def test_search_results_has_verse_list(self):
"""
Test that a SearchResults object with a valid verse list returns True when checking ``has_verse_list()``
"""
# GIVEN: A valid SearchResults object with a proper verse list
search_results = SearchResults('Genesis', 1, {1: 'In the beginning God created the heavens and the earth.'})
# WHEN: We check that the SearchResults object has a verse list
has_verse_list = search_results.has_verse_list()
# THEN: It should be True
self.assertTrue(has_verse_list, 'The SearchResults object should have a verse list')
def test_search_results_has_no_verse_list(self):
"""
Test that a SearchResults object with an empty verse list returns False when checking ``has_verse_list()``
"""
# GIVEN: A valid SearchResults object with an empty verse list
search_results = SearchResults('Genesis', 1, {})
# WHEN: We check that the SearchResults object has a verse list
has_verse_list = search_results.has_verse_list()
# THEN: It should be False
self.assertFalse(has_verse_list, 'The SearchResults object should have a verse list')
def test_search_results_has_no_verse_list(self):
"""
Test that a SearchResults object with an empty verse list returns False when checking ``has_verse_list()``
"""
# GIVEN: A valid SearchResults object with an empty verse list
search_results = SearchResults('Genesis', 1, {})
# WHEN: We check that the SearchResults object has a verse list
has_verse_list = search_results.has_verse_list()
# THEN: It should be False
assert has_verse_list is False, 'The SearchResults object should have a verse list'
def test_search_results_has_verse_list(self):
"""
Test that a SearchResults object with a valid verse list returns True when checking ``has_verse_list()``
"""
# GIVEN: A valid SearchResults object with a proper verse list
search_results = SearchResults(
'Genesis', 1,
{1: 'In the beginning God created the heavens and the earth.'})
# WHEN: We check that the SearchResults object has a verse list
has_verse_list = search_results.has_verse_list()
# THEN: It should be True
assert has_verse_list is True, 'The SearchResults object should have a verse list'
def test_search_results_creation(self):
"""
Test the creation and construction of the SearchResults class
"""
# GIVEN: A book, chapter and a verse list
book = 'Genesis'
chapter = 1
verse_list = {
1:
'In the beginning God created the heavens and the earth.',
2:
'The earth was without form and void, and darkness was over the face of the deep. And the Spirit of '
'God was hovering over the face of the waters.'
}
# WHEN: We create the search results object
search_results = SearchResults(book, chapter, verse_list)
# THEN: It should have a book, a chapter and a verse list
self.assertIsNotNone(search_results,
'The search_results object should not be None')
self.assertEqual(search_results.book, book,
'The book should be "Genesis"')
self.assertEqual(search_results.chapter, chapter,
'The chapter should be 1')
self.assertDictEqual(search_results.verse_list, verse_list,
'The verse lists should be identical')
def get_bible_chapter(self, version, book_name, chapter):
"""
Access and decode bibles via Bibleserver mobile website
:param version: The version of the bible like NIV for New International Version
:param book_name: Text name of bible book e.g. Genesis, 1. John, 1John or Offenbarung
:param chapter: Chapter number
"""
log.debug('BSExtract.get_bible_chapter("%s", "%s", "%s")', version, book_name, chapter)
url_version = urllib.parse.quote(version.encode("utf-8"))
url_book_name = urllib.parse.quote(book_name.encode("utf-8"))
chapter_url = 'http://m.bibleserver.com/text/%s/%s%d' % (url_version, url_book_name, chapter)
header = ('Accept-Language', 'en')
soup = get_soup_for_bible_ref(chapter_url, header)
if not soup:
return None
self.application.process_events()
content = soup.find('div', 'content')
if not content:
log.error('No verses found in the Bibleserver response.')
send_error_message('parse')
return None
content = content.find('div').find_all('div')
verses = {}
for verse in content:
self.application.process_events()
versenumber = int(VERSE_NUMBER_REGEX.sub(r'\3', ' '.join(verse['class'])))
verses[versenumber] = verse.contents[1].rstrip('\n')
return SearchResults(book_name, chapter, verses)
def get_bible_chapter(self, version, book_name, chapter):
"""
Access and decode Bibles via the BibleGateway website.
:param version: The version of the Bible like 31 for New International version.
:param book_name: Name of the Book.
:param chapter: Chapter number.
"""
log.debug('BGExtract.get_bible_chapter("%s", "%s", "%s")', version, book_name, chapter)
url_book_name = urllib.parse.quote(book_name.encode("utf-8"))
url_params = 'search=%s+%s&version=%s' % (url_book_name, chapter, version)
soup = get_soup_for_bible_ref(
'http://legacy.biblegateway.com/passage/?%s' % url_params,
pre_parse_regex=r'<meta name.*?/>', pre_parse_substitute='')
if not soup:
return None
div = soup.find('div', 'result-text-style-normal')
if not div:
return None
self._clean_soup(div)
span_list = div.find_all('span', 'text')
log.debug('Span list: %s', span_list)
if not span_list:
# If we don't get any spans then we must have the old HTML format
verse_list = self._extract_verses_old(div)
else:
verse_list = self._extract_verses(span_list)
if not verse_list:
log.debug('No content found in the BibleGateway response.')
send_error_message('parse')
return None
return SearchResults(book_name, chapter, verse_list)
def get_bible_chapter(self, version, book_name, chapter):
"""
Access and decode bibles via the Crosswalk website
:param version: The version of the Bible like niv for New International Version
:param book_name: Text name of in english e.g. 'gen' for Genesis
:param chapter: Chapter number
"""
log.debug(
'CWExtract.get_bible_chapter("{version}", "{book}", "{chapter}")'.
format(version=version, book=book_name, chapter=chapter))
url_book_name = book_name.replace(' ', '-')
url_book_name = url_book_name.lower()
url_book_name = urllib.parse.quote(url_book_name.encode("utf-8"))
chapter_url = 'http://www.biblestudytools.com/{version}/{book}/{chapter}.html'.format(
version=version, book=url_book_name, chapter=chapter)
soup = get_soup_for_bible_ref(chapter_url)
if not soup:
return None
self.application.process_events()
verses_div = soup.find_all('div', 'verse')
if not verses_div:
log.error('No verses found in the CrossWalk response.')
send_error_message('parse')
return None
verses = {}
for verse in verses_div:
self.application.process_events()
verse_number = int(verse.find('strong').contents[0])
verse_span = verse.find('span', class_='verse-%d' % verse_number)
tags_to_remove = verse_span.find_all(['a', 'sup'])
for tag in tags_to_remove:
tag.decompose()
verse_text = verse_span.get_text()
self.application.process_events()
# Fix up leading and trailing spaces, multiple spaces, and spaces between text and , and .
verse_text = verse_text.strip('\n\r\t ')
verse_text = REDUCE_SPACES_REGEX.sub(' ', verse_text)
verse_text = FIX_PUNKCTUATION_REGEX.sub(r'\1', verse_text)
verses[verse_number] = verse_text
return SearchResults(book_name, chapter, verses)
def get_bible_chapter(self, version, book_name, chapter):
"""
Access and decode bibles via Bibleserver website
:param version: The version of the bible like NIV for New International Version
:param book_name: Text name of bible book e.g. Genesis, 1. John, 1John or Offenbarung
:param chapter: Chapter number
"""
log.debug(
'BSExtract.get_bible_chapter("{version}", "{book}", "{chapter}")'.
format(version=version, book=book_name, chapter=chapter))
url_version = urllib.parse.quote(version.encode("utf-8"))
url_book_name = urllib.parse.quote(book_name.encode("utf-8"))
chapter_url = 'https://bibleserver.com/{version}/{name}{chapter:d}'.format(
version=url_version, name=url_book_name, chapter=chapter)
soup = get_soup_for_bible_ref(chapter_url)
if not soup:
return None
self.application.process_events()
content = soup.find('article', 'chapter')
if not content:
log.error('No verses found in the Bibleserver response.')
send_error_message('parse')
return None
# remove spans with footnotes
for span in soup.find_all('span', 'footnote-tooltip'):
span.decompose()
# remove noscript tags
for noscript in soup.find_all('noscript'):
noscript.decompose()
content = soup.find_all('span', 'verse')
verses = {}
for verse in content:
self.application.process_events()
versenumber = int(
verse.find('span', 'verse-number__group').get_text().strip())
verses[versenumber] = verse.find(
'span', 'verse-content--hover').get_text().strip()
return SearchResults(book_name, chapter, verses)
