Apr-18-2018, 10:38 AM
import csv
from collections import defaultdict
from Bio import Entrez
from Bio import Medline
import requests
import datetime
import pandas as pd
##please install before using this script: pip install biopython
def search(query): ## fetch omids of author
Entrez.email = '[email protected]'
handle = Entrez.esearch(db='pubmed',
sort='relevance',
retmax='1000',
retmode='xml',
term=query)
results = Entrez.read(handle)
return results
def fetch_details(id_list): ## extract medline record of PMids
ids = ','.join(id_list)
Entrez.email = '[email protected]'
handle = Entrez.efetch(db='pubmed',
retmode='text',
rettype='medline',
id=ids)
results = Medline.parse(handle)
return results
def read_grant_file(grant): #Read grant file and use author name as search field
rows=[]
rows1=[]
output=defaultdict(list)
output1={}
s=''
with open(grant, "r", encoding="ISO-8859-1") as File:
csvreader = csv.reader(File)
fields = next(csvreader)
included_cols = [21]
include=[0,21]
for row in csvreader:
content = list(row[i].rstrip() for i in included_cols)
content1 = list(row[i].rstrip() for i in include)
rows.append(content)
rows1.append(content1)
for x in rows:
t=''.join(x)
s=s+t
#print(s)
#print("Total no. of rows: %d"%(csvreader.line_num))
#print('Field names are:' + ', '.join(field for field in fields))
for cols in rows1:
cols[1]=cols[1].rstrip(";")
cols[1]=cols[1].split(";")
if len(cols[1])==1:
output1[cols[0]]=cols[1]
else:
j=0
for i in cols[1]:
output1[cols[0]+"_"+str(j)]=i
j+=1
print(output1)
return s
def distinct(names): ## unique names
import ordered_set
from ordered_set import OrderedSet
return list(OrderedSet(names))
if __name__ == '__main__':
authors=read_grant_file("C:\\Users\\ragarwa3\\Desktop\\pubmed\\Funding_Report_2017_1.csv")
authors=authors.rstrip(";")
print("Number of distinct authors:"+str(len(distinct(authors.split(";")))))
Ofile = open("C:\\Users\\ragarwa3\\Desktop\\pubmed\\Funding_Report_2017_PI_mapping_file011.txt", "w+", encoding="UTF-8")
for name in authors.split(";"):
qry=name.rstrip()+'[AU]'
results = search(qry)
id_list = results['IdList']
records = fetch_details(id_list)
for record in records:
ti=record.get('TI') ##title
dt=record.get('DP') ##Date of publication
jt=record.get('JT') ## journal title
pmid=record.get('PMID') ## pmid
grant=record.get('GR') ## grant sources
otext=str(pmid)+"\t"+str(ti)+"\t"+str(dt)+"\t"+str(jt)+"\t"+str(grant)
au = record.get('AU', '?')
authors = []
for a in au:
if a not in authors:
authors.append(a)
otext=otext +"\t"+'{0}'.format(', '.join(authors))+"\n"
Ofile.write(otext)
Traceback (most recent call last):File "C:\Users\ragarwa3\Desktop\pubmed\nih_grant.py", line 67, in <module>
records = fetch_details(id_list)
File "C:\Users\ragarwa3\Desktop\pubmed\nih_grant.py", line 26, in fetch_details
id=ids)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\site-packages\Bio\Entrez\__init__.py", line 180, in efetch
return _open(cgi, variables, post=post)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\site-packages\Bio\Entrez\__init__.py", line 528, in _open
handle = _urlopen(cgi)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 223, in urlopen
return opener.open(url, data, timeout)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 526, in open
response = self._open(req, data)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 544, in _open
'_open', req)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 504, in _call_chain
result = func(*args)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 1361, in https_open
context=self._context, check_hostname=self._check_hostname)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\urllib\request.py", line 1321, in do_open
r = h.getresponse()
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\http\client.py", line 1331, in getresponse
response.begin()
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\http\client.py", line 297, in begin
version, status, reason = self._read_status()
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\http\pyclient.", line 258, in _read_status
line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\socket.py", line 586, in readinto
return self._sock.recv_into(b)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\ssl.py", line 1009, in recv_into
return self.read(nbytes, buffer)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\ssl.py", line 871, in read
return self._sslobj.read(len, buffer)
File "C:\Users\ragarwa3\AppData\Local\Programs\Python\Python36\lib\ssl.py", line 631, in read
v = self._sslobj.read(len, buffer)
ssl.SSLError: [SSL: WRONG_VERSION_NUMBER] wrong version number (_ssl.c:2217)