def parse_medline_grant_id(path):
"""Parse grant id from Medline XML file
Parameters
----------
path: str
The path to the XML with the information
Return
------
grant_id_list: list
A list of dictionaries contains the grants in a given path. Each dictionary
has the keys of 'pmid', 'grant_id', 'grant_acronym', 'country', and 'agency'
>>> pubmed_parser.parse_medline_grant_id('data/pubmed20n0014.xml.gz')
[{
'pmid': '399300',
'grant_id': 'HL17731',
'grant_acronym': 'HL',
'country': 'United States',
'agency': 'NHLBI NIH HHS'
}, ...
]
"""
tree = read_xml(path)
medline_citations = tree.findall("//MedlineCitationSet/MedlineCitation")
if len(medline_citations) == 0:
medline_citations = tree.findall("//PubmedArticle")
grant_id_list = list(map(parse_grant_id, medline_citations))
grant_id_list = list(chain(*grant_id_list)) # flatten list
return grant_id_list
def get_medline_tree(path, to_string=False, encoding='utf-8'):
"""Initial parsing of the xml file tree. Finds all the articles.
Parameters
----------
path: str
The path
to_string: bool
If True, return a list of string elements
encoding: str
How to encode the elements if `to_string=True`
Return
------
medline_citations: list
A list of lxml.etree._Element, each being a pubmed article
"""
tree = read_xml(path)
medline_citations = tree.findall("//MedlineCitationSet/MedlineCitation")
if len(medline_citations) == 0:
medline_citations = tree.findall("//PubmedArticle")
if to_string:
return [lxml.etree.tostring(elem, encoding=encoding) for elem in medline_citations]
return medline_citations
def parse_medline_xml(path, year_info_only=True, nlm_category=False):
"""Parse XML file from Medline XML format available at
ftp://ftp.nlm.nih.gov/nlmdata/.medleasebaseline/gz/
Parameters
----------
path: str
The path
year_info_only: bool
if True, this tool will only attempt to extract year information from PubDate.
if False, an attempt will be made to harvest all available PubDate information.
If only year and month information is available, this will yield a date of
the form 'YYYY-MM'. If year, month and day information is available,
a date of the form 'YYYY-MM-DD' will be returned.
NOTE: the resolution of PubDate information in the Medline(R) database varies
between articles.
Defaults to True.
nlm_category: bool, default False
if True, this will parse structured abstract where each section if original Label
if False, this will parse structured abstract where each section will be assigned to
NLM category of each sections
Returns
-------
article_list: list
Dictionary containing information about articles in NLM format (see
`parse_article_info`). Articles that have been deleted will be
added with no information other than the field `delete` being `True`
"""
tree = read_xml(path)
medline_citations = tree.findall('//MedlineCitationSet/MedlineCitation')
if len(medline_citations) == 0:
medline_citations = tree.findall('//MedlineCitation')
article_list = list(
map(lambda m: parse_article_info(m, year_info_only, nlm_category),
medline_citations))
delete_citations = tree.findall('//DeleteCitation/PMID')
dict_delete = \
[
{'title': None,
'abstract': None,
'journal': None,
'author': None,
'affiliation': None,
'pubdate': None,
'pmid': p.text,
'other_id': None,
'pmc': None,
'mesh_terms': None,
'keywords': None,
'delete': True,
'medline_ta': None,
'nlm_unique_id': None,
'issn_linking': None,
'country': None
} for p in delete_citations
]
article_list.extend(dict_delete)
return article_list
def parse_medline_xml(path, year_info_only=True):
"""Parse XML file from Medline XML format available at
ftp://ftp.nlm.nih.gov/nlmdata/.medleasebaseline/gz/
Parameters
----------
path: str
The path
year_info_only: bool
if True, this tool will only attempt to extract year information from PubDate.
if False, an attempt will be made to harvest all available PubDate information.
If only year and month information is available, this will yield a date of
the form 'YYYY-MM'. If year, month and day information is available,
a date of the form 'YYYY-MM-DD' will be returned.
NOTE: the resolution of PubDate information in the Medline(R) database varies
between articles.
Defaults to True.
Returns
-------
article_list: list
Dictionary containing information about articles in NLM format (see
`parse_article_info`). Articles that have been deleted will be
added with no information other than the field `delete` being `True`
"""
tree = read_xml(path)
medline_citations = tree.findall('//MedlineCitationSet/MedlineCitation')
if len(medline_citations) == 0:
medline_citations = tree.findall('//MedlineCitation')
article_list = list(map(lambda m: parse_article_info(m, year_info_only), medline_citations))
delete_citations = tree.findall('//DeleteCitation/PMID')
dict_delete = \
[
{'title': None,
'abstract': None,
'journal': None,
'author': None,
'affiliation': None,
'pubdate': None,
'pmid': p.text,
'other_id': None,
'pmc': None,
'mesh_terms': None,
'keywords': None,
'delete': True
} for p in delete_citations
]
article_list.extend(dict_delete)
return article_list
def parse_medline_grant_id(path):
"""Parse grant id from Medline XML file
Parameters
----------
path: str
The path to the XML with the information
Returns
-------
grant_id_list: list
List of dictionaries for all files in `path`. Each dictionary
will have the information returned by `parse_grant_id`
"""
tree = read_xml(path)
medline_citations = tree.xpath('//MedlineCitationSet/MedlineCitation')
grant_id_list = list(map(parse_grant_id, medline_citations))
grant_id_list = list(chain(*grant_id_list)) # flatten list
return grant_id_list
def parse_medline_grant_id(path):
"""Parse grant id from Medline XML file
Parameters
----------
path: str
The path to the XML with the information
Return
------
grant_id_list: list
A list of dictionaries contains the grants in a given path. Each dictionary
has the keys of 'pmid', 'grant_id', 'grant_acronym', 'country', and 'agency'
"""
tree = read_xml(path)
medline_citations = tree.findall("//MedlineCitationSet/MedlineCitation")
if len(medline_citations) == 0:
medline_citations = tree.findall("//PubmedArticle")
grant_id_list = list(map(parse_grant_id, medline_citations))
grant_id_list = list(chain(*grant_id_list)) # flatten list
return grant_id_list
def parse_medline_grant_id(path):
"""Parse grant id from Medline XML file
Parameters
----------
path: str
The path to the XML with the information
Returns
-------
grant_id_list: list
List of dictionaries for all files in `path`. Each dictionary
will have the information returned by `parse_grant_id`
"""
tree = read_xml(path)
medline_citations = tree.findall('//MedlineCitationSet/MedlineCitation')
if len(medline_citations) == 0:
medline_citations = tree.findall('//MedlineCitation')
grant_id_list = list(map(parse_grant_id, medline_citations))
grant_id_list = list(chain(*grant_id_list)) # flatten list
return grant_id_list
def parse_medline_xml(
path,
year_info_only=True,
nlm_category=False,
author_list=False,
reference_list=False,
):
"""Parse XML file from Medline XML format available at
ftp://ftp.nlm.nih.gov/nlmdata/.medleasebaseline/gz/
Parameters
----------
path: str
The path
year_info_only: bool
if True, this tool will only attempt to extract year information from PubDate.
if False, an attempt will be made to harvest all available PubDate information.
If only year and month information is available, this will yield a date of
the form 'YYYY-MM'. If year, month and day information is available,
a date of the form 'YYYY-MM-DD' will be returned.
NOTE: the resolution of PubDate information in the Medline(R) database varies
between articles.
default: True
nlm_category: bool
if True, this will parse structured abstract where each section if original Label
if False, this will parse structured abstract where each section will be assigned to
NLM category of each sections
default: False
author_list: bool
if True, return parsed author output as a list of authors
if False, return parsed author output as a string of authors concatenated with ``;``
default: False
reference_list: bool
if True, parse reference list as an output
if False, return string of PMIDs concatenated with ;
default: False
Return
------
article_list: list
A list of dictionary containing information about articles in NLM format (see
`parse_article_info`). Articles that have been deleted will be
added with no information other than the field `delete` being `True`
"""
tree = read_xml(path)
medline_citations = tree.findall("//MedlineCitationSet/MedlineCitation")
if len(medline_citations) == 0:
medline_citations = tree.findall("//PubmedArticle")
article_list = list(
map(
lambda m: parse_article_info(m, year_info_only, nlm_category,
author_list, reference_list),
medline_citations,
))
delete_citations = tree.findall("//DeleteCitation/PMID")
dict_delete = [{
"title": np.nan,
"abstract": np.nan,
"journal": np.nan,
"authors": np.nan,
"affiliations": np.nan,
"pubdate": np.nan,
"pmid": p.text.strip(),
"doi": np.nan,
"other_id": np.nan,
"pmc": np.nan,
"mesh_terms": np.nan,
"keywords": np.nan,
"publication_types": np.nan,
"chemical_list": np.nan,
"delete": True,
"medline_ta": np.nan,
"nlm_unique_id": np.nan,
"issn_linking": np.nan,
"country": np.nan,
"references": np.nan,
} for p in delete_citations]
article_list.extend(dict_delete)
return article_list
