def main():
article_list = helper.id_run('fetch', 'springer')
parsed_df = parse_all(article_list)
prop_dict = parse_properties(parsed_df)
unique_id = prop_dict['id']
helper.serialize_output(unique_id, parsed_df)
helper.update_id_json(prop_dict)
def main_fetch(input_db,input_term, email_id,api_key):
if input_db in ('pmc','pubmed'):
fetch_inst = NCBIFetch.ncbi_fetch(input_db,email_id)
id_list_fetch = helper.id_run('search',input_db)
doc_list = fetch_inst.pub_fetch(id_list_fetch)
prop_dict = fetch_inst.search_properties()
unique_id = prop_dict['id']
helper.serialize_output(unique_id,doc_list)
helper.update_id_json(prop_dict)
if input_db == 'springer':
springer_fetch_inst = SpringerFetch.springer_fetch(input_term,api_key)
url = springer_fetch_inst.ping_api()
results,record_count = springer_fetch_inst.pull_results(url)
prop_dict = springer_fetch_inst.search_properties(record_count)
unique_id = prop_dict['id']
helper.serialize_output(unique_id,results['records'])
helper.update_id_json(prop_dict)
def main():
full_doc = helper.id_run('fetch')
article_list = helper.xml_to_html(full_doc, 'pmc')
parsed_df = parse_all(article_list)
prop_dict = parse_properties(parsed_df)
unique_id = prop_dict['id']
helper.serialize_output(unique_id, parsed_df)
helper.update_id_json(prop_dict)
def ncbi_search(input_term,input_db,email_id):
ncbi_search_inst = NCBISearch.ncbi_search(input_term = input_term,input_db = input_db,email_id = email_id)
# record_count = ncbi_search_inst.pub_count()
record_count = 10
id_list_all = ncbi_search_inst.pub_search(record_count)
prop_dict = ncbi_search_inst.search_properties(record_count)
unique_id = prop_dict['id']
helper.serialize_output(unique_id,id_list_all)
helper.update_id_json(prop_dict)
# helper.clean_folder()
return prop_dict
def main_search(input_term, input_db, email_id):
search_inst = NCBISearch.ncbi_search(input_term, input_db, email_id)
id_list = search_inst.pub_search()
prop_dict = search_inst.search_properties()
unique_id = prop_dict['id']
helper.serialize_output(unique_id, id_list)
helper.update_id_json(prop_dict)
def ncbi_fetch(input_db,input_term, email_id):
fetch_inst = NCBIFetch.ncbi_fetch(input_db,email_id)
id_list_fetch = helper.id_run('search',input_db)
doc_list = fetch_inst.pub_fetch(id_list_fetch)
prop_dict = fetch_inst.search_properties()
unique_id = prop_dict['id']
helper.serialize_output(unique_id,doc_list)
helper.update_id_json(prop_dict)
return(len(id_list_fetch),prop_dict)
def main_search(input_term,input_db,email_id,cur):
if input_db in ('pmc','pubmed'):
search_inst = NCBISearch.ncbi_search(input_term,input_db,email_id)
record_count = search_inst.pub_count()
id_list_all = search_inst.pub_search(record_count)
id_list = helper.filter_ids(input_db,id_list_all,cur)
prop_dict = search_inst.search_properties(record_count)
unique_id = prop_dict['id']
helper.serialize_output(unique_id,id_list)
helper.update_id_json(prop_dict)
def springer_search_fetch(input_term,api_key):
springer_fetch_inst = SpringerFetch.springer_fetch(input_term,api_key)
url = springer_fetch_inst.ping_api()
results,record_count = springer_fetch_inst.pull_results(url)
# record_count = 10
prop_dict = springer_fetch_inst.search_properties(record_count)
unique_id = prop_dict['id']
helper.serialize_output(unique_id,results['records'])
helper.update_id_json(prop_dict)
return(record_count,prop_dict)