def collect_words(terms,
inclusions=[],
exclusions=[],
db='pubmed',
retmax=None,
field='TIAB',
usehistory=False,
api_key=None,
save_and_clear=False,
logging=None,
directory=None,
verbose=False):
"""Collect text data and metadata from EUtils using specified search term(s).
Parameters
----------
terms : list of list of str
Search terms.
inclusions : list of list of str, optional
Inclusion words for search terms.
exclusions : list of list of str, optional
Exclusion words for search terms.
db : str, optional, default: 'pubmed'
Which database to access from EUtils.
retmax : int, optional
Maximum number of articles to return.
field : str, optional, default: 'TIAB'
Field to search for term within.
Defaults to 'TIAB', which is Title/Abstract.
usehistory : bool, optional, default: False
Whether to use EUtils history, storing results on their server.
api_key : str, optional
An API key for a NCBI account.
save_and_clear : bool, optional, default: False
Whether to save words data to disk per term as it goes, instead of holding in memory.
logging : {None, 'print', 'store', 'file'}
What kind of logging, if any, to do for requested URLs.
directory : str or SCDB, optional
Folder or database object specifying the save location.
verbose : bool, optional, default: False
Whether to print out updates.
Returns
-------
results : list of Articles
Results from collecting data for each term.
meta_data : MetaData
Meta data from the data collection.
Notes
-----
The collection does an exact word search for the term given. It then loops through all
the articles found for that term.
For each article, it pulls and saves out data (including title, abstract, authors, etc),
using the hierarchical tag structure that organizes the articles.
"""
# Get EUtils URLS object, with desired settings, and build required utility URLs
urls = EUtils(db=db,
usehistory='y' if usehistory else 'n',
retmax=retmax,
retmode='xml',
field=field,
api_key=api_key)
urls.build_url('info', settings=['db'])
urls.build_url('search',
settings=['db', 'usehistory', 'retmax', 'retmode', 'field'])
urls.build_url('fetch', settings=['db', 'retmode'])
# Initialize results, meta data & requester
results = []
meta_data = MetaData()
req = Requester(wait_time=get_wait_time(urls.authenticated),
logging=logging,
directory=directory)
# Get current information about database being used
meta_data.add_db_info(get_db_info(req, urls.get_url('info')))
# Check inclusions & exclusions
inclusions = inclusions if inclusions else [[]] * len(terms)
exclusions = exclusions if exclusions else [[]] * len(terms)
# Loop through all the terms
for search, incl, excl in zip(terms, inclusions, exclusions):
# Collect term information and make search term argument
term = Term(search[0], search, incl, excl)
term_arg = mk_term(term)
if verbose:
print('Collecting data for: ', term.label)
# Initialize object to store data for current term articles
arts = Articles(term)
# Request web page
url = urls.get_url('search', settings={'term': term_arg})
page = req.request_url(url)
page_soup = BeautifulSoup(page.content, 'lxml')
if usehistory:
# Get number of articles, and keys to use history
count = int(page_soup.find('count').text)
web_env = page_soup.find('webenv').text
query_key = page_soup.find('querykey').text
# Loop through, collecting article data, using history
ret_start_it = 0
while ret_start_it < count:
# Set the number of articles per iteration (the ret_max per call)
# This defaults to 100, but will set to less if fewer needed to reach retmax
ret_end_it = min(100, int(retmax) - ret_start_it)
# Get article page, collect data, update position
url_settings = {
'WebEnv': web_env,
'query_key': query_key,
'retstart': str(ret_start_it),
'retmax': str(ret_end_it)
}
art_url = urls.get_url('fetch', settings=url_settings)
arts = get_articles(req, art_url, arts)
ret_start_it += ret_end_it
if ret_start_it >= int(retmax):
break
# Without using history
else:
ids = page_soup.find_all('id')
art_url = urls.get_url('fetch', settings={'id': ids_to_str(ids)})
arts = get_articles(req, art_url, arts)
arts._check_results()
if save_and_clear:
arts.save_and_clear(directory=directory)
results.append(arts)
meta_data.add_requester(req)
return results, meta_data
def collect_counts(terms_a,
inclusions_a=None,
exclusions_a=None,
labels_a=None,
terms_b=None,
inclusions_b=None,
exclusions_b=None,
labels_b=None,
db='pubmed',
field='TIAB',
api_key=None,
collect_coocs=True,
logging=None,
directory=None,
verbose=False,
**eutils_kwargs):
"""Collect count and term co-occurrence data from EUtils.
Parameters
----------
terms_a : list of list of str
Search terms.
inclusions_a : list of list of str, optional
Inclusion words for search terms.
exclusions_a : list of list of str, optional
Exclusion words for search terms.
labels_a : list of str, optional
Labels for the search terms.
terms_b : list of list of str, optional
Secondary list of search terms.
inclusions_b : list of list of str, optional
Inclusion words for the second list of search terms.
exclusions_b : list of list of str, optional
Exclusion words for the second list of search terms.
labels_b : list of str
Labels for the second list of search terms.
db : str, optional, default: 'pubmed'
Which database to access from EUtils.
field : str, optional, default: 'TIAB'
Field to search for term within.
Defaults to 'TIAB', which is Title/Abstract.
api_key : str, optional
An API key for a NCBI account.
collect_coocs : bool, optional, default: True
Whether to collect co-occurence data.
If False, only collects the counts for first term list.
logging : {None, 'print', 'store', 'file'}, optional
What kind of logging, if any, to do for requested URLs.
directory : str or SCDB, optional
Folder or database object specifying the save location.
verbose : bool, optional, default: False
Whether to print out updates.
**eutils_kwargs
Additional settings for the EUtils API.
Returns
-------
co_occurences : 2d array
The numbers of articles found for each combination of terms.
Only returned if `collect_coocs` is True.
counts : 1d array or list of 1d array
Number of articles for each term independently.
meta_data : dict
Meta data from the data collection.
Notes
-----
The collection does an exact word search for search terms.
The HTML page returned by the EUtils search includes a 'count' field.
This field contains the number of articles with both terms. This is extracted.
Examples
--------
Collect counts and co-occurrences for a single set of two search terms:
>>> coocs, counts, meta_data = collect_counts([['frontal lobe'], ['temporal lobe']])
Collect counts and co-occurrences for two sets of search terms:
>>> coocs, counts, meta_data = collect_counts(terms_a=[['frontal lobe'], ['temporal lobe']],
... terms_b=[['attention'], ['perception']])
"""
# Get e-utils URLS object. Set retmax as 0, since not using UIDs for counts
urls = EUtils(db=db,
retmax='0',
field=field,
retmode='xml',
**eutils_kwargs,
api_key=api_key)
# Define the settings for the search utility, adding a default for datetype if not provided
search_settings = ['db', 'retmax', 'retmode', 'field']
if 'date' in ''.join(
eutils_kwargs.keys()) and 'datetype' not in eutils_kwargs.keys():
search_settings.append('datetype')
# Build the URLs for the utilities that will be used
urls.build_url('info', settings=['db'])
urls.build_url('search',
settings=search_settings + list(eutils_kwargs.keys()))
# Initialize meta data object
meta_data = MetaData()
# Check for a Requester object to be passed in as logging, otherwise initialize
req = logging if isinstance(logging, Requester) else \
Requester(wait_time=get_wait_time(urls.authenticated),
logging=logging, directory=directory)
# Sort out terms for list a
n_terms_a = len(terms_a)
counts_a = np.ones([n_terms_a], dtype=int) * -1
labels_a = labels_a if labels_a else [term[0] for term in terms_a]
inclusions_a = [[]] * n_terms_a if not inclusions_a else inclusions_a
exclusions_a = [[]] * n_terms_a if not exclusions_a else exclusions_a
# If collecting co-occurences, sort out terms for list b and initialize co-occurence stores
if collect_coocs:
if not terms_b:
square = True
terms_b, inclusions_b, exclusions_b = terms_a, inclusions_a, exclusions_a
else:
square = False
n_terms_b = len(terms_b)
counts_b = np.ones([n_terms_b], dtype=int) * -1
labels_b = labels_b if labels_b else [term[0] for term in terms_b]
inclusions_b = [[]] * n_terms_b if not inclusions_b else inclusions_b
exclusions_b = [[]] * n_terms_b if not exclusions_b else exclusions_b
# Initialize matrices to store co-occurrence data
co_occurences = np.ones([n_terms_a, n_terms_b], dtype=int) * -1
# Set diagonal to zero if square (term co-occurrence with itself)
if square:
np.fill_diagonal(co_occurences, 0)
# Get current information about database being used
meta_data.add_db_info(get_db_info(req, urls.get_url('info')))
# Loop through each term (list-A)
for a_ind, (label_a, search_a, incl_a, excl_a) in \
enumerate(zip(labels_a, terms_a, inclusions_a, exclusions_a)):
# Make term arguments
term_a = Term(label_a, search_a, incl_a, excl_a)
term_a_arg = make_term(term_a)
if verbose:
print('Running counts for: ', term_a.label)
# Get number of results for current term search
url = urls.get_url('search', settings={'term': term_a_arg})
counts_a[a_ind] = get_count(req, url)
if collect_coocs:
# For each term in list a, loop through each term in list b
for b_ind, (label_b, search_b, incl_b, excl_b) in \
enumerate(zip(labels_b, terms_b, inclusions_b, exclusions_b)):
# Skip collections of equivalent term combinations - if single term list
# This will skip the diagonal row, and any combinations already collected
if square and co_occurences[a_ind, b_ind] != -1:
continue
# Make term arguments
term_b = Term(label_b, search_b, incl_b, excl_b)
term_b_arg = make_term(term_b)
full_term_arg = join(term_a_arg, term_b_arg, 'AND')
# Get number of results for current term search
if not square:
url = urls.get_url('search', settings={'term': term_b_arg})
counts_b[b_ind] = get_count(req, url)
# Get number of results for combination of terms
url = urls.get_url('search', settings={'term': full_term_arg})
count = get_count(req, url)
co_occurences[a_ind, b_ind] = count
if square:
co_occurences[b_ind, a_ind] = count
if collect_coocs:
counts = counts_a if square else [counts_a, counts_b]
else:
counts = counts_a
meta_data.add_requester(req)
if not collect_coocs:
return counts, meta_data
else:
return co_occurences, counts, meta_data
def collect_counts(terms_a, inclusions_a=None, exclusions_a=None,
terms_b=None, inclusions_b=None, exclusions_b=None,
db='pubmed', field='TIAB', api_key=None,
logging=None, directory=None, verbose=False):
"""Collect count and term co-occurrence data from EUtils.
Parameters
----------
terms_a : list of list of str
Search terms.
inclusions_a : list of list of str, optional
Inclusion words for search terms.
exclusions_a : list of list of str, optional
Exclusion words for search terms.
terms_b : list of list of str, optional
Secondary list of search terms.
inclusions_b : list of list of str, optional
Inclusion words for secondary list of search terms.
exclusions_b : list of list of str, optional
Exclusion words for secondary list of search terms.
db : str, optional, default: 'pubmed'
Which database to access from EUtils.
field : str, optional, default: 'TIAB'
Field to search for term within.
Defaults to 'TIAB', which is Title/Abstract.
api_key : str, optional
An API key for a NCBI account.
logging : {None, 'print', 'store', 'file'}, optional
What kind of logging, if any, to do for requested URLs.
directory : str or SCDB, optional
Folder or database object specifying the save location.
verbose : bool, optional, default: False
Whether to print out updates.
Returns
-------
co_occurences : 2d array
The numbers of articles found for each combination of terms.
counts : 1d array or list of 1d array
Number of articles for each term independently.
meta_data : dict
Meta data from the data collection.
Notes
-----
The collection does an exact word search for two terms.
The HTML page returned by the EUtils search includes a 'count' field.
This field contains the number of articles with both terms. This is extracted.
Examples
--------
Collect counts and co-occurrences for a single set of two search terms:
>>> coocs, counts, meta_data = collect_counts([['frontal lobe'], ['temporal lobe']])
Collect counts and co-occurrences for two sets of search terms:
>>> coocs, counts, meta_data = collect_counts(terms_a=[['frontal lobe'], ['temporal lobe']],
... terms_b=[['attention'], ['perception']])
"""
# Get e-utils URLS object. Set retmax as 0, since not using UIDs for counts
urls = EUtils(db=db, retmax='0', field=field, retmode='xml', api_key=api_key)
urls.build_url('info', settings=['db'])
urls.build_url('search', settings=['db', 'retmax', 'retmode', 'field'])
# Initialize meta data & requester
meta_data = MetaData()
req = Requester(wait_time=get_wait_time(urls.authenticated),
logging=logging, directory=directory)
# Sort out terms
n_terms_a = len(terms_a)
if not terms_b:
square = True
terms_b, inclusions_b, exclusions_b = terms_a, inclusions_a, exclusions_a
else:
square = False
n_terms_b = len(terms_b)
# Check inclusions & exclusions
inclusions_a = [[]] * n_terms_a if not inclusions_a else inclusions_a
inclusions_b = [[]] * n_terms_b if not inclusions_b else inclusions_b
exclusions_a = [[]] * n_terms_a if not exclusions_a else exclusions_a
exclusions_b = [[]] * n_terms_b if not exclusions_b else exclusions_b
# Initialize count variables to the correct length
counts_a = np.ones([n_terms_a], dtype=int) * -1
counts_b = np.ones([n_terms_b], dtype=int) * -1
# Initialize right size matrices to store co-occurence data
co_occurences = np.ones([n_terms_a, n_terms_b], dtype=int) * -1
# Set diagonal to zero if square (term co-occurrence with itself)
if square:
np.fill_diagonal(co_occurences, 0)
# Get current information about database being used
meta_data.add_db_info(get_db_info(req, urls.get_url('info')))
# Loop through each term (list-A)
for a_ind, (search_a, incl_a, excl_a) in enumerate(zip(terms_a, inclusions_a, exclusions_a)):
# Make term arguments
term_a = Term(search_a[0], search_a, incl_a, excl_a)
term_a_arg = mk_term(term_a)
if verbose:
print('Running counts for: ', term_a.label)
# Get number of results for current term search
url = urls.get_url('search', settings={'term' : term_a_arg})
counts_a[a_ind] = get_count(req, url)
# For each term in list a, loop through each term in list b
for b_ind, (search_b, incl_b, excl_b) in enumerate(zip(terms_b, inclusions_b, exclusions_b)):
# Skip collections of equivalent term combinations - if single term list
# This will skip the diagonal row, and any combinations already collected
if square and co_occurences[a_ind, b_ind] != -1:
continue
# Make term arguments
term_b = Term(search_b[0], search_b, incl_b, excl_b)
term_b_arg = mk_term(term_b)
full_term_arg = join(term_a_arg, term_b_arg, 'AND')
# Get number of results for current term search
if not square:
url = urls.get_url('search', settings={'term' : term_b_arg})
counts_b[b_ind] = get_count(req, url)
# Get number of results for combination of terms
url = urls.get_url('search', settings={'term' : full_term_arg})
count = get_count(req, url)
co_occurences[a_ind, b_ind] = count
if square:
co_occurences[b_ind, a_ind] = count
if square:
counts = counts_a
else:
counts = [counts_a, counts_b]
meta_data.add_requester(req)
return co_occurences, counts, meta_data
def collect_words(terms, inclusions=None, exclusions=None, labels=None,
db='pubmed', retmax=100, field='TIAB', usehistory=False,
api_key=None, save_and_clear=False, logging=None, directory=None,
verbose=False, **eutils_kwargs):
"""Collect text data and metadata from EUtils using specified search term(s).
Parameters
----------
terms : list of list of str
Search terms.
inclusions : list of list of str, optional
Inclusion words for search terms.
exclusions : list of list of str, optional
Exclusion words for search terms.
labels : list of str, optional
Labels for the search terms.
db : str, optional, default: 'pubmed'
Which database to access from EUtils.
retmax : int, optional, default: 100
Maximum number of articles to return.
field : str, optional, default: 'TIAB'
Field to search for term within.
Defaults to 'TIAB', which is Title/Abstract.
usehistory : bool, optional, default: False
Whether to use EUtils history, storing results on their server.
api_key : str, optional
An API key for a NCBI account.
save_and_clear : bool, optional, default: False
Whether to save words data to disk per term as it goes, instead of holding in memory.
logging : {None, 'print', 'store', 'file'}
What kind of logging, if any, to do for requested URLs.
directory : str or SCDB, optional
Folder or database object specifying the save location.
verbose : bool, optional, default: False
Whether to print out updates.
**eutils_kwargs
Additional settings for the EUtils API.
Returns
-------
results : list of Articles
Results from collecting data for each term.
meta_data : MetaData
Meta data from the data collection.
Notes
-----
The collection does an exact word search for the term given. It then loops through all
the articles found for that term.
For each article, it pulls and saves out data (including title, abstract, authors, etc),
using the hierarchical tag structure that organizes the articles.
Examples
--------
Collect words data for two terms, limiting the results to 5 articles per term:
>>> results, meta_data = collect_words([['frontal lobe'], ['temporal lobe']], retmax=5)
"""
# Check for valid database based on what words is set up to collect
if db != 'pubmed':
msg = 'Only the `pubmed` database is currently supported for words collection.'
raise NotImplementedError(msg)
# Get EUtils URLS object, with desired settings, and build required utility URLs
urls = EUtils(db=db, retmax=retmax, usehistory='y' if usehistory else 'n',
field=field, retmode='xml', **eutils_kwargs, api_key=api_key)
# Define the settings for the search utility, adding a default for datetype if not provided
search_settings = ['db', 'usehistory', 'retmax', 'retmode', 'field']
if 'date' in ''.join(eutils_kwargs.keys()) and 'datetype' not in eutils_kwargs.keys():
search_settings.append('datetype')
# Build the URLs for the utilities that will be used
urls.build_url('info', settings=['db'])
urls.build_url('search', settings=search_settings + list(eutils_kwargs.keys()))
urls.build_url('fetch', settings=['db', 'retmode'])
# Initialize results & meta data
results = []
meta_data = MetaData()
# Check for a Requester object to be passed in as logging, otherwise initialize
req = logging if isinstance(logging, Requester) else \
Requester(wait_time=get_wait_time(urls.authenticated),
logging=logging, directory=directory)
# Get current information about database being used
meta_data.add_db_info(get_db_info(req, urls.get_url('info')))
# Check labels, inclusions & exclusions
labels = labels if labels else [term[0] for term in terms]
inclusions = inclusions if inclusions else [[]] * len(terms)
exclusions = exclusions if exclusions else [[]] * len(terms)
# Loop through all the terms
for label, search, incl, excl in zip(labels, terms, inclusions, exclusions):
# Collect term information and make search term argument
term = Term(label, search, incl, excl)
term_arg = make_term(term)
if verbose:
print('Collecting data for: ', term.label)
# Initialize object to store data for current term articles
arts = Articles(term)
# Request web page
url = urls.get_url('search', settings={'term' : term_arg})
page = req.request_url(url)
page_soup = BeautifulSoup(page.content, 'lxml')
# Get number of articles
count = int(page_soup.find('count').text)
# Collect articles, using history
if usehistory:
# Get the information from the page for using history
web_env = page_soup.find('webenv').text
query_key = page_soup.find('querykey').text
# Set default retmax per history iteration
retmax_hist = 100
# Loop through, using history to collect groups of articles at a time
retstart_it = 0
while retstart_it < count:
# Set the retmax for the current iteration
retmax_it = min(retmax-retstart_it, retmax_hist)
# Get article page, collect data
url_settings = {'WebEnv' : web_env, 'query_key' : query_key,
'retstart' : str(retstart_it), 'retmax' : str(retmax_it)}
art_url = urls.get_url('fetch', settings=url_settings)
arts = get_articles(req, art_url, arts)
# Update position for counting, and break out if more than global retmax
retstart_it += retmax_hist
if retstart_it >= int(retmax):
break
# Without using history
else:
ids = page_soup.find_all('id')
ids_str = ','.join([el.text for el in ids])
art_url = urls.get_url('fetch', settings={'id' : ids_str})
arts = get_articles(req, art_url, arts)
arts._check_results()
if save_and_clear:
arts.save_and_clear(directory=directory)
results.append(arts)
meta_data.add_requester(req)
return results, meta_data