def build_book(articles, filename):
book = epub.EpubBook()
book.set_identifier("pinkindbook")
book.set_title('Pinkind Article Collection')
book.set_language('en')
book.add_author('pinkind.dbalan.in')
style = 'body { font-family: Times, Times New Roman, serif; }'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
book.add_item(nav_css)
spine = []
for art in articles:
book.add_item(art)
spine.append(art)
book.toc = spine
book.spine = ['nav'] + spine
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
epub.write_epub(filename, book)
def __init__(self, identifier, title, contributor, series_title):
self.__identifier = identifier
self.__title = title
self.__contributor = contributor
self.__series_title = series_title
self.book = epub.EpubBook()
self.book.FOLDER_NAME = r"OEBPS"
self.book.set_identifier(self.__identifier)
self.book.set_title(self.__title)
self.book.set_language('ja')
self.book.set_direction('rtl')
self.book.add_metadata('DC', 'contributor', self.__contributor)
self.book.add_metadata('DC', 'rights',
"All rights reserved by the contributor")
self.book.add_author(self.__contributor)
if len(self.__series_title) >= 1:
self.book.add_metadata(
None, 'meta', self.__series_title,
OrderedDict([('property', 'belongs-to-collection'),
('id', 'series_id')]))
self.book.add_metadata(
None, 'meta', r"series",
OrderedDict([('refines', '#series_id'),
('property', 'collection-type')]))
self.tocs = []
currentPath = os.path.dirname(os.path.abspath(__file__))
css_path = os.path.abspath(
os.path.join(currentPath, r"assets/stylesheet.css"))
style = TextFileManager(css_path).load()
self.default_css = epub.EpubItem(uid="style",
file_name="stylesheet.css",
media_type="text/css",
content=style)
self.book.add_item(self.default_css)
cover_css_path = os.path.abspath(
os.path.join(currentPath, r"assets/cover.css"))
style_cover = TextFileManager(cover_css_path).load()
self.cover_css = epub.EpubItem(uid="style_cover",
file_name="cover.css",
media_type="text/css",
content=style_cover)
self.book.add_item(self.cover_css)
def make_epub(id, title, lang, author, cover_path, subtitle):
book = epub.EpubBook()
# add metadata
book.set_identifier('ted_' + id)
book.set_title(title)
book.set_language(lang)
book.add_author(author)
# add cover image
book.set_cover("cover.jpg", open(cover_path, 'rb').read())
chpt = epub.EpubHtml(title='subtitle',
file_name='subtitle.xhtml',
lang=lang)
chpt.content = '<html><head></head><body>' + subtitle + '</body></html>'
book.add_item(chpt)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
style = 'BODY {color: while;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
book.add_item(nav_css)
book.spine = ['nav', chpt]
epub_path = './epub/' + id + '.epub'
epub.write_epub(epub_path, book, {})
return
def create_book_chapter(self, chapter_url):
chapter_info = self.extractor.get_chapter_info(chapter_url)
chapter_content = self.extractor.get_chapter_content(
chapter_info["content"])
if chapter_info != None and chapter_content != None:
title = chapter_info["title"]
print(f"create_book_chapter: creating {title}")
chapter = ebooklib.EpubHtml(title=title,
file_name=chapter_info["full_path"],
lang=self.lang)
chapter.set_content(chapter_content)
for stylesheet in chapter_info["stylesheets"]:
css_url = stylesheet["url"]
name = stylesheet["full_path"]
if css_url not in self.styles:
style = self.extractor.get_chapter_style(css_url)
nav_css = ebooklib.EpubItem(
uid=f"style_{name.replace('.css', '')}",
file_name=f"{name}",
media_type="text/css",
content=style)
self.styles.append(css_url)
chapter.add_item(nav_css)
self.chapters.append(chapter)
self.epub.add_item(chapter)
self.create_images(chapter_info["images"],
chapter_info["asset_base_url"])
else:
print("create_book_chapter: errored on ", chapter_url)
def makeImage(self, chapter_content, chapter_id):
img_tags = chapter_content.findAll('img')
img_urls = []
if img_tags:
for img_tag in img_tags:
img_urls.append(img_tag.get('src'))
content = str(chapter_content)
for i, img_url in enumerate(img_urls):
try:
img = Utils().getImage(img_url)
b = BytesIO()
img.save(b, 'jpeg')
b_img = b.getvalue()
img_path = 'images/chapter_' + \
str(chapter_id) + '/image_' + str(i) + '.jpeg'
image_item = epub.EpubItem(file_name=img_path,
media_type='image/jpeg',
content=b_img)
self.book.add_item(image_item)
img_old_path = 'src="' + img_url
img_new_path = 'style="display: block;margin-left: auto;margin-right: auto;" src="' + img_path
content = content.replace(img_old_path, img_new_path)
except:
print('Error: Can not get chapter images! ' + img_url)
else:
content = str(chapter_content)
return content
def add_css(self):
# compile assets
default_collector.collect(self.request)
# add the files that produce export.css
pkg = self.package_for('epub', 'css')
packager = Packager()
paths = packager.compile(pkg.paths)
self.stylesheets = []
for path in paths:
with codecs.open(staticfiles_storage.path(path), 'r',
'utf-8') as f:
css = f.read()
self.book.add_item(
epub.EpubItem(file_name=path,
media_type="text/css",
content=css))
self.stylesheets.append(path)
# now ensure all html items link to the stylesheets
for item in self.book.items:
if isinstance(item, (epub.EpubHtml, epub.EpubNav)):
for stylesheet in self.stylesheets:
# relativise path
href = '/'.join(['..'] * item.file_name.count('/') +
[stylesheet])
item.add_link(href=href, rel='stylesheet', type='text/css')
def add_css(book):
style = """
@namespace epub "http://www.idpf.org/2007/ops";
body {
font-family: Cambria, Liberation Serif, Bitstream Vera Serif, Georgia, Times, Times New Roman, serif;
}
h2 {
text-align: left;
text-transform: uppercase;
font-weight: 200;
}
ol {
list-style-type: none;
}
ol > li:first-child {
margin-top: 0.3em;
}
nav[epub|type~='toc'] > ol > li > ol {
list-style-type:square;
}
nav[epub|type~='toc'] > ol > li > ol > li {
margin-top: 0.3em;
}
"""
# add css file
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
book.add_item(nav_css)
def process_output_to_epub(feed: FeedParserDict, limit: int) -> epub.EpubBook:
"""Form epub structure for epub file"""
logging.debug("Starting format html for epub file")
book = epub.EpubBook()
book.set_identifier('rss news')
book.set_title(feed.get("feed", {}).get("title"))
book.set_language('en')
book.spine = ['nav']
book.toc = []
for news in feed.get("entries")[:limit]:
chapter = epub.EpubHtml(title=news.get("title"),
file_name=str(hash(news.get("title"))) +
'.xhtml')
content = BeautifulSoup(
create_title(news.get("title")) + news.get("summary") +
create_link(news.get("link")), "lxml")
images = content.find_all('img')
process_images(images, book)
chapter.set_content(str(content))
book.add_item(chapter)
book.spine.append(chapter)
book.toc.append(chapter)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
style = 'BODY {color: white;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
book.add_item(nav_css)
logging.debug("Structure for epub file created")
return book
def fetch_img(self, url_img):
if self.image_size is not None and self.image_size < self.image_count:
self.logger.warn('达到最大图像总计大小，取消图像下载')
# 此时文档中的链接是错误的...所以贪心要付出代价
# 上一行注释是啥来着(?)
return
if not self.running:
logger.warning(f'Canceling image: {url_img}')
return
self.logger.info('->Fetching image: ' + url_img + '...')
data_img = requests.get(url_img,
headers={
'User-Agent': Wenku8ToEpub.USER_AGENT
},
proxies=self.get_proxy()).content
self.image_count = self.image_count + len(data_img)
filename = None
for sp in self.img_splits:
if sp in url_img:
filename = url_img.split(sp)[-1]
if filename is None:
filename = url_img.split(':')[-1].split('//')[-1]
filetype = url_img.split('.')[-1]
# print('done. filename:', filename, "filetype", filetype)
img = epub.EpubItem(file_name="images/%s" % filename,
media_type="image/%s" % filetype,
content=data_img)
self.lock.acquire()
self.book.add_item(img)
self.lock.release()
self.logger.info('<-Done image: ' + url_img)
def export_epub(self, book_name):
# set metadata
# add default NCX and Nav file
self.book.add_item(epub.EpubNcx())
self.book.add_item(epub.EpubNav())
# define CSS style
style = 'BODY {color: white;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
# add CSS file
self.book.add_item(nav_css)
# basic spine
self.book.spine = ['nav'] + self.chapterinfo
# write to the file
output_folder = os.path.join(os.path.dirname(__file__), "output")
output_file = os.path.join(output_folder, book_name + '.epub')
try:
os.mkdir(output_folder)
except:
pass
epub.write_epub(output_file, self.book, {})
print('輸出路徑: ' + output_file)
print('Done')
def work(project, _vars):
book = epub.EpubBook()
book.set_identifier(_vars.nid)
book.set_title(_vars.title)
book.set_language('zh')
book.add_author(_vars.author)
book.add_item(epub.EpubNav())
book.add_item(epub.EpubNcx())
book.add_item(
epub.EpubItem(uid="style_nav",
file_name="style/style.css",
media_type="text/css",
content=css))
book.spine = ['nav']
book.add_metadata('DC', 'description', _vars.description)
book.toc = tuple(
(epub.Section(title),
tuple(
build_page(book, f'./{project}/{file}', file.replace(".tex", ""))
for file in files)) for title, files in _vars.menu.items())
epub.write_epub(f"./artifacts/{project}/epub/{project}_latest.epub", book,
{'epub3_pages': False})
shutil.copy(
f"./artifacts/{project}/epub/{project}_latest.epub",
f"./artifacts/{project}/epub/history/{project}_{datetime.datetime.now().strftime('%y%m%d')}.epub"
)
_abspath = os.path.abspath(
f"./artifacts/{project}/epub/{project}_latest.epub")
print(f'[{now}] Epub file saved at {_abspath}.')
def _write_chapter(self, chapter, content, image_name):
"""
Write Chapter
Args:
chapter (string): [Name of chapter]
content (string): [Content of chapter]
Returns:
[epub.EpubHtml]: [Chapter of book]
"""
# create chapter
chap = epub.EpubHtml(title=chapter,
file_name=chapter + '.xhtml',
lang='vi')
chap.content = content
chap.add_item(self.book_default_css)
# add chapter
self.book.add_item(chap)
# add image
for iname in image_name:
image_item = epub.EpubItem(file_name=iname,
content=open(iname, 'rb').read(),)
self.book.add_item(image_item)
return chap
def __init_book(self):
"""
[Init epub writer]
"""
self.book = epub.EpubBook()
self.book.set_identifier(self.name)
self.book.set_title(self.name)
self.book.set_language('vi')
self.book.set_cover("temp.png", open('temp.png', 'rb').read())
self.book.add_author(self.author)
# defube style
style = '''
p {
margin-top: 0.0em;
margin-bottom: 0.3em;
text-indent: 1.3em;
}
'''
self.book_default_css = epub.EpubItem(uid="style_default",
file_name="style/default.css",
media_type="text/css", content=style)
self.book.add_item(self.book_default_css)
self.book.add_metadata(None, 'meta', '', {'name': 'website',
'content': self.start_url,
})
def build_epub(self):
logger.info(f"build epub for {self}...")
self.epub = epub.EpubBook()
self.epub.set_title(f"{self.novel.title} - {self.title}")
self.epub.set_identifier(uuid.uuid4().hex)
self.epub.set_language('en')
self.epub.add_item(epub.EpubNcx())
self.epub.add_item(epub.EpubNav())
self.epub.spine = ['Nav'] + self.build_chapters()
st = 'p { margin-top: 1em; text-indent: 0em; } ' \
'h1 {margin-top: 1em; text-align: center} ' \
'h2 {margin: 2em 0 1em; text-align: center; font-size: 2.5em;} ' \
'h3 {margin: 0 0 2em; font-weight: normal; text-align:center; font-size: 1.5em; font-style: italic;} ' \
'.center { text-align: center; } ' \
'.pagebreak { page-break-before: always; } '
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=st)
self.epub.add_item(nav_css)
novel_cache_path = self.novel.get_cache_path()
epub_file_path = os.path.join(novel_cache_path,
f'{self.epub.title}.epub')
epub.write_epub(epub_file_path, self.epub, {})
logger.info(f"Epub for volume {self} done!")
def bind_and_save_epub(self):
"""
Finalizes binding of the ebook and saves it to the filesystem.
"""
print("=== Binding and saving EPUB. ===")
self.book.toc = (self.weather_link,
(epub.Section("Articles"), tuple(self.article_toc_list))
)
# add navigation files
self.book.add_item(epub.EpubNcx())
self.book.add_item(epub.EpubNav())
# define css style
with open('tmpl/book_style.css', 'r') as css_file:
style = css_file.read()
# add css file
nav_css = epub.EpubItem(uid="style_nav", file_name="style/nav.css", media_type="text/css", content=style)
self.book.add_item(nav_css)
self.chaps.insert(0, 'nav')
self.book.spine = self.chaps
self.book_filename = 'news_update_{}.epub'.format(self.target_time)
epub.write_epub(self.book_filename, self.book, {})
print("Saved as {}.".format(self.book_filename))
def filter_chapter(self, html, new_css_item):
'''每一章都是一个html
'''
#给每一个html文件添加css
rel_css_dir = os.path.relpath('.', os.path.dirname(html.get_name()))
rel_css_file_name=os.path.join(rel_css_dir, self.new_css_filename)
html.add_item(epub.EpubItem(file_name=rel_css_file_name, media_type='text/css'))
rel_image_dir=os.path.relpath(self.font_image_dir, os.path.dirname(html.get_name()))
#生成html对应的links
self.init_links_of_html(html)
#只处理body里面正文处理
html_tree = parse_html_string(html.get_body_content())
root=html_tree.getroottree()
build_text_list = etree.XPath("//text()")
text_list=build_text_list(root)
for text in text_list:
#找出一段文字中生僻字的位置
pos_list = self.find_uncommon_words_in_one_text(text)
self.add_image_tag_for_uncommon_words_in_one_text(text, pos_list,rel_image_dir)
#将root更新到html的content中，不然的话，不会保存
ori_root=parse_html_string(html.content)
#删除旧的body
body=ori_root.find('body')
ori_root.remove(body)
#新的body
ori_root.append(root.find('body'))
html.content = etree.tostring(ori_root, pretty_print=True, encoding='utf-8', xml_declaration=True)
def create_book(self, feed):
"""
add news on epub format
:param feed: feed news
:return: book of news
"""
logging.debug("Starting format html for epub file")
self.book.spine = ['nav']
self.book.toc = []
for title, date, link, img in zip(feed["Title"], feed["Date"],
feed['Link'], feed["img"]):
chapter = epub.EpubHtml(title=title, file_name=title + '.xhtml')
content = f"<h4>{title}</h4><br>Date:{date}<br><a href='{link}'>Link<br><img src='{img}'" \
f"alt='NoPhoto' ></a>"
chapter.set_content(str(content))
self.book.add_item(chapter)
self.book.toc.append(chapter)
self.book.add_item(epub.EpubNcx())
self.book.add_item(epub.EpubNav())
style = 'BODY {color: white;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
self.book.add_item(nav_css)
logging.debug("Structure for epub file created")
return self.book
def write_epub():
article_content_list = get_all_article_content()
book = epub.EpubBook()
book.set_identifier('id310626')
book.set_language('en')
book.add_author('Mark Manson')
chapter_list = []
for i, article in enumerate(article_content_list):
chapter_title = article[0]
chapter_content = article[1]
chapter = epub.EpubHtml(title=chapter_title,
file_name=str(i),
lang='en')
chapter_list.append(chapter)
chapter.content = chapter_content
book.add_item(chapter)
book.spine = ['nav'] + chapter_list
book.toc = tuple(chapter_list)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
style = 'BODY {color:white;}'
nav_css = epub.EpubItem(uid='style_nav',
file_name='style/nav.css',
media_type='text/css',
content=style)
book.add_item(nav_css)
epub.write_epub('Manson.epub', book, {})
def union(self, name, size):
file_name = self._get_valid_name(name)
book = epub.EpubBook()
book.set_identifier(file_name)
book.set_title(file_name)
book.set_language('zh')
spine_list = ['nav']
toc_list = []
for index in range(1, size + 1):
content = self.__read_content(index)
lines_of_content = content.split('\n')
title = lines_of_content[0]
ch = epub.EpubHtml(title=title,
file_name='ch_{}.xhtml'.format(index),
lang='zh')
ch.content = '<h4>{}</h4>{}'.format(
title, self.__create_content(lines_of_content[1:]))
book.add_item(ch)
spine_list.append(ch)
toc_list.append(ch)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
style = 'BODY {color: white;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
book.add_item(nav_css)
book.toc = toc_list
book.spine = spine_list
epub.write_epub(self._base_path + file_name + '.epub', book, {})
def contents(self):
if not self._workpath:
return
self._toc = []
def _page_name(i):
return "pdf_frame%s.html" % (str(i) if i else '')
n = len(self._workpath)
for i in range(n):
p = self._workpath[i]
for filename in glob(os.path.join(p, '*.html')):
with open(filename, 'r') as f:
content = f.read()
m = 'link rel="stylesheet" href="'
s = '../Styles/%d/' % i
content = content.replace(m, m + s)
if i:
m = '<div id="page-container">'
s = PREV_TEMPLATE % _page_name(i - 1)
content = content.replace(m, m + s)
if i < n - 1:
m = '</div>\n<div class="loading-indicator">'
s = NEXT_TEMPLATE % _page_name(i + 1)
content = content.replace(m, s + m)
url = "Text/%s" % _page_name(i)
page = epub.EpubItem(file_name=url, content=content)
yield page
for p in self._workpath:
for filename in glob(os.path.join(p, 'chapter*.xhtml')):
name = os.path.basename(filename)
with open(filename, 'rb') as f:
page = epub.EpubItem(file_name="Text/%s" % name,
content=f.read())
yield page
n = 0
for p in self._workpath:
prefix = 'Styles/' + str(n)
n += 1
for filename in glob(os.path.join(p, '*.woff')):
name = os.path.basename(filename)
with open(filename, 'rb') as f:
page = epub.EpubItem(file_name="%s/%s" % (prefix, name),
content=f.read())
yield page
def read_comments_css():
style = load_resource_text("styles.css")
return epub.EpubItem(
uid="style_nav",
file_name="style/comments.css",
media_type="text/css",
content=style,
)
def images(self):
for filename in glob(os.path.join(self._workpath, '*.jpg')):
name = os.path.basename(filename)
with open(filename, 'rb') as f:
yield epub.EpubItem(uid=name,
file_name="Text/%s" % name,
media_type="images/jpg",
content=f.read())
def post_process(self):
self.book.add_item(epub.EpubNcx())
self.book.add_item(epub.EpubNav())
self.book.add_item(
epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=css))
def add_body_style(self, css):
# Define the CSS style
self.body_css = epub.EpubItem(uid="style_body",
file_name="style/body.css",
media_type="text/css",
content=css)
# Add the style as a file
self.book.add_item(self.body_css)
def stylesheets(self):
for filename in glob(os.path.join(self._workpath, '*.css')):
name = os.path.basename(filename)
with open(filename, "rb") as f:
yield epub.EpubItem(uid=name,
file_name="Styles/%s" % name,
media_type="text/css",
content=f.read())
def to_epub(self, style=None):
"""Generate `EpubBook` from result of `get_articles`"""
if not style:
style = STYLE
logging.info('Creating book using %s style' % style)
articles = self.get_articles()
book = epub.EpubBook()
book.set_title(self.__class__.name)
# Create HTML file for each article
chapters = []
for i, article in enumerate(articles):
chapter = epub.EpubHtml(uid=str(i),
title=article.title,
file_name=('%d.xhtml' % i))
chapter.content = '<html><head>' + \
'<link rel="stylesheet" href="style/default.css" />' + \
'</head><body>' + \
('<h1>%s</h1>' % article.title) + \
article.content + '</body></html>'
chapters.append(chapter)
book.add_item(chapter)
# Add generic book metadata
book.toc = map(
lambda c: epub.Link(c.get_name(), c.title, str(c.get_id())),
chapters)
book.add_item(epub.EpubNcx())
book.add_item(epub.EpubNav())
# Add stylesheet
# Use path if file exists
if os.path.exists(style):
style_path = style
logging.debug('Using custom style %s' % style)
# Otherwise use preset style
else:
style_name = style if style.endswith('.css') else style + '.css'
style_path = os.path.join(STYLES_PATH, style_name)
if not os.path.exists(style_path):
raise Exception('%s is not a preset style' % style)
logging.debug('Using preset style %s' % style)
with open(style_path) as f:
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/default.css",
media_type="text/css",
content=f.read())
book.add_item(nav_css)
book.spine = ['nav'] + chapters
return book
def __init__(self, config, callbacks):
self.config = config
self.callbacks = callbacks
self.chapters = []
self.title = config.book.title
self.author = config.book.author
with open(config.book.css_filename, 'r') as css:
self.css = epub.EpubItem(uid='default', file_name="style/"+config.book.css_filename, media_type="text/css", content=css.read())
def define_css(book_id, new_book_id):
logger.info('Defining css for book book_id: %s and new_book_id:%s',
book_id, new_book_id)
style = 'BODY {color: white;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
return nav_css
async def download_img(self, url, sem):
async with sem:
filename = os.path.basename(url)
data = requests.get(url).content
file_type = filename.split('.')[-1]
item_img = epub.EpubItem(file_name="images/%s" % filename,
media_type="image/%s" % file_type, content=data)
self.book.add_item(item_img)
self.logger.info('<-Done image: ' + url)
def _add_css(self):
# define CSS style
style = 'BODY {color: white;}'
nav_css = epub.EpubItem(uid="style_nav",
file_name="style/nav.css",
media_type="text/css",
content=style)
self.book.add_item(nav_css)
