Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Refactor using JSON, and multiple smaller additions/changes/improvements #56

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
2 changes: 2 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
.vscode/launch.json
data
230 changes: 188 additions & 42 deletions funda_scraper/config/config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -9,52 +9,198 @@ keep_cols:
# - term_days
selling_data:
- url
- house_id
- city
- house_type
- building_type
- price
- price_m2
- room
- bedroom
- bathroom
- price_m2grond
- status
- acceptance
- listed_since
- house_type
- building_type
- year_built
- building_roofing
- building_details
- volume
- living_area
- property_area
- balcony_size
- other_interior_area
- other_exterior_area
- exteriors
- rooms
- bathroom
- bedroom
- toilets
- stories
- layout
- energy_label
- zip
- insulation
- heating
- heatedwater
- heatingCV
- heatingAge
- solarpanels
- heatpump
- lowenergy
- street
- address
- year_built
- house_age
# - date_list
# - ym_list
# - year_list
- zip_code
- city
- descrip
- photo
- ownership
- cadastralarea
- location
- garden
- garden_size
- garden_width
- garden_depth
- gardenorientation
- balcony
- parking
- parkingownproperty
- enclosedparking
- neighborhood_name
- latitude
- longitude
- monument
- monumentstatus
- DIYhome
- leasehold
- NeighourhoodId
- photos
- neighbourhood_price_m2
- neighbourhood_families
- sound
- ppm25
- no2
- log_id
css_selector:
url: none
price: ".object-header__price"
address: ".object-header__title"
descrip: ".object-description-body"
listed_since: ".fd-align-items-center:nth-child(6) span"
zip_code: ".object-header__subtitle"
size: ".object-kenmerken-list:nth-child(8) .fd-align-items-center:nth-child(5) span"
year: ".fd-align-items-center~ .fd-align-items-center .fd-m-right-xs"
living_area: ".object-kenmerken-list:nth-child(8) .fd-align-items-center:nth-child(2) span"
kind_of_house: ".object-kenmerken-list:nth-child(5) .fd-align-items-center:nth-child(2) span"
building_type: ".object-kenmerken-list:nth-child(5) .fd-align-items-center:nth-child(4) span"
num_of_rooms: ".object-kenmerken-list:nth-child(11) .fd-align-items-center:nth-child(2)"
num_of_bathrooms: ".object-kenmerken-list:nth-child(11) .fd-align-items-center:nth-child(4)"
layout: ".object-kenmerken-list:nth-child(11)"
energy_label: ".energielabel"
insulation: ".object-kenmerken-list:nth-child(14) .fd-align-items-center:nth-child(4)"
heating: ".object-kenmerken-list:nth-child(14) .fd-align-items-center:nth-child(6)"
ownership: ".object-kenmerken-list:nth-child(17) .fd-align-items-center:nth-child(4)"
exteriors: ".object-kenmerken-list:nth-child(19)"
parking: ".object-kenmerken-list:nth-child(24)"
neighborhood_name: ".fd-display-inline--bp-m"
date_list: "dd:nth-child(2)"
date_sold: "dd:nth-child(4)"
term: "dd:nth-child(6)"
price_sold: ".object-header__price--historic"
last_ask_price: ".object-kenmerken-list:nth-child(2) .fd-align-items-center:nth-child(2)"
last_ask_price_m2: ".object-kenmerken-list__asking-price"
photo: ".media-viewer-overview__section-list-item--photo img[data-lazy]"
url: "ContentUrl"
price:
- "Id"
-
- "overdracht-huurprijs"
- "overdracht-vraagprijs"
price_m2:
- "Id"
- "overdracht-vraagprijsperm2"
status:
- "Id"
- "overdracht-status"
acceptance:
- "Label"
- "Aanvaarding"
listed_since:
- "Label"
-
- "Aangeboden sinds"
house_type:
- "Id"
- "bouw-soortobject"
building_type:
- "Id"
- "bouw-soortbouw"
year_built:
- "Label"
-
- "Bouwjaar"
- "Bouwperiode"
building_roofing:
- "Id"
- "bouw-dak"
building_details:
- "Id"
- "bouw-bijzonderheden"
volume:
- "Id"
- "afmetingen-inhoud"
living_area: "woonoppervlakte"
property_area: "PerceelOppervlakteSubTitle"
balcony_size:
- "Id"
- "afmetingen-gebruiksoppervlakte-gebouwgebondenbuitenruimte"
other_interior_area:
- "Id"
- "afmetingen-gebruiksoppervlakte-overigeinpandigeruimte"
other_exterior_area:
- "Label"
- "Externe bergruimte"
exteriors:
- "Id"
- "afmetingen-gebruiksoppervlakte-externebergruimte"
num_of_rooms: "aantalkamers"
num_of_bathrooms:
- "Id"
- "indeling-totalbathroom"
num_of_bedrooms: "NumberOfBedrooms"
stories:
- "Id"
- "indeling-totalstories"
layout:
- "Id"
- "indeling-generalfacilities"
energy_label: "EnergyLabel"
insulation:
- "Id"
- "energie-isolatie"
heating:
- "Id"
- "energie-verwarming"
heatedwater:
- "Id"
- "energie-warmwater"
heatingCV:
- "Id"
- "energie-cv"
heatingAge: "cvketel"
solarpanels: "zonnepanelen"
heatpump: "warmtepomp"
lowenergy: "energiezuinig"
street: "AddressTitle"
address: "AddressSubTitle"
zip_code: "postcode"
city: "plaats"
descrip: "Aanbiedingstekst"
ownership:
- "Id"
- "cadastral-ownershipsituation"
cadastralarea:
- "Id"
- "cadastral-area"
location:
- "Id"
- "buitenruimte-ligging"
garden:
- "Id"
- "buitenruimte-tuin"
garden_size:
- "Id"
- "buitenruimte-hoofdtuin"
gardenorientation:
- "Id"
- "buitenruimte-liggingtuin"
balcony:
- "Id"
- "buitenruimte-balkonterras"
parking:
- "Label"
- "Soort parkeergelegenheid"
parkingownproperty: "parkeergelegenheidopeigenterrein"
enclosedparking: "parkeergelegenheidopeigenterrein"
neighborhood_name: "BuurtName"
latitude: "Latitude"
longitude: "Longitude"
monument: "rijksmonument"
monumentstatus: "monumentalestatus"
DIYhome: "kluswoning"
leasehold: "erfpacht"
term:
price_sold:
date_sold:
NeighourhoodId: "BuurtIdentifier"
photos:
neighbourhood_price_m2:
neighbourhood_families:
sound:
ppm25:
no2:
Loading