Downloading full records from Entrez

Question

I can't get the data on the E. coli genome from NCBI.For this purpose I used two documentations for obtaining data http://biopython.org/DIST/docs/tutorial/Tutorial.html#sec149 http://biopython.org/DIST/docs/tutorial/Tutorial.html#sec37

So I've written a code:

from Bio import Entrez
from Bio import SeqIO

Entrez.email = "may mail"

organism_id = "NC_000913"
handle = Entrez.efetch(db="nucleotide", id=organism_id, rettype="gbwithparts", retmode="text")
record = SeqIO.read(handle, "genbank")
handle.close()
genome_length = len(record.seq)

But, I'm receiving a strange error. For example:

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/urllib/request.py:1348, in AbstractHTTPHandler.do_open(self, http_class, req, **http_conn_args)
   1347 try:
-> 1348     h.request(req.get_method(), req.selector, req.data, headers,
   1349               encode_chunked=req.has_header('Transfer-encoding'))
   1350 except OSError as err: # timeout error

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py:1282, in HTTPConnection.request(self, method, url, body, headers, encode_chunked)
   1281 """Send a complete request to the server."""
-> 1282 self._send_request(method, url, body, headers, encode_chunked)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py:1328, in HTTPConnection._send_request(self, method, url, body, headers, encode_chunked)
   1327     body = _encode(body, 'body')
-> 1328 self.endheaders(body, encode_chunked=encode_chunked)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py:1277, in HTTPConnection.endheaders(self, message_body, encode_chunked)
   1276     raise CannotSendHeader()
-> 1277 self._send_output(message_body, encode_chunked=encode_chunked)

File /Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/http/client.py:1037, in HTTPConnection._send_output(self, message_body, encode_chunked)
   1036 del self._buffer[:]
-> 1037 self.send(msg)
   1039 if message_body is not None:
   1040 
...
-> 1351         raise URLError(err)
   1352     r = h.getresponse()
   1353 except:

URLError: 
Output is truncated. View as a scrollable element or open in a text editor. Adjust cell output settings...

And I don't how I can manage with this problem? Could you help me please? Thanks in advance.

Answer 1

try this

# Increase the data rate limit
%config ZMQInteractiveShell.iopub_data_rate_limit=100000000

from Bio import Entrez

# Provide your email to the Entrez API
Entrez.email = "[email protected]"

def download_entrez_record(organism_id, rettype="gbwithparts", retmode="text"):
    """Downloads a full Entrez record using the specified ID and parameters.

    Args:
        organism_id: NCBI database ID of the record to download.
        rettype: Entrez return type (e.g., "gbwithparts").
        retmode: Entrez return mode (e.g., "text").

    Returns:
        The downloaded record as a string, or None if an error occurs.
    """
    try:
        print("Connecting to NCBI...")
        handle = Entrez.efetch(db="nucleotide", id=organism_id, rettype=rettype, retmode=retmode)
        print("Downloading...")
        record = handle.read()
        handle.close()
        return record
    except Exception as e:
        print(f"Error downloading record: {e}")
        return None

# Example: Download E. coli genome record
organism_id = "NC_000913"
record = download_entrez_record(organism_id)

if record:
    # Process the downloaded record (display a portion)
    print(record[:500])  # Display the first 500 characters
else:
    print("Failed to download record.")



#if u want u can save also with below command 
# Example: Download E. coli genome record and save to a file

if record:
    # Save the downloaded record to a file
    output_file_path = "e_coli_genome.gb"
    with open(output_file_path, "w") as file:
        file.write(record)
    print(f"Downloaded record saved to {output_file_path}")
else:
    print("Failed to download record.")