Commit graph

21 commits

Author SHA1 Message Date
Kadir
2c2adcfa7c improving OCR 2025-03-30 23:41:52 +01:00
Kadir
e0e7853c8c updating districts of relevance to me 2025-02-14 21:35:44 +00:00
Kadir
dbf72e42e3 removing districts which are far away from the default crawl 2024-09-23 01:43:20 +01:00
Kadir
4dfbcc64c1 floorplan rec: fix regex rule + filter out extreme values 2024-08-25 12:11:55 +02:00
Kadir
2e94bda7fa refac 2024-08-25 09:50:41 +02:00
Kadir
f98cd02696 adding better exception messages and interrupt free crawling 2024-05-06 18:54:55 +01:00
Kadir
874fed3e8f format and committing notebook 2024-04-05 11:38:55 +01:00
Kadir
b16fee0648 changing to 500 listings per query 2024-04-01 20:28:15 +02:00
Kadir
a7a4f88a39 sort districts 2024-03-30 19:24:35 +01:00
Kadir
40285245d5 remove debug print statements 2024-03-30 18:35:32 +01:00
Kadir
ec86b572b3 adding districts and location identifier to search 2024-03-30 18:31:49 +01:00
Kadir
4c40462bb8 adding property type 2024-03-25 20:58:35 +00:00
Kadir
d777558b34 ruff format 2024-03-25 20:48:48 +00:00
Kadir
47f7b2b672 Adding initial walking time and identifier to the information 2024-03-25 20:47:31 +00:00
Kadir
4dea766a12 fixing floorplan detection and adding recalculation method 2024-03-18 00:56:39 +00:00
Kadir
d4f87bed76 add routing and util to the right places 2024-03-13 16:22:53 +00:00
Kadir
a9b8d4d630 adding musthave and lastXdays 2024-03-13 16:21:54 +00:00
Kadir
d108bf11ee adding tesseract OCR for floorplan detection 2024-03-10 22:32:34 +00:00
Kadir
508aa02812 Real crawling scripts and floorplan detection
1. get all listings
2. get all detail jsons
3. get all images
4. get all floorplans
5. detecting floorplans

Also updating dependencies for huggingface etc.
2024-03-10 18:49:39 +00:00
Kadir
46bb641026 adding floorplans, detail json, refactored the folders 2024-03-07 22:02:09 +00:00
Kadir
e2f7998ee9 merging the visual query answering with the crawler. Monorepo go! 2024-03-01 16:42:48 +01:00