Reference¶

pybman.client module¶

class pybman.client.Client(secret='')¶

Bases: object

get_data(ctx_id=None, ou_id=None, pers_id=None, lang_id=None, jour_name=None, misc_query=None)¶

update_data(idx, item_data, comment)¶

pybman.data module¶

class pybman.data.DataSet(data_id, data=None, raw=None)¶

Bases: object

get_cone_persons()¶: extract persons’ CoNE IDs and associated names

get_contexts()¶: extract IDs of records an associated IDs of collection

get_creators()¶: extract data of creators from records

get_creators_data()¶: extract persons’ CoNE IDs and associated records

get_creators_from_records()¶: extract creators lists from records

get_genre_data()¶: extract genres and associated records

get_genre_relationships()¶: extract genres and associated source genres

get_genres()¶: extract genres and associated IDs of records

get_item(item_id)¶: extract record with given record ID

get_items_from_year(year)¶: extract IDs of records with given publication year

get_items_from_year_data(year)¶: extract records with given publication year

get_items_released()¶: extract IDs of records with state ‘released’ and associated records

get_items_submitted()¶: extract records with state ‘submitted’ and associated IDs

get_items_with_external_url()¶: extract records with external url

get_items_with_genre(genre)¶: extract IDs of records with state ‘released’ and associated records

get_items_with_identifier_uri()¶: extract records with identifier uri

get_items_with_source_genre(source_genre)¶: extract records with given source genre

get_journals()¶: extract publication sources from records with JOURNAL as source genre

get_journals_data()¶: extract records with JOURNAL as source genre

get_languages()¶: extract publication languages and associated record IDs

get_languages_data()¶: extract publication languages and associated records

get_organizations()¶: extract organizations of creators and associated IDs of records

get_places()¶: extract publication places and associated IDs of records

get_publishers()¶: extract publishers and associated IDs of records

get_series()¶: extract publication source from records with SERIES as source genre

get_source_from_items_with_source_genre(source_genre)¶: extract data of record’s source with given source genre

get_source_genres()¶: extract genres of publication sources and associated record IDs

get_source_genres_data()¶: extract genres of publication sources and associated records

get_sources_identifiers()¶: extract identifers of publication sources and associated record IDs

get_sources_titles()¶: extract titles of publication sources and associated record IDs

get_titles()¶: extract titles and associated IDs of records

get_titles_from_source()¶: extract titles of sources and associated IDs of records

get_years()¶: extract publication years and associated record IDs

get_years_data()¶: extract publication years and associated records

pybman.extract module¶

data extraction routines

pybman.extract.creators_from_item(item)¶: extract creators of item

pybman.extract.creators_from_source(source)¶: extract sources’ titles and genres from item

pybman.extract.ctx_from_item(item)¶: extract identifier of item

pybman.extract.ctx_idx_from_item(item)¶: extract identifier of item

pybman.extract.data(item)¶: extract data of item

pybman.extract.date_accepted_from_item(item)¶: extract date of acceptance from item

pybman.extract.date_created_from_item(item)¶: extract date of creation from item

pybman.extract.date_from_item(item)¶: extract date from item

pybman.extract.date_modified_from_item(item)¶: extract date of modification from item

pybman.extract.date_pubonline_from_item(item)¶: extract publication date (online) from item

pybman.extract.date_pubprint_from_item(item)¶: extract publication date (print) from item

pybman.extract.date_submitted_from_item(item)¶: extract date of submission from item

pybman.extract.field_from_creator(field, creator)¶: extract field from creator of item

pybman.extract.field_from_metadata(field, item, value=True)¶: extract field from metadata of item

pybman.extract.field_from_pubinfo(field, item)¶: extract field from publishing info of item

pybman.extract.field_in_level(field, level)¶: true if field is in level, false otherwise

pybman.extract.genre_from_item(item)¶: extract genre of item

pybman.extract.identifers_from_item(item)¶: extract values and types of identifiers

pybman.extract.idx_from_item(item)¶: extract identifier of item

pybman.extract.items(records)¶: iterate items

pybman.extract.iter_fields(field, level)¶: iterate over field of level

pybman.extract.languages_from_item(item)¶: extract languages of item

pybman.extract.list_from_level(field, level)¶: extract list from field in level of item

pybman.extract.metadata(item)¶: extract meta data of item

pybman.extract.organizations_from_item(item)¶: extract organizations from item

pybman.extract.organizations_identifier_from_creator(creator)¶: extract organizations’ identifiers from item

pybman.extract.organizations_name_from_creator(creator)¶: extract organizations’ names from item

pybman.extract.persons_affiliation_from_creator(creator)¶: exract persons’ affiliations from creator of item

pybman.extract.persons_from_item(item)¶: extract persons from item

pybman.extract.persons_id_from_creator(creator)¶: exract persons’ ID and type of ID from creator of item

pybman.extract.persons_identifier_from_creator(creator)¶: exract persons’ identifier from creator of item

pybman.extract.persons_name_from_creator(creator)¶: exract persons’ name from creator of item

pybman.extract.persons_organizations_from_creator(creator)¶: exract persons’ organizations from creator of item

pybman.extract.place_from_item(item)¶: extract publishing place of item

pybman.extract.pubinfo_from_item(item)¶: extract publishing info of item

pybman.extract.publisher_from_item(item)¶: extract publisher from item

pybman.extract.role_from_creator(creator)¶: extract role from creator of item

pybman.extract.source_titles(collection)¶: extract source titles from records

pybman.extract.source_titles_genres(collection)¶: extract source titles and genres from records

pybman.extract.sources(item)¶: iterate over sources of item

pybman.extract.sources_identifiers_from_item(item)¶: extract values and types of identifiers from item’s sources

pybman.extract.sources_persons_affiliations_from_item(item)¶: extract persons affilations from source of item

pybman.extract.sources_persons_from_item(item)¶: extract sources’ creators from item if person

pybman.extract.sources_persons_id_from_item(item)¶: extract persons ID from source of item

pybman.extract.sources_titles_from_item(item)¶: extract sources’ titles from item

pybman.extract.sources_titles_genres_from_item(item)¶: extract sources’ titles and genres from item

pybman.extract.title_from_item(item)¶: extract title of item

pybman.extract.titles_from_records(records)¶: extract titles from records

pybman.extract.type_from_creator(creator)¶: extract type of creator

pybman.extract.value_from_level(field, level)¶: extract value from field in level of item

pybman.inspector module¶

class pybman.inspector.Inspector(client, records)¶

Bases: object

change_genre(new_genre, old_genre)¶

change_pers_name(old_family_name=None, new_family_name=None, old_given_name=None, new_given_name=None)¶

change_source_genre(new_genre, old_genre)¶

check_publication_date()¶

check_publication_titles(clean=False)¶

check_publication_uri()¶

check_publication_url()¶

check_publishers(clean=False)¶

check_publishers_omission(clean=False)¶

check_publishing_places(clean=False)¶

check_publishing_places_omission(clean=False)¶

check_source_titles(clean=False)¶

clean_publishers()¶

clean_publishing_places()¶

clean_source_titles()¶

clean_titles()¶

update_genre(new_genre, old_genre)¶

update_source_genre(new_genre, old_genre)¶

pybman.local module¶

class pybman.local.LocalData(base_dir='./data/', ous_dir='ous', ctx_dir='ctx', pers_dir='pers', create=False)¶

Bases: object

find_data_path(pattern)¶

generate_data_path(data_id)¶

get_data(pattern)¶

store_data(idx, dict_data)¶

pybman.query module¶

class pybman.query.AllQuery¶

Bases: object

get_files_query()¶

get_locators_query()¶

class pybman.query.ConeQuery¶: Bases: object

class pybman.query.ContextQuery¶

Bases: object

get_item_query(ctx_id)¶

get_released_item_query(ctx_id)¶

class pybman.query.JournalQuery¶

Bases: object

get_item_query(jour_name)¶

get_released_item_query(jour_name)¶

class pybman.query.LangQuery¶

Bases: object

get_item_query(lang_id)¶

get_released_item_query(lang_id)¶

class pybman.query.OrgUnitQuery¶

Bases: object

get_item_query(ou_id)¶

get_item_released_query(ou_id)¶

class pybman.query.PersQuery¶

Bases: object

get_item_query(cone_id)¶

get_item_released_query(cone_id)¶

class pybman.query.Query¶: Bases: object

pybman.rest module¶

class pybman.rest.BaseController(url='https://pure.mpg.de/')¶: Bases: object

class pybman.rest.ConeController¶: Bases: pybman.rest.BaseController

class pybman.rest.ContextRestController¶

Bases: pybman.rest.RestController

get(ctx_id='ctx_924547')¶

get_all()¶

class pybman.rest.FeedRestController¶

Bases: pybman.rest.RestController

get_recent_oa()¶

get_recent_releases()¶

get_recent_releases_for_ou()¶

get_search_as_feed()¶

class pybman.rest.ItemRestController(secret='')¶

Bases: pybman.rest.LoginRestController

count_items(query=None)¶

release_item(item_id, data, comment)¶

revise_item()¶

scroll_items(scroll_id, counter)¶

search_items(query=None)¶

submit_item()¶

update_item(item_id, data)¶

withdraw_item()¶

class pybman.rest.JournalConeController¶

Bases: pybman.rest.ConeController

get_entities()¶

get_entity(journal_id='954928372938')¶

search_entity(cone_id)¶

class pybman.rest.LanguageConeController¶

Bases: pybman.rest.ConeController

full_init()¶

get_entities()¶

get_entity(language_id='deu')¶

init()¶

search_entity(cone_id)¶

class pybman.rest.LoginRestController(auth=True, cred='')¶

Bases: pybman.rest.RestController

get_user()¶

login()¶

logout()¶

class pybman.rest.OrgUnitRestController¶

Bases: pybman.rest.RestController

child_organizations(ou_id='ou_907574')¶

get(ou_id='ou_907574')¶

get_all()¶

top_level()¶

class pybman.rest.PersonConeController¶

Bases: pybman.rest.ConeController

full_init()¶

get_entities()¶

get_entity(person_id='persons32341')¶

init()¶

ous_graph()¶

search_entity(cone_id)¶

class pybman.rest.RestController¶

Bases: pybman.rest.BaseController

get_docs()¶: retrieve api docs of rest interface

pybman.utils module¶

pybman.utils.add_value(d, dkey='', dvalue='')¶

pybman.utils.check_url(url)¶

pybman.utils.clean_string(string)¶

pybman.utils.get_request(url, params=None, headers=None, json_response=True)¶

pybman.utils.post_request(url, params=None, headers=None, data=None, json_res=True)¶

pybman.utils.put_request(url, header, data)¶

pybman.utils.read_csv_with_header(path)¶

pybman.utils.read_json(path)¶

pybman.utils.read_plain_clean(path)¶

pybman.utils.resolve_path(path)¶

pybman.utils.url_exists(url)¶

pybman.utils.url_exists2(url)¶

pybman.utils.write_csv(path, results)¶

pybman.utils.write_json(path, data)¶

pybman.utils.write_list(path, results)¶