def main():
login(user=username, pwd=password)
for cat in categories:
# https://www.blinkist.com/en/nc/categories/entrepreneurship-and-small-business-en
book_titles = get_books_for_category(
url="https://www.blinkist.com/en/nc/categories/{cat}/books/".
format(cat=cat))
for index, title in enumerate(book_titles):
print("{}/{} - {}".format(index + 1, len(book_titles), title))
# check if we already have the epub file
filename = './{cat}/{title}'.format(
cat=cat, title=title
) # title=book.title.translate(ILLEGAL_FILENAME_CHARACTERS))
if os.path.isfile(filename + '.epub'):
print('File already exists')
else:
book = ez_epub.Book()
book.sections = []
book = analytic_info_html(
category=cat,
book=book,
url="https://www.blinkist.com/books/{title}/".format(
title=title))
book = analytic_content_html(
book=book,
url="https://www.blinkist.com/en/nc/reader/{title}/".
format(title=title))
book.make(filename)
print('Created epub file: ' + filename)
def create_epub():
title = raw_input('Titulo del libro: ')
author = raw_input('Autor del libro: ')
book = ez_epub.Book()
book.title = title
book.authors = [author]
book.sections = epubCreator.parseBook(r'temp.txt', 1, 100)
book.make(r'%s' % book.title)
def main():
login(username=username, password=password)
for index, book_url in enumerate(book_urls):
title = extract_title_from_book_url(book_url)
print("{}/{} - {}".format(index + 1, len(book_urls), title))
book = ez_epub.Book()
book.sections = []
book = analytic_info_html(book=book, url="https://www.blinkist.com/en/books/{title}.html".format(title=title))
book = analytic_content_html(book=book, url="https://www.blinkist.com/en/reader/{title}/".format(title=title))
print('Saving epub')
book.make('./{title}'.format(title=book.title.translate(ILLEAGAL_FILENAME_CHARACTERS)))
continue
if p.__contains__("<xa"):
p = p.replace("<xa", "<a")
section.text.append(genshi.core.Markup(p))
else:
for p in str(page).replace("\n", "<br/>").split("<br/><br/>"):
p, error = tidy_fragment(p)
if p.__contains__("<xa"):
p = p.replace("<xa", "<a")
section.text.append(genshi.core.Markup(p))
except Exception, e:
print str(e)
pass
return section
book = ez_epub.Book()
book.title = "Paul Graham's Essays"
book.authors = ['Paul Graham']
page = urllib2.urlopen('http://www.paulgraham.com/articles.html').read()
soup = BeautifulSoup(page)
soup.prettify()
links = soup.findAll('table', {'width': '435'})[1].findAll('a')
sections = []
for link in links:
sections.append(addSection(link['href'], link.text))
book.sections = sections
book.make(book.title)
def generate_epub(self):
book = ez_epub.Book()
book.title = self.title
book.authors = [self.author]
book.sections = [chapter.generate_epub() for chapter in self.chapters]
return book
def download_story(story_url):
# TODO verify input URL better
story_id = story_url.split('/')[-1].split('-')[0]
# TODO: probably use {'drafts': 0, 'include_deleted': 0}
storyinfo_req = session.get(API_STORYINFO + story_id,
params={
'drafts': 1,
'include_deleted': 1
})
storyinfo_json = json.loads(storyinfo_req.content)
story_title = storyinfo_json['title']
story_description = storyinfo_json['description']
story_createDate = dateutil.parser.parse(storyinfo_json['createDate'])
story_modifyDate = dateutil.parser.parse(storyinfo_json['modifyDate'])
story_author = storyinfo_json['user']['name']
story_categories = [
categories[c] for c in storyinfo_json['categories'] if c in categories
] # category can be 0
story_rating = storyinfo_json['rating'] # TODO: I think 4 is adult?
story_cover = StringIO.StringIO(
session.get(storyinfo_json['cover']).content)
print 'Story "{story_title}": {story_id}'.format(story_title=story_title,
story_id=story_id)
# Setup epub
book = ez_epub.Book()
book.title = story_title
book.authors = [story_author]
book.sections = []
book.impl.add_cover(story_cover)
book.impl.description = HTML(
story_description,
encoding='utf-8') # TODO: not sure if this is HTML or text
book.impl.add_meta('publisher', 'Wattpad - scraped')
book.impl.add_meta('source', story_url)
for part in storyinfo_json['parts']:
chapter_title = part['title']
if part['draft']:
print 'Skipping "{chapter_title}": {chapter_id}, part is draft'.format(
chapter_title=chapter_title, chapter_id=chapter_id)
continue
if 'deleted' in part and part['deleted']:
print 'Skipping "{chapter_title}": {chapter_id}, part is deleted'.format(
chapter_title=chapter_title, chapter_id=chapter_id)
continue
chapter_id = part['id']
# TODO: could intelligently only redownload modified parts
chapter_modifyDate = dateutil.parser.parse(part['modifyDate'])
print 'Downloading "{chapter_title}": {chapter_id}'.format(
chapter_title=chapter_title, chapter_id=chapter_id)
chapter_req = session.get(API_STORYTEXT, params={'id': chapter_id})
chapter_html = json.loads(chapter_req.content)['text']
section = ez_epub.Section()
section.html = HTML(chapter_html, encoding='utf-8')
section.title = chapter_title
book.sections.append(section)
print 'Saving epub'
book.make(book.title + '.epub')
def download_story(story_id):
# TODO: probably use {'drafts': 0, 'include_deleted': 0}
storyinfo = session.get(API_STORYINFO + story_id,
params={
'drafts': 1,
'include_deleted': 1
}).json()
story_title = storyinfo['title']
story_description = storyinfo['description']
story_createDate = dateutil.parser.parse(storyinfo['createDate'])
story_modifyDate = dateutil.parser.parse(storyinfo['modifyDate'])
story_author = storyinfo['user']['name']
story_categories = [
categories[c] for c in storyinfo['categories'] if c in categories
] # category can be 0
story_rating = storyinfo['rating'] # TODO: I think 4 is adult?
story_cover = io.BytesIO(session.get(storyinfo['cover']).content)
story_url = storyinfo['url']
print('Story "{story_title}": {story_id}'.format(story_title=story_title,
story_id=story_id))
# Setup epub
book = ez_epub.Book()
book.title = story_title
book.authors = [story_author]
book.sections = []
book.impl.addCover(fileobj=story_cover)
book.impl.description = HTML(
story_description,
encoding='utf-8') # TODO: not sure if this is HTML or text
book.impl.url = story_url
book.impl.addMeta('publisher', 'Wattpad - scraped')
book.impl.addMeta('source', story_url)
for part in storyinfo['parts']:
chapter_title = part['title']
if part['draft']:
print('Skipping "{chapter_title}": {chapter_id}, part is draft'.
format(chapter_title=chapter_title, chapter_id=chapter_id))
continue
if 'deleted' in part and part['deleted']:
print('Skipping "{chapter_title}": {chapter_id}, part is deleted'.
format(chapter_title=chapter_title, chapter_id=chapter_id))
continue
chapter_id = part['id']
# TODO: could intelligently only redownload modified parts
chapter_modifyDate = dateutil.parser.parse(part['modifyDate'])
print('Downloading "{chapter_title}": {chapter_id}'.format(
chapter_title=chapter_title, chapter_id=chapter_id))
chapter_html = session.get(API_STORYTEXT,
params={
'id': chapter_id,
'output': 'json'
}).json()['text']
chapter_html = smartypants.smartypants(chapter_html)
section = ez_epub.Section()
section.html = HTML(chapter_html, encoding='utf-8')
section.title = chapter_title
book.sections.append(section)
print('Saving epub')
book.make('./{title}'.format(
title=book.title.translate(ILLEAGAL_FILENAME_CHARACTERS)))