update
This commit is contained in:
parent
555769e89a
commit
483a62010c
File diff suppressed because one or more lines are too long
@ -43,6 +43,7 @@ fi
|
||||
# Check if the container image exists
|
||||
if [[ ! "$(docker images -q ${IMAGE_NAME})" ]]; then
|
||||
echo "Building the Docker container..."
|
||||
cp ${OUT_JSON_PATH} src/locations.json
|
||||
docker build -t ${IMAGE_NAME} --build-arg http_proxy=$http_proxy --build-arg https_proxy=$https_proxy .
|
||||
check_ret "Docker build failed!"
|
||||
fi
|
||||
@ -66,4 +67,4 @@ fi
|
||||
|
||||
|
||||
# Run container
|
||||
docker run --name ${CONTAINER_NAME} -p ${PORT_MAPPING} -v ${OUT_JSON_PATH}:/usr/src/app/src/locations.json ${IMAGE_NAME}
|
||||
docker run --name ${CONTAINER_NAME} -p ${PORT_MAPPING} ${IMAGE_NAME}
|
196660
scrape/out.json
196660
scrape/out.json
File diff suppressed because one or more lines are too long
Binary file not shown.
@ -2,7 +2,7 @@ import geopy
|
||||
# from funda_scraper import FundaScraper
|
||||
from funda_scraper.scrape import FundaScraper
|
||||
import datetime, os, pickle, json, tqdm, numpy
|
||||
import osrm
|
||||
import osrm, random
|
||||
|
||||
OSRM_HOST = 'https://osrm.herreweb.nl'
|
||||
NOMINATIM_HOST = 'geocode.herreweb.nl'
|
||||
@ -47,18 +47,26 @@ def generate_json(houses):
|
||||
# address_l = f"{houses.zip.get(i)}".split(" ")
|
||||
address = f"{houses.address.get(i)} {houses.city.get(i)}"
|
||||
|
||||
if "lindenlaan" in address.lower():
|
||||
pass
|
||||
|
||||
res = nomi_c.geocode(address)
|
||||
|
||||
# res = gmaps.geocode(f"{address}")
|
||||
if res == None:
|
||||
print(f"{i}:Failed to get any loction for: {address}")
|
||||
continue
|
||||
address = f"{houses.city.get(i)}"
|
||||
res = nomi_c.geocode(address)
|
||||
if res == None:
|
||||
print(f"{i}:Failed to get any loction for: {address}")
|
||||
continue
|
||||
|
||||
destination_location = res.point
|
||||
destination_location = [destination_location.longitude, destination_location.latitude]
|
||||
|
||||
if destination_location in saved_locations:
|
||||
print(f"double for: {address}")
|
||||
destination_location[0] = destination_location[0] + random.randint(1, 10) / 10000
|
||||
destination_location[1] = destination_location[1] + random.randint(1, 10) / 10000
|
||||
saved_locations.append(destination_location)
|
||||
|
||||
out_dict['name'] = f"{address}_{count}" # Fix for duplicate names in dictionary.
|
||||
|
Loading…
Reference in New Issue
Block a user