def extract_add_info(arts, art_id, art):
"""Extract information from an article and add it to a data object.
Parameters
----------
arts : Articles
Object to store information for the current article.
art_id : int
ID of the new article.
art : bs4.element.Tag
Extracted article.
Returns
-------
arts : Articles
Object updated with data from the current article.
"""
arts.add_data('ids', art_id)
arts.add_data('titles', extract(art, 'ArticleTitle', 'str'))
arts.add_data('authors', process_authors(extract(art, 'AuthorList',
'raw')))
arts.add_data(
'journals',
(extract(art, 'Title', 'str'), extract(art, 'ISOAbbreviation', 'str')))
arts.add_data('words', extract(art, 'AbstractText', 'all-str'))
arts.add_data('keywords', extract(art, 'Keyword', 'all-list'))
arts.add_data('years', process_pub_date(extract(art, 'PubDate', 'raw')))
arts.add_data('dois', process_ids(extract(art, 'ArticleId', 'all'), 'doi'))
return arts
def get_db_info(req, info_url):
"""Calls EInfo to get info and status of the database to be used for data collection.
Parameters
----------
req : Requester
Object to launch requests from.
info_url : str
URL to request db information from.
Returns
-------
db_info : dict
Information about the database from which the data was accessed.
"""
# Get the info page and parse with BeautifulSoup
info_page = req.request_url(info_url)
info_page_soup = BeautifulSoup(info_page.content, 'lxml')
# Set list of fields to extract from EInfo
fields = [
'dbname', 'menuname', 'description', 'dbbuild', 'count', 'lastupdate'
]
# Extract basic information into a dictionary
db_info = dict()
for field in fields:
db_info[field] = extract(info_page_soup, field, 'str')
return db_info
def get_count(req, url):
"""Get the count of how many articles listed at the requested URL.
Parameters
----------
req : Requester
Object to launch requests from.
url : str
URL to request count data from.
Returns
-------
count : int
Count of the number of articles found.
"""
page = req.request_url(url)
page_soup = BeautifulSoup(page.content, 'lxml')
counts = extract(page_soup, 'count', 'all')
try:
count = int(counts[0].text)
except IndexError:
count = 0
return count
def get_articles(req, art_url, arts):
"""Collect information for each article found for a given term.
Parameters
----------
req : Requester
Requester object to launch requests from.
art_url : str
URL for the article to be collected.
arts : Articles
Object to add data to.
Returns
-------
arts : Articles
Object to store information for the current term.
"""
# Get page of all articles
art_page = req.request_url(art_url)
art_page_soup = BeautifulSoup(art_page.content, 'xml')
articles = art_page_soup.findAll('PubmedArticle')
# Loop through each article, extracting relevant information
for art in articles:
# Get ID of current article & extract and add info to data object
new_id = process_ids(extract(art, 'ArticleId', 'all'), 'pubmed')
arts = extract_add_info(arts, new_id, art)
return arts
def get_db_info(req, info_url):
"""Calls EInfo to get info and status of the database to be used for data collection.
Parameters
----------
req : Requester
Object to launch requests from.
info_url : str
URL to request db information from.
Returns
-------
db_info : dict
Information about the database from which the data was accessed.
Examples
--------
Get info on the pubmed database:
>>> from lisc.requester import Requester
>>> url = 'http://eutils.ncbi.nlm.nih.gov/entrez/eutils/einfo.fcgi?db=pubmed'
>>> db_info = get_db_info(Requester(), url)
"""
# Get the info page and parse with BeautifulSoup
info_page = req.request_url(info_url)
info_page_soup = BeautifulSoup(info_page.content, 'lxml')
# Set list of fields to extract from EInfo
fields = [
'dbname', 'menuname', 'description', 'dbbuild', 'count', 'lastupdate'
]
# Extract basic information into a dictionary
db_info = dict()
for field in fields:
db_info[field] = extract(info_page_soup, field, 'str')
return db_info
