fetch_pubmed_notes.py

fetch_pubmed.py

import requests
import json

db = 'pmc'
domain = 'https://www.ncbi.nlm.nih.gov/entrez/eutils'
nresults = 4
query = "depression"
retmode='json'

# standard query
queryLinkSearch = f'{domain}/esearch.fcgi?db={db}&retmax={nresults}&retmode={retmode}&term={query}'
response = requests.get(queryLinkSearch)
pubmedJson = response.json()

results = []

for paperId in pubmedJson["esearchresult"]["idlist"]:
    # metadata query
    # queryLinkSummary = f'{domain}/esummary.fcgi?db={db}&id={paperId}&retmode={retmode}'
    # print(queryLinkSummary)
    fetch_abstract=f'https://eutils.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db={db}&id={paperId}&retmode=xml&rettype=abstract'
    print(fetch_abstract)
    # results.append({'paperId': paperId, 'metadata': requests.get(queryLinkSummary).json()})
    # results.append({'paperId': paperId, 'abstract': requests.get(fetch_abstract).json()})
    # for pubmed abstract
    # my_dict=xmltodict.parse(response.content)
    # my_dict['PubmedArticleSet']['PubmedArticle']['MedlineCitation']['Article']['Abstract']['AbstractText']
    # print(each_line.keys()) dict_keys(['@Label', '@NlmCategory', '#text'])
    # for each_line in my_dict['PubmedArticleSet']['PubmedArticle']['MedlineCitation']['Article']['Abstract']['AbstractText']:
    #   print(each_line['@Label'])
    #   print(each_line['#text'])
    # PMC abstract
    # my_pmc_dict['pmc-articleset']['article']['front']['article-meta']['abstract'] or (my_pmc_dict['pmc-articleset']['article']['front']['article-meta']['abstract']['sec'])
    # my_pmc_dict['pmc-articleset']['article']['body']
    # >>> my_pmc_dict['pmc-articleset']['article']['body']['sec'][0].keys()
    # dict_keys(['@id', 'title', 'p', 'sec'])
    # publication date 
    # my_pmc_dict['pmc-articleset']['article']['front']['article-meta']['pub-date'][0]
    # my_pmc_dict['pmc-articleset']['article']['front']['article-meta']['pub-date'][0]['day'] 
    # my_pmc_dict['pmc-articleset']['article']['front']['article-meta']['pub-date'][0]['month']
    # my_pmc_dict['pmc-articleset']['article']['front']['article-meta']['pub-date'][0]['year']
    # get all text paragraphs 
    # for each_paragraph in my_pmc_dict['pmc-articleset']['article']['body']['sec']:
    #    if 
    #    each_paragraph['p'][0]['#text']


    
    


# resultsSorted = sorted(results, key=lambda x: x["metadata"]["result"][x["paperId"]]["fulljournalname"])

# with open('resultsSorted.json', 'w') as f:
#     json.dump(results, f)

# handle = Entrez.esearch(db="pubmed", term="obesity", retmax=5)
# results = Entrez.read(handle)                                                   
# print(results["IdList"])
# def print_abstract(pmid):
    # handle = efetch(db='pubmed', id=pmid, retmode='text', rettype='abstract')
    # print(handle.read()