Searching an apartment in Germany can be a frustrating task. Not any longer though, as Fredy will take over and will only notify you once new listings have been found that match your requirements.
Fredy scrapes multiple services (Immonet, Immowelt etc.) and send new listings to you once they become available. The list of available services can easily be extended. For your convenience, Fredy has a UI to help you configure your search jobs.
If Fredy finds matching results, it will send them to you via Slack, Email, Telegram etc. (More adapters can be configured.) As Fredy stores the listings it has found, new results will not be sent to you twice (and as a side-effect, Fredy can show some statistics). Furthermore, Fredy checks duplicates per scraping so that the same listings are not being sent twice or more when posted on various platforms (which happens more often than one might think).
If you like my work, consider becoming a sponsor. I'm not expecting anybody to pay for Fredy or any other Open Source Project I'm maintaining, however keep in mind, I'm doing all of this in my spare time :) Thanks.
Fredy is supported by JetBrains under Open Source Support Program
- Make sure to use Node.js 20 or above
- Run the following commands:
yarn (or npm install)
yarn run prod
yarn run start
Fredy will start with the default port, set to 9998. You can access Fredy by opening your browser at http://localhost:9998. The default login is admin, both for username and password. You should change the password as soon as possible when you plan to run Fredy on a server.
There are 3 important parts in Fredy, that you need to understand to leverage the full power of Fredy.
Fredy supports multiple services. Immonet, Immowelt and Ebay are just a few examples. Those services are called providers within Fredy. When creating a new job, you can choose one or more providers. A provider contains the URL that points to the search results for the respective service. If you go to immonet.de and search for something, the displayed URL in the browser is what the provider needs to do its magic. It is important that you order the search results by date, so that Fredy always picks the latest results first!
Fredy supports multiple adapters, such as Slack, SendGrid, Telegram etc. A search job can have as many adapters as supported by Fredy. Each adapter needs different configuration values, which you have to provide when using them. A adapter dictactes how the frontend renders by telling the frontend what information it needs in order to send listings to the user.
A Job wraps adapters and providers. Fredy runs the configured jobs in a specific interval (can be configured in /conf/config.json).
To create your first job, click on the button "Create New Job" on the job table. The job creation dialog should be self-explanatory, however there is one important thing. When configuring providers, before copying the URL from your browser, make sure that you have sorted the results by date to make sure Fredy always picks the latest results first.
As an administrator, you can create, edit and remove users from Fredy. Be careful, each job is connected to the user that has created the job. If you remove the user, their jobs will also be removed.
To run Fredy in development mode, you need to run the backend & frontend separately. Start the backend with:
yarn run startFor the frontend, run:
yarn run devYou should now be able to access Fredy from your browser. Check your Terminal to see what port the frontend is running on.
To run the tests, run
yarn run test
I have added experimental support for Immoscout, Immonet and NeubauKompass. They all are somewhat special, because they have decided to secure their service from bots using Re-Capture. Finding a way around this is barely possible. For Fredy to be able to bypass this check, I'm using a service called ScrapingAnt. The trick is to use a headless browser, rotating proxies and (once successfully validated) to re-send the cookies each time.
To be able to use Immoscout / Immonet, you need to create an account at ScrapingAnt. Configure the API key in the "General Settings" tab (visible when logged in as administrator). The rest will be handled by Fredy. Keep in mind, the support is experimental. There might be bugs and you might not always pass the re-capture check, but most of the time it works rather well :)
If you need more than the 1000 API calls allowed per month, I'd suggest opting for a paid account... ScrapingAnt loves OpenSource, therefore they have decided to give all Fredy users a 10% discount by using the code FREDY10 (Disclaimer: I do not earn any money for recommending their service).
Thanks to all the people who already contributed!
See Contributing
Use the Dockerfile in this repository to build an image.
Example: docker build -t fredy/fredy /path/to/your/Dockerfile
Or use docker-compose:
Example docker-compose build
Or use the container that will be built automatically.
docker pull ghcr.io/orangecoding/fredy:master
Put your config.json into a path of your choice, such as /path/to/your/conf/.
Example: docker create --name fredy -v /path/to/your/conf/:/conf -p 9998:9998 fredy/fredy
You can browse the logs with docker logs fredy -f.