ben's code snippet

fetchPubmedAbstract.py

import requests
import os
import xml.etree.ElementTree as ET
import pyperclip
import argparse
import re
reLink = re.compile(r'https://www.ncbi.nlm.nih.gov/pubmed/(\d+)')
parser = argparse.ArgumentParser(
    "-i pmid -l pubmed link")
parser.add_argument('-i')
parser.add_argument('-l')
parser.add_argument('-p')
parser.add_argument('-verbose')
parser.add_argument('-paste')

args = parser.parse_args()
if args.i is not None:
    print(args.i)
    ids = args.i
elif args.p is not None:
    ids = re.search(reLink,pyperclip.paste()).group(1)
    if ids is None:
        raise Exception("link format is wrong")
elif args.l is not None:
    print(args.l)
    ids = re.search(reLink,args.l).group(1)
    if ids is None:
        raise Exception("link format is wrong")
else:
    ids = '30693853'

dbname = 'pubmed'

def xmlParse(strtxt):
    root = ET.fromstring(strtxt)
    rstDict = {}
    rstDict['pmid'] = root.find('./PubmedArticle/MedlineCitation/PMID').text
    rstDict['journal'] = root.find('./PubmedArticle/MedlineCitation/Article/Journal')
    rstDict['journal'] = {
        'volume': rstDict['journal'].find('./JournalIssue/Volume').text,
        'issue': (lambda iss:iss.text if iss is not None else "")(rstDict['journal'].find('./JournalIssue/Issue')),
        'pubyear': rstDict['journal'].find('./JournalIssue/PubDate').text,
        'title': rstDict['journal'].find('./Title').text,
        'abbrev': rstDict['journal'].find('./ISOAbbreviation').text,
    }
    rstDict['title'] = root.find('./PubmedArticle/MedlineCitation/Article/ArticleTitle').text
    rstDict['doi'] = [e for e in root.findall(
        './PubmedArticle/PubmedData/ArticleIdList/ArticleId') if e.get('IdType')=='doi'][0].text
    rstDict['abstract'] = root.find(
        './PubmedArticle/MedlineCitation/Article/Abstract')
    abstractLabels = [e.get('Label') for e in rstDict['abstract'].findall('AbstractText')]
    abstractText = [
        e.text for e in rstDict['abstract'].findall('AbstractText')]
    rstDict['abstract'] = dict(zip(abstractLabels,abstractText))
    rstDict['authors'] = root.find(
        './PubmedArticle/MedlineCitation/Article/AuthorList')
    authorsList = rstDict['authors'].findall('Author')
    rstDict['authors'] = ["{}, {}({})".format(
        e.find('LastName').text, 
        e.find('ForeName').text, 
        e.find('Initials').text) for e in authorsList]
    return rstDict


fetchedData = requests.get(
    f"""https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db={dbname}&id={ids}&rettype=abstract&retmode=XML
    """
)
# 残留代码，调试完成以后已经不从本地读取xml了
with open('out.xml', 'w', encoding='utf8') as xmlFile:
    xmlFile.write(fetchedData.text)
rstDict = xmlParse(fetchedData.text)
txt = """
title: {}
journal: {}, {}-{}, {}
author: {}, et al.
doi: {}
""".format(
    rstDict['title'],
    rstDict['journal']['title'], 
    rstDict['journal']['volume'],
    rstDict['journal']['issue'],
    rstDict['journal']['pubyear'],
    rstDict['authors'][0],
    rstDict['doi']
)
abstracts = "abstract:\n".join(["{}:\n{}".format(k, v)
                                for k, v in rstDict['abstract'].items()])
if args.verbose is not None:
    txt = txt+abstracts
pyperclip.copy(txt)
print(txt)