fetch_img.py

import os
import requests
from bs4 import BeautifulSoup
from urllib.parse import urljoin
import urllib.request
import pandas as pd
import warnings
from requests.packages.urllib3.exceptions import InsecureRequestWarning

warnings.simplefilter('ignore', InsecureRequestWarning)

REQ_FMT =  {
    "url": 'https://api.ebird.org/v2/ref/taxonomy/ebird',
    "params" : {
        'species': 'CHANGE THIS TO SPECIES CODE'
    }
}
bird_df = pd.read_csv("ebird_taxonomy_v2023.csv")


def scientific_to_species_code(scientific_name: str):
    scode = bird_df[bird_df['SCI_NAME'].str.contains(scientific_name, na=False)]['SPECIES_CODE']
    if not scode.array:
        return []
    else:
        return scode.array[0]

# Gets taxonomical info on bird. (Is not actually used)
def get_bird_info(species_code : str):
    
    REQ_FMT['params'] = {"species": species_code}
    response = requests.get(REQ_FMT["url"], headers=REQ_FMT["headers"], params=REQ_FMT['params'], verify=False)
    data = response.content
    return data

def download_images(url):
    
    # Fetch the HTML content of the webpage
    response = requests.get(url, verify=False)
    if response.status_code != 200:
        print(f"Failed to retrieve the page. Status code: {response.status_code}")
        return

    # Parse the HTML content
    soup = BeautifulSoup(response.content, 'html.parser')

    # Find all image tags
    img_tags = soup.find_all('img')

    # Extract image URLs
    img_urls = [urljoin(url, img['src']) for img in img_tags if 'src' in img.attrs]
    img_urls = [el for el in img_urls if "api" in el and "asset" in el]

    return img_urls

if __name__ == '__main__':
    bird_tax = pd.read_csv("ebird_taxonomy_v2023.csv")
    scode = scientific_to_species_code("Melanocharis striativentris")
    print(get_bird_info(scode))
    download_images(f"https://ebird.org/species/{scode}")