def _getGutenbergSpiegelChapters(pages):
chapters = []
for page in pages:
soup = BeautifulSoup(page)
chapter = Library.BookChapter()
titleElement = soup.find('div', attrs={'id': 'gutenb'}).find('h3')
if titleElement != None:
chapter.Title = ''.join(titleElement.strings)
paragraphElements = soup.find('div', attrs={
'id': 'gutenb'
}).find_all('p')
for paragraphElement in paragraphElements:
paragraph = Library.BookParagraph()
paragraphString = ''.join(paragraphElement.strings)
if paragraphString != None:
sentences = paragraphString.replace('!', '.').replace(
'?', '.').split('.')
paragraph.Sentences = [
s.strip() for s in sentences if s.strip() != ''
]
if len(paragraph.Sentences) != 0:
chapter.Paragraphs.append(paragraph)
if len(chapter.Paragraphs) != 0 and chapter.Title != None:
chapters.append(chapter)
return chapters
def _getLowereadBookChapters(pages):
chapters = []
currentChapter = Library.BookChapter()
currentChapter.Title = ''
currentChapter.Paragraphs = []
for page in pages:
soup = BeautifulSoup(page)
readBookElement = soup.find('td', attrs={'class': 'tb_read_book'})
if readBookElement != None:
pageContentElement = readBookElement.find(
'div', attrs={
'class': 'MsoNormal'
}).find('p', attrs={'class': 'MsoNormal'})
for child in pageContentElement.find_all(re.compile('p|div')):
if child.name == 'div':
if child.string != None and child.string.strip() != '':
if len(currentChapter.Paragraphs) != 0:
chapters.append(currentChapter)
currentChapter = Library.BookChapter()
currentChapter.Title = child.string
if child.name == 'p':
paragraphString = ''.join(child.strings)
if paragraphString.strip() != '':
paragraphString = paragraphString.replace(
os.linesep, ' ')
paragraph = Library.BookParagraph()
paragraph.Sentences = []
sentences = paragraphString.replace('!', '.').replace(
'?', '.').split('.')
sentences = [s.strip() for s in sentences]
for sentence in sentences:
if sentence != "":
paragraph.Sentences.append(sentence)
if len(paragraph.Sentences) != 0:
currentChapter.Paragraphs.append(paragraph)
return chapters
def _getReadcentralBookChapter(path):
chapter = Library.BookChapter()
chapter.Paragraphs = []
html = HtmlDownloader.DownloadHtml('www.readcentral.com', path)
soup = BeautifulSoup(html)
pageheadElem = soup.find('div', attrs={'id': 'pagehead'})
chapter.Title = pageheadElem.div.string.strip()
contentElement = soup.find(
'div', attrs={'id': 'ctl00_contents_book_chapter_content_area'})
for paragraphElement in contentElement.find_all('p'):
paragraphString = ''.join(paragraphElement.strings)
#paragraphString = re.sub('<[^>]+>', '', paragraphString)
if paragraphString != None:
paragraph = Library.BookParagraph()
paragraph.Sentences = getEnSentencesFromParagraphString(
paragraphString)
if len(paragraph.Sentences) != 0:
chapter.Paragraphs.append(paragraph)
return chapter