def __init__(self,
recipe_kind='Notset',
read_list='ReadList.txt',
url=None,
debug=False):
u"""
配置文件使用$符区隔，同一行内的配置文件归并至一本电子书内
:param recipe_kind:
:param read_list: default value: ReadList.txt
:param url:
:param debug:
:return:
"""
self.recipe_kind = recipe_kind
self.read_list = read_list
self.url = url
log.warning_log(u"website type: " + str(self.recipe_kind) + '\n')
import logging
if debug is True:
Debug.logger.setLevel(logging.DEBUG)
else:
Debug.logger.setLevel(logging.INFO)
Debug.logger.debug(u"read_list: " + str(self.read_list))
Debug.logger.debug(u"url: " + str(self.url))
Debug.logger.debug(u"recipe type:" + str(recipe_kind))
Path.init_base_path(recipe_kind) # 设置路径
Path.init_work_directory() # 创建路径
self.init_database() # 初始化数据库
Config._load()
return
def init_database():
if Path.is_file(Path.db_path):
Debug.logger.debug(u"Connect to the database...")
Debug.logger.debug(u"db_path: " + str(Path.db_path))
DB.set_conn(sqlite3.connect(Path.db_path))
else:
Debug.logger.debug(u"Create db file...")
DB.set_conn(sqlite3.connect(Path.db_path))
with open(Path.sql_path) as sql_script:
DB.cursor.executescript(sql_script.read())
DB.commit()
def create_book(command, counter):
Path.reset_path()
Debug.logger.info(u"Ready to make No.{} e-book".format(counter))
Debug.logger.info(u"Analyzes {} ".format(command))
task_package = UrlParser.get_task(command) # 分析命令
if not task_package.is_work_list_empty():
worker_factory(task_package.work_list) # 执行抓取程序
Debug.logger.info(u"Complete fetching from web")
file_name_set = None
if not task_package.is_book_list_empty():
Debug.logger.info(u"Start generating e-book from the database")
book = Book(task_package.book_list)
file_name_set = book.create()
if file_name_set is not None:
file_name_set2list = list(file_name_set)
file_name = '-'.join(file_name_set2list[0:3])
return file_name
return u"Oops! no epub file produced"
def create_book(self, book_package):
book_package.image_container.set_save_path(Path.image_pool_path)
book_package.image_container.start_download()
title = book_package.get_title()
Debug.logger.debug(u"title of the e-book:" + str(title))
if not title:
# 电子书题目为空时自动跳过
# 否则会发生『rm -rf / 』的惨剧
return
Path.chdir(Path.pwd_path + u'/e-books_tmp_source')
epub = Epub(title)
html_tmp_path = Path.html_pool_path + u'/'
image_tmp_path = Path.image_pool_path + u'/'
epub.set_creator(u'macbookpro2100')
epub.set_language(u'zh')
epub.set_book_id()
epub.set_output_path(Path.result_path)
epub.add_css(Path.in_base_path + u'/www/css/markdown.css')
epub.add_css(Path.in_base_path + u'/www/css/customer.css')
epub.add_css(Path.in_base_path + u'/www/css/normalize.css')
epub.add_css(Path.in_base_path + u'/www/css/bootstrap.css')
# epub.add_css(Path.in_base_path + u'/www/css/article.css') # TODO: 来自新浪,需要精简
for book in book_package.book_list:
page = book.page_list[0]
with open(html_tmp_path + page.filename, 'w') as html:
html.write(page.content)
if '_' in page.title:
page.title = ''.join(page.title.split('_')[1:]) # 删除章节前缀
epub.create_chapter(html_tmp_path + page.filename, page.title)
for page in book.page_list[1:]:
with open(html_tmp_path + page.filename, 'w') as html:
html.write(page.content)
epub.add_html(html_tmp_path + page.filename, page.title)
epub.finish_chapter()
for image in book_package.image_list:
epub.add_image(image_tmp_path + image['filename'])
epub.create()
Path.reset_path()
return
def create_book(self, book_package):
book_package.image_container.set_save_path(Path.image_pool_path)
book_package.image_container.start_download()
title = book_package.get_title()
Debug.logger.debug(u"title of the e-book:" + str(title))
if not title:
# 电子书题目为空时自动跳过
# 否则会发生『rm -rf / 』的惨剧
return
Path.chdir(Path.pwd_path + u'/e-books_tmp_source')
epub = Epub(title)
html_tmp_path = Path.html_pool_path + u'/'
image_tmp_path = Path.image_pool_path + u'/'
epub.set_creator(u'EEBookV0-1')
epub.set_language(u'zh')
epub.set_book_id()
epub.set_output_path(Path.result_path)
epub.add_css(Path.in_base_path + u'/www/css/markdown.css')
epub.add_css(Path.in_base_path + u'/www/css/customer.css')
epub.add_css(Path.in_base_path + u'/www/css/normalize.css')
epub.add_css(Path.in_base_path + u'/www/css/bootstrap.css')
# epub.add_css(Path.in_base_path + u'/www/css/article.css') # TODO: 来自新浪,需要精简
for book in book_package.book_list:
page = book.page_list[0]
with open(html_tmp_path + page.filename, 'w') as html:
html.write(page.content)
if '_' in page.title:
page.title = ''.join(page.title.split('_')[1:]) # 删除章节前缀
epub.create_chapter(html_tmp_path + page.filename, page.title)
for page in book.page_list[1:]:
with open(html_tmp_path + page.filename, 'w') as html:
html.write(page.content)
epub.add_html(html_tmp_path + page.filename, page.title)
epub.finish_chapter()
for image in book_package.image_list:
epub.add_image(image_tmp_path + image['filename'])
epub.create()
Path.reset_path()
return
def create_single_html_book(self, book_package):
title = book_package.get_title()
if not title:
# 电子书题目为空时自动跳过
# 否则会发生『rm -rf / 』的惨剧
return
Path.reset_path()
Path.chdir(Path.result_path)
Path.rmdir(u'./' + title)
Path.mkdir(u'./' + title)
Path.chdir(u'./' + title)
page = []
for book in book_package.book_list:
page += book.page_list
content = u' \r\n '.join([Match.html_body(x.content) for x in page]).replace(u'../images/', u'./images/')
with open(TemplateConfig.content_base_uri) as html:
content = html.read().format(title=title, body=content).replace(u'../style/', u'./')
with open(title + u'.html', 'w') as html:
html.write(content)
Path.copy(Path.html_pool_path + u'/../{}/OEBPS/images'.format(title), u'./images')
Path.copy(Path.www_css + u'/customer.css', u'./customer.css')
Path.copy(Path.www_css + u'/markdown.css', u'./markdown.css')
Path.copy(Path.www_css + u'/normalize.css', u'./normalize.css')
# Path.copy(Path.www_css + u'/article.css', u'./article.css') # TODO: 需要精简
Path.reset_path()
return title
def create_single_html_book(self, book_package):
title = book_package.get_title()
if not title:
# 电子书题目为空时自动跳过
# 否则会发生『rm -rf / 』的惨剧
return
Path.reset_path()
Path.chdir(Path.result_path)
Path.rmdir(u'./' + title)
Path.mkdir(u'./' + title)
Path.chdir(u'./' + title)
page = []
for book in book_package.book_list:
page += book.page_list
content = u' \r\n '.join([Match.html_body(x.content) for x in page]).replace(u'../images/', u'./images/')
with open(TemplateConfig.content_base_uri) as html:
content = html.read().format(title=title, body=content).replace(u'../style/', u'./')
with open(title + u'.html', 'w') as html:
html.write(content)
Path.copy(Path.html_pool_path + u'/../{}/OEBPS/images'.format(title), u'./images')
Path.copy(Path.www_css + u'/customer.css', u'./customer.css')
Path.copy(Path.www_css + u'/markdown.css', u'./markdown.css')
Path.copy(Path.www_css + u'/normalize.css', u'./normalize.css')
# Path.copy(Path.www_css + u'/article.css', u'./article.css') # TODO: 需要精简
Path.reset_path()
return title