def test_editions(self):
pandata = Pandata(EDITIONTEST_FILENAME)
(ed1,ed2) = pandata.get_edition_list()
self.assertEqual(ed1.publisher, "Project Gutenberg")
self.assertEqual(ed2.publisher, "Recovering the Classics")
self.assertEqual(ed2.isbn, "9781111122223")
self.assertEqual(ed1.isbn, "")
self.assertEqual(ed1.edition_identifiers['edition_id'], "repo:Space-Viking_20728#default")
self.assertEqual(ed2.edition_identifiers['edition_id'], u'repo:Space-Viking_20728#9781111122223')
pandata = Pandata('https://github.com/gitenberg-dev/metadata/raw/master/samples/pandata.yaml')
[ed] = pandata.get_edition_list()
def test_editions(self):
pandata = Pandata(EDITIONTEST_FILENAME)
(ed1,ed2) = pandata.get_edition_list()
self.assertEqual(ed1.publisher, "Project Gutenberg")
self.assertEqual(ed2.publisher, "Recovering the Classics")
self.assertEqual(ed2.isbn, "9781111122223")
self.assertEqual(ed1.isbn, "")
self.assertEqual(ed1.edition_identifiers['edition_id'], "repo:Space-Viking_20728#default")
self.assertEqual(ed2.edition_identifiers['edition_id'], u'repo:Space-Viking_20728#9781111122223')
pandata = Pandata('https://github.com/gitenberg-dev/metadata/raw/master/samples/pandata.yaml')
[ed] = pandata.get_edition_list()
def add_by_webpage(url, work=None, user=None):
edition = None
scraper = get_scraper(url)
loader = BasePandataLoader(url)
pandata = Pandata()
pandata.metadata = scraper.metadata
for metadata in pandata.get_edition_list():
edition = loader.load_from_pandata(metadata, work)
work = edition.work
loader.load_ebooks(pandata, edition, user=user)
return edition if edition else None
def load_from_yaml(yaml_url, test_mode=False):
"""
This really should be called 'load_from_github_yaml'
if mock_ebook is True, don't construct list of ebooks from a release -- rather use an epub
"""
all_metadata = Pandata(yaml_url)
loader = GithubLoader(yaml_url)
for metadata in all_metadata.get_edition_list():
edition = loader.load_from_pandata(metadata)
loader.load_ebooks(metadata, edition, test_mode)
return edition.work_id if edition else None
def add_by_sitemap(url, maxnum=None):
editions = []
for bookdata in scrape_sitemap(url, maxnum=maxnum):
edition = work = None
loader = BasePandataLoader(bookdata.base)
pandata = Pandata()
pandata.metadata = bookdata.metadata
for metadata in pandata.get_edition_list():
edition = loader.load_from_pandata(metadata, work)
work = edition.work
loader.load_ebooks(pandata, edition)
if edition:
editions.append(edition)
return editions
def add_from_bookdatas(bookdatas):
''' bookdatas are iterators of scrapers '''
editions = []
for bookdata in bookdatas:
edition = work = None
loader = BasePandataLoader(bookdata.base)
pandata = Pandata()
pandata.metadata = bookdata.metadata
for metadata in pandata.get_edition_list():
edition = loader.load_from_pandata(metadata, work)
work = edition.work
loader.load_ebooks(pandata, edition)
if edition:
editions.append(edition)
return editions
