from core.LSH.lsh import SQLDiskLSH
from core.main import set_credentials, initialize, add

# set your instagram credentials to scrape instagram profiles
set_credentials("instagram", "your-instagram-username", "your-instagram-password")

index = SQLDiskLSH()

# urls of profiles that you want to scrape
urls = [
    "https://www.instagram.com/veritasium/?hl=en",
    "https://www.instagram.com/thephysicsgirl/?hl=en",
]

# the add function will download every single image from the url and stores the face embeddings. If you run the add function on the same url again, then it will pickup where it left off (scrape any new images that were added after a while)
for url in urls:
    add(index, url)

from core.mappers import default_sql_mapper
from core.main import initialize, query, get_faces

index = SQLDiskLSH()

faces = []
for data in get_faces("some_image_that_has_a_face.jpg"):
    faces.append(data)

face_num, face_loc, face_embedding = faces[0]

# query function returns a list of matches where each match has information on the ID of face stored in database and the euclidean distance of the given face and the matched face (low distance = better match)
matches = query(index, default_sql_mapper, face_embedding, 20)

print(matches)

# you can use the IDs to query the FaceData database and get the link to the original post