Bioinformatics Python Uniprot Protein Sequence Fasta Downloader with Obsolete Check and Custom Range

all_proteins = []


"""
# Use only if your data is in (ID Position Sequence) Format
text_file = open("peptide_data/allfasta.txt", "r")

for i in text_file:
    temp = i.split(' ')
    all_proteins.append(temp[0])
text_file.close()

all_proteins = list(sorted(set(all_proteins)))
print(all_proteins)
"""

# If you use want to this, keep the code above commented vice versa 
all_proteins = [
'P62821',
'Q9R1P0',
'P63101',
'Q8CAQ8',
'Q9ET01'
]


obsolete_list = []

# query the website and return the html to the variable ‘page’
import urllib.request

# Change the range here for custom range of protein query instead of all proteins
for i in range(0, len(all_proteins)):
    query_page = 'https://www.uniprot.org/uniprot/' + all_proteins[i] + '.fasta'
    print(query_page)

    try:
        with urllib.request.urlopen(query_page) as url:
            page = url.read()

            fasta_string = page.decode("utf8")
            print(fasta_string)
            with open("fastas/mouse/" + all_proteins[i] + ".fasta", "a") as p:
                p.write(fasta_string)
            if len(fasta_string) == 0:
                obsolete_list.append(all_proteins[i])
    except:
        obsolete_list.append(all_proteins[i])
        pass

    print("Now at: ", i)

print(list(set(obsolete_list)))