1
#by m36-intj: makes bibtex entries from a list of pubmed article pmids, uses pmc article link, if available
2
#list format is
3
#%comment
4
#12345678
5
#23415251
6
#....
7
 
8
 
9
from pymed import PubMed
10
pubmed = PubMed()
11
from Bio import Entrez
12
from Bio import Medline
13
 
14
def test():
15
    output_file = open('/storage/emulated/0/Download/python/bibtex.txt', "w")
16
    pmids= open('/storage/emulated/0/Download/python/pmids', "r")
17
    
18
    for pmid in pmids:
19
    	if pmid.startswith("%"):
20
    		continue
21
    	pmid = pmid.strip()
22
    	results = pubmed.query(f"{pmid}[PMID]", max_results=1)
23
    	article = next(results, None)
24
    	if article:
25
    	   print(f"PMID: {pmid}")
26
    	   print(f"Title: {article.title}")
27
    	   raw_id = str(article.pubmed_id)
28
    	   clean_pmid = raw_id.split()[0]  # Takes first entry if multiple exist
29
    	   
30
    	   first_author = article.authors[0]  # Get first author dict
31
    	   first_author_name = f"{first_author.get('firstname', '')} {first_author.get('lastname', '')}".strip()
32
    	   print(f"First Author: {first_author_name}")
33
    	   
34
    	   url = get_pmc(clean_pmid)
35
    	   print(f"URL: {url}")
36
    	   # Extract year (handles string or datetime.date formats)
37
    	   pub_date = article.publication_date
38
    	   if hasattr(pub_date, 'year'):  # If it's a datetime.date object
39
    	   	year = pub_date.year
40
    	   else:  # If it's a string (e.g., "2023-05-15")
41
    	   	year = pub_date.split('-')[0]  # Takes the first part (YYYY)
42
    	   print(f"Publication Year: {year}")
43
    	   # Example usage:
44
    	   abbrev = get_journal_abbreviation(clean_pmid)  # Replace with your PMID
45
    	   print(f"ISO Abbreviation: {abbrev}")  # e.g., "Nat. Biotechnol."
46
    	   bibtex_entry(output_file,first_author_name, url, article.title, abbrev, year)
47
    	   print("")
48
    	else:
49
    		print(f"\nPMID {pmid} not found.")
50
    
51
# Example:
52
def get_pmc(pmid):
53
    Entrez.email = "[email protected]"  # Required by NCBI
54
    """Fetch PMCID given a PMID using elink."""
55
    try:
56
        handle = Entrez.elink(dbfrom="pubmed", db="pmc", id=pmid)
57
        record = Entrez.read(handle)
58
        #time.sleep(0.34)  # Respect NCBI rate limits
59
        
60
        # Check if PMC links exist
61
        if record and "LinkSetDb" in record[0] and record[0]["LinkSetDb"]:
62
            pmcid = record[0]["LinkSetDb"][0]["Link"][0]["Id"]
63
            return f"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC{pmcid}/"
64
    except Exception as e:
65
        print(f"Error fetching PMCID for PMID {pmid}: {str(e)}")
66
    #if no PMC article is available return base pmid link to article
67
    return  f"https://pubmed.ncbi.nlm.nih.gov/{pmid}"
68
    
69
 
70
def get_journal_abbreviation(pmid):
71
    Entrez.email = "[email protected]"  # Required by NCBI
72
    try:
73
        # Step 1: Fetch record in Medline format (more reliable than XML)
74
        handle = Entrez.efetch(db="pubmed", id=pmid, rettype="medline", retmode="text")
75
        record = Medline.read(handle)
76
        
77
        # Step 2: Check all possible journal name fields
78
        journal_fields = ['TA', 'JT', 'SO']
79
        for field in journal_fields:
80
            if field in record:
81
                return record[field]
82
        
83
        # Step 3: Ultimate fallback
84
        return record.get('SO', 'Journal name unavailable')
85
    
86
    except Exception as e:
87
        print(f"Error processing PMID {pmid}: {str(e)}")
88
        return "Journal name unavailable"
89
        
90
#@Article{hallmarks_aging,
91
 # Author         = "Carlos Lopez-Otin and others",
92
#  Title          = "\href{https://pubmed.ncbi.nlm.nih.gov/36599349/}{Hallmarks of aging: An expanding universe}",
93
  #Journal        = "Cell Metabolism",
94
 # Year           = 2023,
95
#}
96
def bibtex_entry(text_file, author, url, title, journal, year):
97
		print(f"@Article {{key,",file=text_file)
98
		print(f"Author = \"{author} and others\",",file=text_file)
99
		print(f"Title = \"\\href{{{url}}}{{{title}}}\",",file=text_file)
100
		print(f"Journal = \"{journal}.\",",file=text_file)
101
		print(f"Year = \"{year}\",\n}}\n",file=text_file)
102
		return
103
 
104
 
105
test()