mirror of
https://gitlab.dit.htwk-leipzig.de/fsr-im/tools/flatscraper.git
synced 2025-07-16 03:28:48 +02:00
feat: add BGL scraper and integrate into main scraping process; update image scraping logic
This commit is contained in:
15
main.py
15
main.py
@ -5,6 +5,7 @@ import src.wogetra.scraper as wogetra_scraper
|
||||
import src.lwb.scraper as lwb_scraper
|
||||
import src.discord.webhook as localwebhook
|
||||
import src.lipsia.lipsia as lipsia_scraper
|
||||
import src.bgl.bgl as bgl_scraper
|
||||
|
||||
# URL of the website to scrape
|
||||
TARGET_URL = "https://www.wogetra.de/immobilien-vermarktungsart/miete/"
|
||||
@ -26,12 +27,14 @@ def main():
|
||||
while True:
|
||||
current_time = time.strftime("%H:%M:%S", time.localtime())
|
||||
print("Scraping properties at " + current_time)
|
||||
print("Scraping properties from Wogetra...")
|
||||
properties = wogetra_scraper.scrape_wogetra()
|
||||
print("Scraping properties from LWB...")
|
||||
properties += lwb_scraper.scrape_easysquare()
|
||||
print("Scraping properties from Lipsia...")
|
||||
properties += lipsia_scraper.scrape_lipsia()
|
||||
# print("Scraping properties from Wogetra...")
|
||||
# properties = wogetra_scraper.scrape_wogetra()
|
||||
# print("Scraping properties from LWB...")
|
||||
# properties += lwb_scraper.scrape_easysquare()
|
||||
# print("Scraping properties from Lipsia...")
|
||||
# properties += lipsia_scraper.scrape_lipsia()
|
||||
print("Scraping properties from BGL...")
|
||||
properties = bgl_scraper.fetch_all_properties()
|
||||
|
||||
for prop in properties:
|
||||
if prop["id"] not in known_properties:
|
||||
|
Reference in New Issue
Block a user