from Bio import Entrez
from Bio import SeqIO
import os

file_name = "proteome1.faa"
net_handle = Entrez.efetch(db="protein", id="trichoderma_harzianum", rettype="gp", retmode="text")
out_handle = open(file_name, "w")
out_handle.write(net_handle.read())
out_handle.close()
net_handle.close()
print("Saved")


for seq_record in SeqIO.parse("proteome1.faa", "genbank"):
    print(seq_record.id)
    print(repr(seq_record.seq))
    print(len(seq_record))

from Bio import Entrez

Entrez.email = 'user@example.org' # Put your email here

def get_tax_id(species):
    species = species.replace('_', '+').strip()
    search = Entrez.esearch(term=species, db='taxonomy', retmode='xml')
    record = Entrez.read(search)
    return record['IdList'][0]

if __name__ == '__main__':
    organisms = ['lophodermium_seditiosum', 'trichoderma_harzianum']
    taxids = [get_tax_id(organism) for organism in organisms]
    print(taxids)

def get_proteomes(taxid):
    query = 'txid{}[Organism:exp] '.format(taxid)
    handle = Entrez.esearch(db='protein', term=query)
    result = Entrez.read(handle)
    if int(result['Count']) <= 2000:
        ids = ','.join(result['IdList'])
        proteomes = Entrez.efetch(db='protein', id=ids, rettype='fasta').read()
        return proteomes
    else:
        raise RuntimeError('Too many results!')

if __name__ == '__main__':
    print(get_proteomes('128023'))

>ADI44294.1 actin, partial [Lophodermium seditiosum]
CKAGFAGDDAPRAVFPSIVGRPRHHGIMIGMGQKDS

>ADI44293.1 actin, partial [Lophodermium seditiosum]
CKAGFAGDDAPRAVFPSIVGRPRHHGIMIGMGQKDS