Hello everyone,
I’m currently working on an automation process that would greatly help me with translating and rewriting product descriptions on my website.
My product descriptions are originally written in Czech, and I need to translate them into English while preserving the original HTML formatting—meaning the tags should remain intact, and only the text content should be translated.
Here’s my current approach:
- I start by loading the HTML content from my Google Sheets.
- Using a text parser, I isolate the HTML tags, enclosing each tag within a single bundle.
- For some reason, when I didnt use the Array aggregator, the next module would consume a ton of operations for no reason (at least to my understanding). Therefore, Ive added this aggregator. Other than helping with keeping single operations for each HTML descriptions, it does the same thing like Text parser and just keeps the values in single bundles.
- I use another text parser to extract only the content of the description.
- In the aggregator module, I combine the text with a “|” separator, preparing it for bulk translation.
- I then translate the aggregated text into English.
- I split the translated text back into individual bundles, using the “|” separator to match the original structure.
Where I’m Stuck:
I can’t figure out how to merge the translated text back with the original HTML tags to reconstruct the formatted HTML. Although I can link the Text Parser [21] and Aggregator [18] modules, the module [45] remains inaccessible for this final step.
Has anyone encountered a similar issue? How did you manage to effectively reassemble the HTML with the translated content intact?
I would appreciate any insights or suggestions!
Thank you so much!