from pubmed_mapper import Article


article = Article.parse_pmid('32329900')

# PubMed ID
print(article.pmid)  # 32329900

# ids
print(article.ids)  # [pubmed: 32329900, doi: 10.1111/jgs.16467]
print(article.ids[1].id_type)  # doi
print(article.ids[1].id_value)  # 10.1111/jgs.16467

# title
print(article.title)  # Associations of Coffee...

# abstract
print(article.abstract)  # <p><strong>Background: </strong>Coffee and tea...

# keywords
print(article.keywords)  # ['aging', 'coffee; diet; longevity', 'tea']

# MeSH headings
print(article.mesh_headings)  # ['Aged', 'Body Mass Index', '...']

# authors
print(article.authors)  # [hadyab AH Aladdin H, Manson JE JoAnn E, ...]
print(article.authors[0].last_name)  # Shadyab
print(article.authors[0].forename)  # Aladdin H
print(article.authors[0].initials)  # AH
print(article.authors[0].affiliation)  # Department of Family...

# journal
print(article.journal)  # Journal of the American Geriatrics Society
print(article.journal.issn)  # 1532-5415
print(article.journal.issn_type)  # Electronic
print(article.journal.title)  # Journal of the American Geriatrics Society
print(article.journal.abbr)  # J Am Geriatr Soc

# volume
print(article.volume)  # 68

# issue
print(article.issue)  # 9

# references
print(article.references)  # [n. 2013;129:643-659....]
print(article.references[0].citation)  # Lotfield E, Freedman ND...
print(article.references[0].ids)  # []

# pubdate
print(article.pubdate)  # 2020-09-01

from lxml import etree
from pubmed_mapper import Article


infile = 'xxx.xml'
with open(infile) as fp:
    root = etree.parse(fp)


articles = []
for pubmed_article_element in root.xpath('/PubmedArticleSet/PubmedArticle'):
    article =  Article.parse_element(pubmed_article_element)
    articles.append(article)