Question

我目前正在开展一个项目，我需要从PubMed下载几千个引文。我目前正在使用BioPython并编写了这段代码：

from Bio import Entrez
from Bio import Medline
from pandas import *
from sys import argv
import os

Entrez.email = "email"
df = read_csv("/Users/.../Desktop/sr_dataset/adhd/excluded/adhdExcluded.csv")
i=0
withoutMesh = 0
withoutMeshID = ""
withoutAbstract = 0
withoutAbstractID = ""
path = '/Users/.../Desktop/sr_dataset/adhd/excluded'

for index, row in df.iterrows():
    print (row.id)
    handle = Entrez.efetch(db="pubmed",rettype="medline",retmode="text", id=str(row.id))
    records = Medline.parse(handle)
    for record in records:
        try:
            abstract = str(record["AB"])
        except:
            abstract = "none"
            withoutAbstract = withoutAbstract +1
            withoutAbstractID = withoutAbstractID + str(row.id) + "\n"
        try:
            title = str(record["TI"])
        except:
            title = "none"
        try:
            mesh = str(record["MH"])
        except:
            mesh = "none"
            withoutMesh = withoutMesh +1
            withoutMeshID = withoutMeshID + str(row.id) + "\n"
    filename= str(row.id) + '.txt'
    filename = os.path.join(path, filename)
    file = open(filename, "w")
    output = "title: "+str(title) + "\n\n" + "abstract: "+str(abstract) + "\n\n" + "mesh: "+str(mesh) + "\n\n"
    file.write(output)
    file.close()
    print (i)
    i=i+1

filename = os.path.join(path, "overview.txt")
file = open(filename, "w")
output = "Without MeSH terms:" + str(withoutMesh) + "\n" + "ID's: "+str(withoutMeshID) + "\n\n" + "Without abstract: "+str(withoutAbstract) + "\n" + "ID's: "+str(withoutAbstractID)
file.write(output)
file.close()

代码适用于表格中的前几百行，但随后停止执行，我收到的错误是：

Traceback (most recent call last):
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 1254, in do_open
    h.request(req.get_method(), req.selector, req.data, headers)
  File "/Users/.../anaconda/lib/python3.5/http/client.py", line 1106, in request
    self._send_request(method, url, body, headers)
  File "/Users/.../anaconda/lib/python3.5/http/client.py", line 1151, in _send_request
    self.endheaders(body)
  File "/Users/.../anaconda/lib/python3.5/http/client.py", line 1102, in endheaders
    self._send_output(message_body)
  File "/Users/.../anaconda/lib/python3.5/http/client.py", line 934, in _send_output
    self.send(msg)
  File "/Users/.../anaconda/lib/python3.5/http/client.py", line 877, in send
    self.connect()
  File "/Users/.../anaconda/lib/python3.5/http/client.py", line 1260, in connect
    server_hostname=server_hostname)
  File "/Users/.../anaconda/lib/python3.5/ssl.py", line 377, in wrap_socket
    _context=self)
  File "/Users/.../anaconda/lib/python3.5/ssl.py", line 752, in __init__
    self.do_handshake()
  File "/Users/.../anaconda/lib/python3.5/ssl.py", line 988, in do_handshake
    self._sslobj.do_handshake()
  File "/Users/.../anaconda/lib/python3.5/ssl.py", line 633, in do_handshake
    self._sslobj.do_handshake()
ConnectionResetError: [Errno 54] Connection reset by peer

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/.../Desktop/sr_dataset/ace_inhibitor/excluded/pumbedMedline.py", line 18, in <module>
    handle = Entrez.efetch(db="pubmed",rettype="medline",retmode="text", id=str(row.id))
  File "/Users/.../anaconda/lib/python3.5/site-packages/biopython-1.68-py3.5-macosx-10.6-x86_64.egg/Bio/Entrez/__init__.py", line 180, in efetch
    return _open(cgi, variables, post=post)
  File "/Users/.../anaconda/lib/python3.5/site-packages/biopython-1.68-py3.5-macosx-10.6-x86_64.egg/Bio/Entrez/__init__.py", line 524, in _open
    handle = _urlopen(cgi)
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 163, in urlopen
    return opener.open(url, data, timeout)
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 466, in open
    response = self._open(req, data)
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 484, in _open
    '_open', req)
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 444, in _call_chain
    result = func(*args)
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 1297, in https_open
    context=self._context, check_hostname=self._check_hostname)
  File "/Users/.../anaconda/lib/python3.5/urllib/request.py", line 1256, in do_open
    raise URLError(err)
urllib.error.URLError: <urlopen error [Errno 54] Connection reset by peer>

以下是CSV文件的前几列：

Answer 1

Biopython确实遵循＆＃34;每秒最多三个查询规则＆＃34;为避免滥用NCBI服务器，但您已经错过了我们的教程http://biopython.org/DIST/docs/tutorial/Tutorial.html中关于指南的第一个要点：

＆＃34;对于任何超过100个请求的系列，请在周末或美国高峰时段之外。这取决于你服从。＆＃34;

也就是说，有时您会从Entrez获得间歇性错误，并建议使用try / except块来处理此问题。本教程中有一个例子。

使用BioPython时Urllib错误

1 个答案: