - -c
            - |
              import sys
              from PyQt5.QtWidgets import QApplication
              from bs4 import BeautifulSoup

              def extract_urls_from_html(html_content):
                  soup = BeautifulSoup(html_content, 'html.parser')
                  anchors = soup.find_all('a')
                  urls = [a['href'] for a in anchors if a.get('href')]
                  return urls

              def main():
                  app = QApplication(sys.argv)

                  clipboard = app.clipboard()
                  mime_data = clipboard.mimeData()
                  
                  if mime_data.hasHtml():
                      html_content = mime_data.html()
                      urls = extract_urls_from_html(html_content)
                      
                      if urls:
                          for url in urls:
                              print(url)
                      else:
                          print("No URLs found in clipboard content.")
                  else:
                      print("Clipboard does not contain HTML content.")

                  # You don't need to run the main loop of the QApplication, so we can exit here.
                  sys.exit()

              if __name__ == "__main__":
                  main()