def set_info(self, info):
self.info.update(info)
if self.kind == Type.question:
self.epub.title = u'知乎问题集锦({})'.format(info['title'])
self.epub.id = info['id']
elif self.kind == Type.answer:
self.epub.title = u'知乎回答集锦({})'.format(info['title'])
self.epub.id = info['id']
elif self.kind == Type.article:
self.epub.title = u'知乎专栏文章集锦({})'.format(info['title'])
self.epub.id = info['id']
if self.kind == Type.topic:
self.epub.title = u'话题_{}({})'.format(info['title'], info['topic_id'])
self.epub.id = info['topic_id']
if self.kind == Type.collection:
self.epub.title = u'收藏夹_{}({})'.format(info['title'], info['collection_id'])
self.epub.id = info['collection_id']
if self.kind == Type.author:
self.epub.title = u'作者_{}({})'.format(info['name'], info['author_id'])
self.epub.id = info['author_id']
if self.kind == Type.column:
self.epub.title = u'专栏_{}({})'.format(info['name'], info['column_id'])
self.epub.id = info['column_id']
self.epub.title = Match.fix_filename(self.epub.title)
return
def create_book(self):
# 确定文件信息
title = Match.fix_filename(self.book_title)
if self.is_split:
title = self.book_title + u'_卷{}'.format(self.chapter_no)
# 先切换到电子书临时资源目录下
Path.chdir(Path.book_pool_path)
epub = Epub(title)
for task_result in self.task_result_list:
chapter_src = ''
# info_page
if task_result.task.task_type == Type.question:
chapter_src = self.generate_question_info_page(task_result.info_page)
elif task_result.task.task_type == Type.answer:
chapter_src = self.generate_question_info_page(task_result.info_page)
elif task_result.task.task_type == Type.collection:
chapter_src = self.generate_collection_info_page(task_result.info_page)
elif task_result.task.task_type == Type.topic:
chapter_src = self.generate_topic_info_page(task_result.info_page)
elif task_result.task.task_type == Type.author:
chapter_src = self.generate_author_info_page(task_result.info_page)
elif task_result.task.task_type == Type.column:
chapter_src = self.generate_column_info_page(task_result.info_page)
elif task_result.task.task_type == Type.article:
chapter_src = self.generate_article_info_page(task_result.info_page)
epub.create_chapter(chapter_src, task_result.get_title())
for question in task_result.question_list:
# 添加图片文件
for filename in question.img_filename_list:
epub.add_image(Path.image_pool_path + '/' + filename)
question_src = self.generate_question_page(question)
epub.add_html(question_src, question.question_info.title)
for column in task_result.column_list:
# 添加图片文件
for filename in column.img_filename_list:
epub.add_image(Path.image_pool_path + '/' + filename)
for article in column.article_list:
article_src = self.generate_article_page(article)
epub.add_html(article_src, article.title)
epub.finish_chapter()
epub.set_creator(u'ZhihuHelp1.8.0')
epub.set_language(u'zh-cn')
epub.set_book_id()
epub.set_output_path(Path.result_path)
epub.add_css(Path.base_path + u'/www/css/markdown.css')
epub.add_css(Path.base_path + u'/www/css/customer.css')
epub.add_css(Path.base_path + u'/www/css/normalize.css')
epub.add_css(Path.base_path + u'/www/css/bootstrap.css')
epub.create()
Path.reset_path()
return
def parse_article_title(self):
u"""
获得博文的标题
:return:
"""
article_title = ''
article_id = ''
list_pcyc_l_ = self.dom.find_all('div', class_="p_title")
for tgo_tgo_ in list_pcyc_l_:
for link in tgo_tgo_.findAll('a'):
article_id = str(link.get('href')).split('/')[1]
article_title = Match.fix_filename(tgo_tgo_.text)
# article_title +
return article_title + str(self.getArticleIndex()).strip()
def parse_article_title(self):
u"""
获得博文的标题
:return:
"""
article_title = ''
article_id = ''
list_pcyc_l_ = self.dom.find_all('div', class_="p_title")
for tgo_tgo_ in list_pcyc_l_:
for link in tgo_tgo_.findAll('a'):
article_id = str(link.get('href')).split('/')[1]
article_title = Match.fix_filename(tgo_tgo_.text)
# article_title +
if self.parse_author_id() != self.account_id:
article_title = u"跟帖:{}".format(article_title.strip())
return article_title.strip()
def get_title(self):
title = '_'.join([book.epub.title for book in self.book_list])
title = Match.fix_filename(title) # 移除特殊字符
return title
def get_title(self):
title = '_'.join([book.epub.title for book in self.book_list])
title = Match.fix_filename(title) # 移除特殊字符
return title
def create_book(self):
# 确定文件信息
title = Match.fix_filename(self.book_title)
if self.is_split:
title = self.book_title + u'_卷{}'.format(self.chapter_no)
# 先切换到电子书临时资源目录下
Path.chdir(Path.book_pool_path)
epub = Epub(title)
for task_result in self.task_result_list:
chapter_src = ''
# info_page
if task_result.task.task_type == Type.question:
chapter_src = self.generate_question_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.answer:
chapter_src = self.generate_question_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.collection:
chapter_src = self.generate_collection_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.topic:
chapter_src = self.generate_topic_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.author:
chapter_src = self.generate_author_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.column:
task_result.info_page.article_count = (
task_result.column_list[0].article_list).__len__()
chapter_src = self.generate_column_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.article:
chapter_src = self.generate_article_info_page(
task_result.info_page)
epub.create_chapter(chapter_src, task_result.get_title())
for question in task_result.question_list:
# 添加图片文件
for filename in question.img_filename_list:
epub.add_image(Path.image_pool_path + '/' + filename)
question_src = self.generate_question_page(question)
epub.add_html(question_src, question.question_info.title)
for column in task_result.column_list:
# 添加图片文件
for filename in column.img_filename_list:
epub.add_image(Path.image_pool_path + '/' + filename)
for article in column.article_list:
article_src = self.generate_article_page(article)
epub.add_html(article_src, article.title)
epub.finish_chapter()
href = self.task_result_list[0].info_page.image_url
if len(href) > 0:
print href
if href:
content = Http.get_content(
url=href, timeout=Config.timeout_download_picture)
if not content:
Debug.logger.debug(u'图片『{}』下载失败'.format(href))
content = ''
else:
Debug.print_in_single_line(u'图片{}下载完成'.format(href))
else:
# 当下载地址为空的时候，就没必要再去下载了
content = ''
if content.__len__() > 10:
filename = Path.image_pool_path + '/' + 'cover.jpg'
with open(filename, 'wb') as image:
image.write(content)
epub.add_cover_image(filename)
else:
epub.add_cover_image('/Users/ex-liyan010/Desktop/cover.png')
# epub.add_cover_image('/Users/ex-liyan010/Desktop/cover.png')
epub.set_creator(u'macbookpro2100')
epub.set_language(u'zh-cn')
epub.set_book_id()
epub.set_output_path(Path.result_path)
epub.add_css(Path.base_path + u'/www/css/markdown.css')
epub.add_css(Path.base_path + u'/www/css/customer.css')
epub.add_css(Path.base_path + u'/www/css/normalize.css')
epub.add_css(Path.base_path + u'/www/css/bootstrap.css')
epub.create()
Path.reset_path()
return
def create_book(self):
# 确定文件信息
title = Match.fix_filename(self.book_title)
if self.is_split:
title = self.book_title + u'_卷{}'.format(self.chapter_no)
# 先切换到电子书临时资源目录下
Path.chdir(Path.book_pool_path)
epub = Epub(title)
for task_result in self.task_result_list:
chapter_src = ''
# info_page
if task_result.task.task_type == Type.question:
chapter_src = self.generate_question_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.answer:
chapter_src = self.generate_question_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.collection:
chapter_src = self.generate_collection_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.topic:
chapter_src = self.generate_topic_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.author:
chapter_src = self.generate_author_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.column:
chapter_src = self.generate_column_info_page(
task_result.info_page)
elif task_result.task.task_type == Type.article:
chapter_src = self.generate_article_info_page(
task_result.info_page)
epub.create_chapter(chapter_src, task_result.get_title())
for question in task_result.question_list:
# 添加图片文件
for filename in question.img_filename_list:
epub.add_image(Path.image_pool_path + '/' + filename)
question_src = self.generate_question_page(question)
epub.add_html(question_src, question.question_info.title)
for column in task_result.column_list:
# 添加图片文件
for filename in column.img_filename_list:
epub.add_image(Path.image_pool_path + '/' + filename)
for article in column.article_list:
article_src = self.generate_article_page(article)
epub.add_html(article_src, article.title)
epub.finish_chapter()
epub.set_creator(u'ZhihuHelp1.8.0')
epub.set_language(u'zh-cn')
epub.set_book_id()
epub.set_output_path(Path.result_path)
epub.add_css(Path.base_path + u'/www/css/markdown.css')
epub.add_css(Path.base_path + u'/www/css/customer.css')
epub.add_css(Path.base_path + u'/www/css/normalize.css')
epub.add_css(Path.base_path + u'/www/css/bootstrap.css')
epub.create()
Path.reset_path()
return